Is this you? Claim this profile to correct it, add a bio and choose the work people see first.
Claim this profileAcademic lineage
Possible advisorsa guess from early papers, not confirmed
- Yoshihide AoshimaSuggested from co-authorship
Is this you? Claim this profile to confirm or dismiss it.
Works420 from public data
- Maximum Classifier Discrepancy for Unsupervised Domain Adaptation2,161
A new approach that attempts to align distributions of source and target by utilizing the task-specific decision boundaries by maximizing the discrepancy between two classifiers' outputs to detect target samples that are far from the support of the source.
- 1,232
- Neural 3D Mesh Renderer1,184
This work proposes an approximate gradient for rasterization that enables the integration of rendering into neural networks and performs gradient-based 3D mesh editing operations, such as 2D-to-3D style transfer and 3D DeepDream, with 2D supervision for the first time.
- Strong-Weak Distribution Alignment for Adaptive Object Detection788
This work proposes an approach for unsupervised adaptation of object detectors from label-rich to label-poor domains which can significantly reduce annotation costs associated with detection, and designs the strong domain alignment model to only look at local receptive fields of the feature map.
- 725
- Open Set Domain Adaptation by Backpropagation622
This paper proposes a method for an open set domain adaptation scenario, which utilizes adversarial training, and allows to extract features that separate unknown target from known target samples.
- 383
- Domain Generalization Using a Mixture of Multiple Latent Domains369
This paper proposes a method that iteratively divides samples into latent domains via clustering, and which trains the domain-invariant feature extractor shared among the divided latent domains through adversarial learning, which outperforms conventional domain generalization methods, including those that utilize domain labels.
- Frequency-Aware Feature Fusion for Dense Image Prediction325
Comprehensive visualization and quantitative analysis demonstrate that FreqFusion effectively improves feature consistency and sharpens object boundaries, and extensive experiments across various dense prediction tasks confirm its effectiveness.
- Neural Articulated Radiance Field249
Neural Articulated Radiance Field is a novel deformable 3D representation for articulated objects learned from images that is fully differentiable and can be trained from images with pose annotations through the use of an autoencoder.
- Between-Class Learning for Image Classification228
This paper proposes a simple mixing method using internal divisions, which surprisingly proves to significantly improve performance and proposes a mixing method that treats the images as waveforms, which leads to a further improvement in performance.
- Image Generation From Small Datasets via Batch Statistics Adaptation212
This work proposes a new method for transferring prior knowledge of the pre-trained generator, which is trained with a large dataset, to a small dataset in a different domain, and can generate higher quality images compared to previous methods without collapsing.
- 207
- Multispectral Object Detection for Autonomous Vehicles201
The results show that each component in the multispectral image was individually useful for the task of object detection when applied to different types of objects, and the mean average precision (mAP) of mult ispectral object detection is 13% higher than that of RGB-only object detection.
- Lepard: Learning partial point cloud matching in rigid and deformable scenes200
Lepard, a Learning based approach for partial point cloud matching in rigid and deformable scenes with key characteristics are an architecture that disentangles point cloud representation into feature space and 3D position space and a position encoding method that explicitly reveals 3D relative distance information through the dot product of vectors.
- 190
- Multitask AET with Orthogonal Tangent Regularity for Dark Object Detection188
This work proposes a novel multitask auto encoding transformation (MAET) model which is able to explore the intrinsic pattern behind illumination translation and achieves the object detection task by decoding the bounding box coordinates and classes.
- Goal-Oriented Gaze Estimation for Zero-Shot Learning171
This work introduces a novel goal-oriented gaze estimation module (GEM) to improve the discriminative attribute localization based on the class-level attributes for ZSL and implies the promising benefits of collecting human gaze dataset and automatic gaze estimation algorithms on high-level computer vision tasks.
- Online growing neural gas for anomaly detection in changing surveillance scenes118
A neural network based model called online Growing Neural Gas (online GNG) to perform an unsupervised learning to perform anomaly detection and effectively reduces the false alarms and leak detections caused by model aging which frequently happens in changing surveillance scenes.
- 100
- 97
- Revisiting Domain Generalized Stereo Matching Networks from a Feature Consistency Perspective91
A simple pixel-wise contrastive learning across the viewpoints for stereo matching performance to unseen domains is proposed, which achieves superior performance over several state-of-the-art networks.
- GPAvatar: Generalizable and Precise Head Avatar from Image(s)89
A framework named GPAvatar is proposed that reconstructs 3D head avatars from one or several images in a single forward pass and introduces a dynamic point-based expression field driven by a point cloud to precisely and effectively capture expressions.
- Learning View Priors for Single-View 3D Reconstruction88
This work proposes to train a discriminator that learns prior knowledge regarding possible views to reconstruct shapes that look reasonable from any viewpoint and outperforms current state-of-the-art methods on both synthetic and natural image datasets.
- Image Reconstruction from Bag-of-Visual-Words86
This work uses a large-scale image database to estimate the spatial arrangement of local descriptors and proposes a heuristic but efficient method to optimize it, which can reconstruct the original images, although the image features lack spatial information and include quantization errors.
- 84
- 80
- Expert Knowledge-Aware Image Difference Graph Representation Learning for Difference-Aware Medical Visual Question Answering79
A novel Chest-Xray Different Visual Question Answering (VQA) task that attempts to answer several questions on both diseases and, more importantly, the differences between them, and a novel expert knowledge-aware graph representation learning model to address this task.
- You Only Need 90K Parameters to Adapt Light: A Light Weight Transformer for Image Enhancement and Exposure Correction79
This work proposes a lightweight fast Illumination Adaptive Transformer (IAT) which comprises two transformer-style branches: local estimation branch and global ISP branch which could also conduct both object detection and semantic segmentation under various light conditions.
- Label-Noise Robust Generative Adversarial Networks73
This work proposes a novel family of GANs called label-noise robust GGANs (rGANs), which, by incorporating a noise transition model, can learn a clean label conditional generative distribution even when training labels are noisy.
- 72
- SayTap: Language to Quadrupedal Locomotion71
An approach to use foot contact patterns as an interface that bridges human commands in natural language and a locomotion controller that outputs these low-level commands results in an interactive system for quadrupedal robots that allows the users to craft diverse locomotion behaviors flexibly.
- Pose Graph optimization for Unsupervised Monocular Visual Odometry71
This paper proposes a hybrid VO system which combines an unsupervised monocular VO called NeuralBundler with a pose graph optimization back-end and proposes a novel pose cycle consistency loss to relieve the tensions in the windowed pose graph, leading to improved performance and robustness.
- Watch It Move: Unsupervised Discovery of 3D Joints for Re-Posing of Articulated Objects68
This work proposes to learn both the appearance and the structure of previously unseen articulated objects by ob-serving them move from multiple views, with no joints annotation supervision, or information about the structure.
- Spatio-Temporal Person Retrieval via Natural Language Queries68
To retrieve the tube of the person described by a given natural language query, this paper designs a model that combines methods for spatio-temporal human detection and multimodal retrieval and demonstrates the versatility of the model by applying it to two other important tasks.
- 67
- Recognizing Activities of Daily Living with a Wrist-Mounted Camera65
A novel dataset and a novel algorithm for recognizing activities of daily living (ADL) from a first-person wearable camera and a discriminative video representation that retains spatial and temporal information after encoding the frame descriptors extracted by convolutional neural networks (CNN).
- Hierarchical Video Generation From Orthogonal Information: Optical Flow and Texture63
This study focuses on the motion and appearance information as two important orthogonal components of a video, and proposes Flow-and-Texture-Generative Adversarial Networks (FTGAN) consisting of FlowGAN and TextureGAN, which generates more plausible motion videos and achieves significantly improved performance for unsupervised action classification in comparison to previous GAN works.
- Dialog System Using Real-Time Crowdsourcing and Twitter Large-Scale Corpus62
A dialog system that creates responses based on a large-scale dialog corpus retrieved from Twitter and real-time crowd-sourcing that replies with the utterance from the database that is most similar to the user input is proposed.
- 61
- 61
- DualNet: Domain-invariant network for visual question answering60
A method is proposed called DualNet that demonstrates performance that is invariant to the differences in real and abstract scene domains, and Experimental results show that DualNet outperforms state-of-the-art methods, especially for the abstract images category.
- Fully Spiking Variational Autoencoder59
The Fully Spiking Variational Autoencoder is built, the first to build a VAE only with SNN layers, and confirmed that it can generate images with the same or better quality compared to conventional ANNs.
- 57
- 56
- The Sound Demixing Challenge 2023 – Music Demixing Track55
A formalization of the errors that can occur in the design of a training dataset for MSS systems and two new datasets that simulate such errors are introduced: SDXDB23_LabelNoise and SDXDB23_Bleeding.
- Multi-Stage Pathological Image Classification Using Semantic Segmentation54
This paper proposes a new model structure combining the patch-based classification model and whole slide-scale segmentation model in order to improve the prediction performance of automatic pathological diagnosis and applies it to the tumor/normal prediction on WSIs and the classification performance is improved compared with the conventional patch- based method.
- Development of a Tiny Orientation Estimation Device to Operate under Motion and Magnetic Disturbance53
Using simulations and the realized device, the proposed algorithm stably estimated the orientation in the presence of motion and magnetic disturbances and a Square-Root Central Difference Kalman Filter was the best method considering stability, accuracy, and calculation cost.
- Automatic diagnosis of neurological diseases using MEG signals with a deep neural network52
MNet, a novel deep neural network to classify multiple neurological diseases using resting-state magnetoencephalography (MEG) signals is developed and the results suggest that this technique would be useful for developing a classifier that will improve neurological diagnoses and allow high specificity in identifying diseases.
- Improving Local Descriptors by Embedding Global and Local Spatial Information50
This paper proposed a general framework to improve any local descriptors by embedding both local and global spatial information into the descriptors, and evaluated the effectiveness of the proposed method from the viewpoint of speed and accuracy.
- 48
- 48
- Automatic detection of different types of small-bowel lesions on capsule endoscopy images using a newly developed deep convolutional neural network46
A new artificial intelligence system able to diagnose multiple types of lesions, including erosions and ulcers, vascular lesions, and tumors, in images from wireless capsule endoscopy is developed and validated.
- 46
- 46
- Interpretable medical image Visual Question Answering via multi-modal relationship graph learning45
A novel VQA method is proposed by constructing three different relationship graphs: spatial relationships, semantic relationships, and implicit relationship graphs on the image regions, questions, and semantic labels, which leveraged graph attention to learn the logical reasoning paths for different questions.
- 45
- Learning to Explain With Complemental Examples44
This paper proposes a novel framework to generate complemental explanations, on which the joint distribution of the variables to explain, and those to be explained is parameterized by three different neural networks: predictor, linguistic explainer, and example selector.
- Parental age and gene expression profiles in individual human blastocysts44
Analyzing single-embryo RNA-seq analysis on human blastocysts fertilized by intracytoplasmic sperm injection suggests that epigenetic modifications of the oocyte genome may change with parental age and be transmitted to the next generation.
- 44
- Luminance-GS: Adapting 3D Gaussian Splatting to Challenging Lighting Conditions with View-Adaptive Curve Adjustment43
Luminance-GS is introduced, a novel approach to achieving high-quality novel view synthesis results under diverse challenging lighting conditions using 3DGS that provides real-time rendering speed with improved reconstruction quality.
- Multimodal Explanations by Predicting Counterfactuality in Videos43
The effectiveness of the proposed explanation model, trained to predict the counterfactuality for possible combinations of multimodal information in a post-hoc manner, is demonstrated by comparison with a baseline of the action recognition datasets extended for this task.
- Decomposing normal and abnormal features of medical images for content-based image retrieval of glioma imaging40
This study proposes a neural network architecture to decompose the semantic components of medical images into two latent codes: normal anatomy code and abnormal anatomy code, and provides a flexible CBIR framework by handling the decomposed features with qualitatively and quantitatively remarkable results.
- Gastric Cancer Detection from Endoscopic Images Using Synthesis by GAN39
This paper proposes a method that lessens this dataset bias by generating new images using a generative model, which synthesizes an image from two images in a dataset.
- Viewpoint-Aware Video Summarization39
A novel variant of video summarization, namely building a summary that depends on the particular aspect of a video the viewer focuses on, is introduced, and a novel dataset is developed to investigate how well the generated summary reflects the underlying viewpoint.
- 39
- 39
- 39
- ARTalk: Speech-Driven 3D Head Animation via Autoregressive Model38
A novel autoregressive model that achieves real-time generation of highly synchronized lip movements and realistic head poses and eye blinks by learning a mapping from speech to a multi-scale motion codebook by learning a mapping from speech to a multi-scale motion codebook.
- Rethinking masked image modelling for medical image representation38
This work proposes and introduces two mutual comprehensive masking strategies, knowledge-driven masking (KDM), and sentence-driven masking (SDM), and substantially outperforms ImageNet pre-training, MIM-based pre-training, and medical image-report pre-training counterparts.
- 37
- 37
- 36
- Noise Robust Generative Adversarial Networks36
Noise robust GANs are proposed, which can learn a clean image generator even when training images are noisy, and the applicability of NR-GANs in image denoising is shown, which demonstrates the effectiveness of the network in noise robust image generation.
- Voxelized Shape and Color Histograms for RGB-D35
This paper presents an approach that is capable of efficiently capturing both the geometric and visual appearance of common objects of daily use into one feature, and showcases this feature’s applicability for the purpose of classifying objects in cluttered scenes with obstructions.
- 34
- Beyond caption to narrative: Video captioning with multiple sentences33
This work attempts to generate video captions that convey richer contents by temporally segmenting the video with action localization, generating multiple captions from multiple frames, and connecting them with natural language processing techniques in order to generate a story-like caption.
- 33
- 33
- Gradual Source Domain Expansion for Unsupervised Domain Adaptation32
The proposed gradual source domain expansion (GSDE) algorithm, which trains the UDA task several times from scratch, each time reinitializing the network weights, but each time expands the source dataset with target data, and uses pseudo-source samples, which helps align the two domains better.
- WebDNN30
An installation-free web browser-based DNN execution framework, WebDNN, that optimizes the trained DNN model to compress model data and accelerate the execution and achieves more than two-hundred times the unusual acceleration.
- 30
- A deep learning model for the detection of various dementia and MCI pathologies based on resting-state electroencephalography data: A retrospective multicentre study29
This study evaluates the generalizability of a DCNN trained on EEG data from a single hospital and suggests a potential for identifying shared EEG signatures between MCI and dementia, contributing to the field's understanding of their common pathophysiological mechanisms.
- Efficient image annotation for automatic sentence generation29
The proposed framework, although simple and scalable, can generate sentences from images with no semantic knowledge and is applicable to image annotation, and it achieves state-of-the-art performance.
- 29
- 28
- 28
- Style-NeRF2NeRF: 3D Style Transfer from Style-Aligned Multi-View Images27
A simple yet effective pipeline for stylizing a 3D scene, harnessing the power of 2D image diffusion models, that can transfer diverse artistic styles to real-world 3D scenes with competitive quality is proposed.
- 27
- 27
- 26
- Learning to Optimize Non-Rigid Tracking25
This paper upgrades the tracking objective by integrating an alignment data term on deep features which are learned end-to-end through CNN, and bridges the gap between the preconditioning technique and learning method by introducing a ConditionNet which is trained to generate a preconditionser such that PCG can converge within a small number of steps.
- Spherical Image Generation from a Single Image by Considering Scene Symmetry24
A method for generating a spherical image from a single NFOV image and controlling the degree of freedom of the generated regions using the scene symmetry, which is a basic property of the global structure of spherical images, such as rotational symmetry, plane symmetry, and asymmetry.
- Learning Agile Locomotion via Adversarial Training24
This paper presents a multi-agent learning system, in which a quadruped robot learns to chase another robot (adversary) while the latter learns to escape, and shows that the locomotion controller learned with adversarial training significantly outperforms carefully designed baselines.
- Clothing Retrieval Based on Local Similarity with Multiple Images24
A novel clothing retrieval system considering local similarity, where users can retrieve their desired clothes which are globally similar to an image and partially similar to another image through a method of coding global features by merging local descriptors extracted from multiple images.
- RealX3D: A Physically-Degraded 3D Benchmark for Multi-view Visual Restoration and Reconstruction23
This work introduces RealX3D, a real capture benchmark for multi-view restoration and reconstruction under real-world degradations, organized into four families spanning nine controlled settings that include motion and defocus blur, low-light, view-varying exposure, smoke, dynamic occlusion, and reflection.
- 22
- Luigi: Large-scale histopathological image retrieval system using deep texture representations22
A web application, the Luigi system, which retrieves similar histopathological images from various cancer cases similar to those of the query image using deep texture representations computed with a pre-trained convolutional neural network as an image feature in conjunction with an approximate nearest neighbor search method.
- Automatic sentence generation from images22
This work proposes a novel approach to generate a sentential caption for the input image by summarizing captions of images that are similar to an input image and demonstrates that the proposed method can generate sentential captions.
- 21
- Blur, Noise, and Compression Robust Generative Adversarial Networks21
This work proposes blur, noise, and compression robust GAN (BNCR-GAN) that can learn a clean image generator directly from degraded images without knowledge of degradation parameters, and introduces masking architectures adjusting degradation strength values in a data-driven manner using bypasses before and after degradation.
- 21
- GRAM: Scalable Generative Models for Graphs with Graph Attention Mechanism.20
This paper proposes GRAM, a generative model for graphs that is scalable in all three contexts, especially in training, and aims to achieve scalability by employing a novel graph attention mechanism, formulating the likelihood of graphs in a simple and general manner.
- Texture-Based Classification of Significant Stenosis in CCTA Multi-view Images of Coronary Arteries20
This paper presents a novel method for automatic classification of significant stenosis from coronary CT angiography scans (CCTA), which leverages a state-of-the-art feature extractor for texture classification that describes effectively the appearance ofsignificant stenosis.
- Visual Question Generation for Class Acquisition of Unknown Objects20
A method for generating questions about unknown objects in an image, as means to get information about classes that have not been learned, and the experimental results via human evaluation show that the method can successfully get informationAbout unknown objectsIn an image dataset.
- Semi-Supervised Learning in Medical Images Through Graph-Embedded Random Forest19
A novel semi-supervised learning algorithm to boost the performance of random forest under limited labeled data by exploiting the local structure of unlabeled data and replacing it with a graph-embedded entropy which is more reliable for insufficient labeled data scenario.
- 19
- Image Captioning with Sentiment Terms via Weakly-Supervised Sentiment Dataset18
The experimental results show that the method can generate image captions with sentiment terms that are more compatible with the images than solely relying on features devoted to object classification, while capable of preserving the semantics.
- 18
- Causality quantification and its applications18
The proposed method can represent the strength of causality as the number of bits, whether each of two time series is symbolic or numerical, and can quantify causality even from a small number of samples.
- Improved Object Detection Artificial Intelligence Using the Revised RetinaNet Model for the Automatic Detection of Ulcerations, Vascular Lesions, and Tumors in Wireless Capsule Endoscopy17
A new version of an AI-based diagnostic model for the multiclass identification of small bowel lesions in WCE images to help endoscopists appropriately diagnose small intestine diseases in daily clinical practice is developed.
- K-VQG: Knowledge-aware Visual Question Generation for Common-sense Acquisition17
This work constructed a novel knowledge-aware VQG dataset called K-VQG, this is the first large, humanly annotated dataset in which questions regarding images are tied to structured knowledge, and developed a new V QG model that can encode and use knowledge as the target for a question.
- 17
- Attention Transfer (ANT) Network for View-invariant Action Recognition17
The proposed AttentioN Transfer (ANT) Network transfers attention from the reference view to arbitrary views, which correctly emphasize crucial body joints and their relations for view-invariant representation and recognition.
- 17
- 17
- Interactive Video Retrieval with Dialog16
This work proposes a system to retrieve videos by asking questions about the content of the videos, and leveraging the user’s responses to the questions and the dialog history, and confirmed the usefulness of the proposed system through experiments using the dataset called AVSD.
- 16
- How narratives move your mind: A corpus of shared-character stories for connecting emotional flow and interestingness16
Crowdsourced volunteers label stories with the emotions of the two characters and those of readers, and empirically analyze the relationship between emotions and interestingness show that a story’s score has a stronger relationship to the readers’ emotions than the characters' emotions.
- Aleth-NeRF: Low-light Condition View Synthesis with Concealing Fields15
The proposed method, Aleth-NeRF, directly learns from the dark image to understand volumetric object representation and concealing field under priors and can render a single or multi-view well-lit image(s) and gain superior performance over other 2D low-light enhancement methods.
- Sketch-based semantic retrieval of medical images15
A sketch-based medical image retrieval (SBMIR) system that enables users to find images of interest without the need for example images, and provides on-demand, customizable medical image retrieval, thereby expanding the utility of medical image databases.
- 15
- 15
- 15
- Improved Dense Trajectory with Cross Streams15
A new local descriptor that pools a new convolutional layer obtained from crossing two networks along iDT is proposed that has achieved state-of-the-art performance on ordinal action recognition datasets, 92.3% on UCF101, and 66.2% on HMDB51.
- Evaluation of dimensionality reduction methods for image auto-annotation15
This paper investigates several linear dimensionality reduction methods for efficient image annotation and obtains a small representation preserving (and hopefully improving) the semantic distance of a visual feature.
- Development of a Diagnostic Artificial Intelligence Tool for Lateral Lymph Node Metastasis in Advanced Rectal Cancer14
Although both baseline and pre-surgery images provided good accuracy for diagnosing lateral lymph node metastases, the accuracy of pre-Surgery images was better than that of baseline images.
- Information bottleneck and selective noise supervision for zero-shot learning14
This work proposes a novel bidirectional embedding based generative model with a tight visual-semantic coupling constraint that outperforms the state-of-the-art methods in different ZSL settings on most benchmark datasets.
- 14
- Point Cloud Based Reinforcement Learning for Sim-to-Real and Partial Observability in Visual Navigation14
This work proposes a method that learns on an observation space constructed by point clouds and environment randomization, generalizing among robots and simulators to achieve sim-to-real, while also addressing partial observability.
- 14
- 14
- 14
- 14
- R2-Dreamer: Redundancy-Reduced World Models without Decoders or Augmentation13
R2-Dreamer is a decoder-free MBRL framework with a self-supervised objective that serves as an internal regularizer, preventing representation collapse without resorting to Data Augmentation, and suggests that an effective internal regularizer can enable versatile, high-performance decoder-free MBRL.
- HyperVQ: MLR-based Vector Quantization in Hyperbolic Space13
This work introduces HyperVQ, a novel approach that formulates VQ as a hyperbolic Multinomial Logistic Regression (MLR) problem, leveraging the exponential volume growth in hyperbolic space to mitigate collapse and improve cluster separability.
- Development and multi‐institutional validation of an artificial intelligence‐based diagnostic system for gastric biopsy13
MSP AI‐G had high diagnostic accuracy and robustness in multi‐institutions, and when pathologists selectively review specimens in which pathologist’s diagnosis and AI prediction are discordant, the requirement of a secondary review process is significantly less compared with reviewing all specimens by another pathologist.
- Bounding-Box Channels for Visual Relationship Detection13
The bounding-box channels are proposed, a novel architecture capable of relating the semantic, spatial, and image features strongly and capable of emphasizing the features in the object area for a better modeling of the relationships within objects.
- 13
- Efficient Shape Matching using Vector Extrapolation13
This work proposes the adoption of a vector extrapolation technique to accelerate convergence of correspondence problems under the quadratic assignment formulation for attributed graph matching (QAP), and provides a class of relaxations of the QAP under elastic net constraints to regulate the sparsity/complexity trade-off.
- ISI at ImageCLEF 2012: Scalable System for Image Annotation.13
This work trains linear classifiers for each label with an online multilabel learning, Passive-Aggressive with Averaged Pairwise Loss (PAAPL) to make the system scalable for the data amount.
- Dense sampling low-level statistics of local features13
A very simple but powerful scheme of boosting the performance of global image features, by densely sampling low-level statistics (mean and correlation) of local features by using a highly scalable learning and classification method which is substantially lighter than SVM.
- 13
- 13
- Precise Discrimination for Multiple Etiologies of Dementia Cases Based on Deep Learning with Electroencephalography12
Electroencephalography data of patients with dementia were successfully discriminated from HVs based on a novel deep learning algorithm, which could be useful for automatic screening and assisting diagnosis of dementia diseases.
- 12
- Coronary Wall Segmentation in CCTA Scans Via a Hybrid Net with Contours Regularization12
A novel boundary detection method for coronary arteries that focuses on the continuity and connectivity of the boundaries and can produce smooth closed boundaries outperforming the state-of-the-art accuracy is proposed.
- 12
- Probabilistic Partial Canonical Correlation Analysis12
This paper proposes a probabilistic interpretation of partial CCA and deriving a Bayesian estimation method based on the Probabilistic model, and demonstrates that the methods can stably estimate the model parameters, even in high dimensions or when there are a small number of samples.
- 11
- Unsupervised Pose-aware Part Decomposition for Man-Made Articulated Objects11
This paper proposes PPD (unsupervised Pose-aware Part Decomposition) to address a novel setting that explicitly targets man-made articulated objects with mechanical joints, considering the part poses in part parsing, and shows that it outperforms previous works in consistent part parsing of the articulated objects.
- Enhancement of Novel View Synthesis Using Omnidirectional Image Completion11
A method to learn the NeRF model using a subset of completed images that cover the target scene with less overlap of completed regions is introduced, which can be attributed to the maximum weight independent set problem.
- Leveraging Human Selective Attention for Medical Image Analysis with Limited Training Data11
This work designs a novel Auxiliary Attention Block (AAB) to allow information from SAN to be utilized by the backbone encoder to focus on selective areas, and shows that the estimated gaze probability map of the SAN is consistent with an actual gaze fixation map obtained by board-certified doctors.
- 11
- Multichannel Semantic Segmentation with Unsupervised Domain Adaptation11
This work proposes two approaches that can efficiently exploit multichannel inputs combined with an unsupervised domain adaptation (UDA) algorithm and demonstrates that the segmentation results were improved by using a multitask learning approach with a post-process and created a benchmark for this task.
- Probabilistic Semi-Canonical Correlation Analysis11
This paper proposes a novel model of probabilistic CCA by considering the mechanism of data missing, which enables widespread applications such as semi-supervised learning via partially labeled training samples and analysis of sensory data which are lacking under certain circumstances.
- 11
- Understanding images with natural sentences11
The proposed system uses general images and captions available on the web as training data to generate captions for new images and has scalability, which makes it useful with large-scale data.
- Image Annotation and Retrieval for Weakly Labeled Images Using Conceptual Learning11
A new image annotation and retrieval method for miscellaneous weakly labeled images is proposed, by combining higher-order local auto-correlation (HLAC) features and a framework of probabilistic canonical correlation analysis.
- 11
- 11
- People Taking Photos That Faces Never Share: Privacy Protection and Fairness Enhancement from Camera to User10
A novel lightweight Flow-based Face Encryption Method (FFEM) on the local embedded system privately connected to the camera, minimizing the risk of eavesdropping during data transmission and could protect privacy and enhance fairness with minimal effect on high-level downstream task.
- 10
- 10
- MIL at ImageCLEF 2013: Scalable System for Image Annotation10
This work trained linear classifiers by Passive- Aggressive with Averaged Pairwise Loss (PAAPL), an online multilabel learning method based on Passive-Aggressive, suitable for this task.
- High-Performance Image Annotation and Retrieval for Weakly Labeled Images Using Latent Space Learning10
A high speed and high accuracy image annotation and retrieval method for miscellaneous objects and scenes that combines the higher-order local auto-correlation (HLAC) features with the probabilistic canonical correlation analysis framework.
- RECOGNITION OF ACTIONS IN DAILY LIFE AND ITS PERFORMANCE ADJUSTMENT BASED ON SUPPORT VECTOR LEARNING10
Comparison with neural networks optimized by a back propagation algorithm and decision trees generated by C4.5 proves that the accuracy of recognition in the proposed method is superior to others.
- 10
- Sketch-based Medical Image Retrieval9
A novel sketch-basedmedical image retrieval (SBMIR) system that enables users to find images of interest without example images and achieves flexible medical image retrieval on demand, thereby expanding the utility of medical image databases.
- Long-Term Human Video Generation of Multiple Futures Using Poses9
A novel method for future human pose prediction capable of predicting multiple long-term futures using a novel approach based on unidimensional convolutional neural networks is proposed and outperforms other state-of-the-art works.
- 9
- Canonical contextual distance for large-scale image annotation and retrieval9
This paper proposes a method of image annotation and retrieval based on the new similarity measure, Canonical Contextual Distance, which effectively uses contexts of images estimated from multiple labels and learns the essential and discriminative latent space.
- 9
- Human Posture Probability Density Estimation Based on Actual Motion Measurement and Eigenpostures9
By applying the constructed human posture probability density for unprecedented posture detection and human motion segmentation, it is verified its effectiveness for many kinds of application.
- 9
- Content-Specific Humorous Image Captioning Using Incongruity Resolution Chain-of-Thought8
Pro-009 pose incongruity-resolution chain-of-thought chain-of-thought 010 (IRCoT) as a novel prompting framework that creates content-specific resolutions from fine details extracted from an image that suppress the output of generic resolutions.
- 8
- COMPASS: A creative support system that alerts novelists to the unnoticed missing contents8
Variable Number MPP (VN-MPP), a new MPP task that removes the restriction to predict multiple missing sentences or to judge whether there are no missing sentences in the first place, is proposed and a creative writing support system, COMPASS, is developed.
- Plug-and-Play Controller for Story Completion: A Pilot Study toward Emotion-aware Story Writing Assistance8
The authors of this paper have examined the use of natural language processing to address the problems of novelists from the perspective of practical creative writing, and found that unsupervised pre-trained large neural models of the sequence-to-sequence type are useful for this task.
- ViNTER: Image Narrative Generation with Emotion-Arc-Aware Transformer8
A novel method of image narrative generation called ViNTER (Visual Narrative Transformer with Emotion arc Representation), which takes “emotion arc” as input to capture a sequence of emotional changes.
- SplitFusion: Simultaneous Tracking and Mapping for Non-Rigid Scenes8
Experimental results show that the proposed approach can provide not only accurate environment maps but also well-reconstructed non-rigid targets, e.g., the moving humans.
- Estimating the Causal Effect from Partially Observed Time Series8
This work proposes a novel semi-supervised extension of probabilistic Partial CCA called semi-Bayesian Partial C CA that exploits the information in samples with missing values to prevent the overfitting of parameter estimation even when there are few complete samples.
- Generalized Bayesian Canonical Correlation Analysis with Missing Modalities8
This work proposes a method called Generalized Bayesian Canonical Correlation Analysis with Missing Modalities, which is strong against outliers and can reduce the amount of data necessary for the model learning even if features of modalities are high dimensional.
- 8
- Customized Image Narrative Generation via Interactive Visual Question Generation and Answering8
Experimental results demonstrate that the proposed customized image narrative generation task can generate a variety of descriptions from single image that cover a wider range of topics than conventional models, while being customizable to the target user of interaction.
- 8
- 8
- Graphical Gaussian Vector for Image Categorization8
This paper proposes a novel image representation called a Graphical Gaussian Vector (GGV), which is a counterpart of the codebook and local feature matching approaches and obtains better performance over the state-of-the-art methods in the standard object recognition datasets and comparable performance in the scene dataset.
- Efficient multi-modal retrieval in conceptual space8
This paper proposes a new, efficient retrieval system for large-scale multi-modal data including video tracks, focused on the correlation between image, sound, and location information recorded simultaneously, and to learn conceptual space describing the contents of the data to realize efficient searching.
- Learning Interaction Rules through Compression of Sensori-Motor Causality Space8
The experiment of human-robot interaction showed that a real robot with camera and arms (3 DoF for each) learns gesture interaction rules with human in high-dimensional sensori-motor space without dividing interaction into learning/interaction phases.
- Scene Classification using Generalized Local Correlation8
It is shown that the performance of global image features can be boosted by considering the correlations of local features in addition to the mean, and the effectiveness of this method is experimentally verified using standard scene classification benchmark datasets.
- 8
- Combining Inherent Knowledge of Vision-Language Models with Unsupervised Domain Adaptation Through Strong-Weak Guidance7
This work introduces a strong-weak guidance learning scheme that employs zero-shot predictions to help align the source and target dataset and shows that this method complements and benefits from prompt adaptation techniques for vision-language models.
- 7
- Open-Set Domain Adaptation via Joint Error Based Multi-class Positive and Unlabeled Learning7
This paper proposes an end-to-end algorithm that tightly bound the risk of the entire target task by positive-unlabeled (PU) learning theory and the joint error from domain adaptation.
- Expert Uncertainty and Severity Aware Chest X-Ray Classification by Multi-Relationship Graph Learning7
A multi-relationship graph learning method with an expert uncertainty-aware loss function that can also interpret the disease classification results and shows that models considering disease severity and uncertainty outperform previous state-of-the-art methods.
- 7
- 7
- Toward a Better Story End: Collecting Human Evaluation with Reasons7
A baseline hierarchical sequence-to-sequence method for story ending generation is introduced and a pairwise comparison against human-written endings is conducted, in which annotators choose the preferable ending.
- 7
- 7
- Reliable index for measuring information flow7
This paper presents a unified formulation of the causality measure based on information theory as well as relationships and disparities between correlation and causality measures, and proves the verification that time-delayed mutual information is not appropriate for nonindependent and identically distributed time series.
- 7
- 7
- 6
- Making Video Recognition Models Robust to Common Corruptions With Supervised Contrastive Learning6
A new benchmark for the robustness of action recognition classifiers to general corruptions is presented, and it is shown that a supervised contrastive learning framework is effective in obtaining discriminative and stable video representations, and makes deep video recognition models robust to general input corruptions.
- 6
- Unsupervised Brain Abnormality Detection Using High Fidelity Image Reconstruction Networks.6
A novel framework for voxel-wise abnormality detection in brain magnetic resonance imaging (MRI) is demonstrated, which exploits an image reconstruction network based on an introspective variational autoencoder trained with a structural similarity constraint.
- Rethinking Task and Metrics of Instance Segmentation on 3D Point Clouds6
A new method with space complexity O(Np) such that large regions can be consumed, as well as novel metrics for tasks that are independent of the categories or size of the inputs, which achieves state-of-the-art performance.
- 6
- 6
- Video Generation Using 3D Convolutional Neural Network6
The proposed method uses the cross-entropy error between the target label and the output of 3D convolutional neural network (C3D) as the objective function for evaluating how close the video is to the target class and uses the Euclidean distance between the input video and the video decoded from the authors' temporal Convolutional auto-encoder ("tempCAE") as the objectives.
- 6
- 6
- 6
- 6
- Dr. RAW: Towards General High-Level Vision from RAW with Efficient Task Conditioning5
Dr. RAW achieves state-of-the-art performance with minimal parameter updates and frozen backbone weights, and harnessing the intrinsic physical cues of RAW alongside parameter-efficient techniques, Dr. RAW advances RAW-based vision systems, achieving both high accuracy and computational economy.
- Discovering Multiple Solutions from a Single Task in Offline Reinforcement Learning5
The experimental results show that the proposed algorithm learns multiple qualitatively and quantitatively distinctive solutions in offline RL.
- Advancing Large Multi-modal Models with Explicit Chain-of-Reasoning and Visual Question Generation5
A novel approach to develop a VLM with the ability to conduct explicit reasoning based on visual content and textual instructions is presented, and a system that can ask a question to acquire necessary knowledge is introduced, thereby enhancing the robustness and explicability of the reasoning process.
- 5
- 5
- Computational Storytelling and Emotions: A Survey5
With the intention of creating a new intersection between computational storytelling research and human creative writing, creative techniques used by professional storytellers are introduced.
- 5
- 5
- 5
- Automatic Determination of the Circuit Constants Fulfilling the Given Impulse Time Parameters5
This paper proposes a generalised L.I. generator circuit, techniques to solve its circuit equation and a method to determine values of circuit constants to fulfil given time parameters.
- 5
- 5
- 4
- 4
- Robustifying a Policy in Multi-Agent RL with Diverse Cooperative Behaviors and Adversarial Style Sampling for Assistive Tasks4
It is demonstrated that policies trained with a popular deep RL method are vulnerable to changes in policies of other agents and that the proposed framework improves the robustness against such changes.
- Grouped self-attention mechanism for a memory-efficient Transformer4
The proposed two novel modules, Grouped Self-Attention (GSA) and Compressed Cross-Att attention (CCA) achieve a computational space and time complexity of order $O(l)$ with a sequence length $l$ under small hyperparameter limitations, and can capture locality while considering global information.
- Graph interaction for automated diagnosis of thoracic disease using x-ray images4
A novel framework is proposed: Feature map Graph Representational Probabilistic Class Activation Map (FGR-PCAM) to learn the graph structure of lesion-specific features and consider these relationships while also leveraging the localization ability of PCAM.
- 4
- 4
- 4
- 4
- 4
- 4
- Weakly-supervised multi-class object detection using multi-type 3D features4
This method is novel in the sense that it learns multiple objects simultaneously in a way to balance the scores of each training sample across all object classes, and combines 3D features considering different properties, that is, color texture, grayscale texture, and surface curvature, to improve the performance.
- 4
- 3
- 3
- 3
- 3
- DistML.js: Installation-free Distributed Deep Learning Framework for Web Browsers3
This work provides a comprehensive explanation of DistML.js's design, API, and implementation, alongside practical applications including data parallelism in learning.
- MaGRITTe: Manipulative and Generative 3D Realization from Image, Topview and Text3
The proposed method for controlling and generating 3D scenes under multimodal conditions using partial images, layout information represented in the top view, and text prompts can generate 3D scenes in diverse domains, from indoor to outdoor, according to multimodal conditions.
- HiPerformer: Hierarchically Permutation-Equivariant Transformer for Time Series Forecasting3
The concept of hierarchical permutation-equivariance is proposed, focusing on index swapping of components within and among groups, to design a model that considers this group structure.
- 3
- 3
- Fully Spiking Denoising Diffusion Implicit Models3
A novel approach fully spiking denoising diffusion implicit model (FSDDIM) is proposed to construct a diffusion model within SNNs and leverage the high speed and low energy consumption features of SNN's via synaptic current learning (SCL).
- 3
- 3
- Learning from Label Proportions with Instance-wise Consistency3
An approximation method is proposed for the proposed risk estimator, to apply it to large bags, by diverting the constraints on bags in existing research, and its estimation error bound is derived.
- 3
- 3
- 3
- Service Robots: A Unified Framework for Detecting, Opening and Navigating Through Doors3
This paper presents a unified framework for the door opening problem, by taking a navigation scenario as a reference, and implements specific algorithms to solve each sub-task and describes the hierarchical automata which integrates the control of the robot during the entire process.
- 3
- 3
- 3
- Long-Term Video Generation of Multiple Futures Using Human Poses.3
A novel method for future video prediction capable of generating multiple long-term futures using a novel approach based on unidimensional convolutional neural networks that outperforms other state-of-the-art works.
- Detecting, Opening and Navigating through Doors: A Unified Framework for Human Service Robots3
This paper presents a unified framework for the door opening problem, by taking a navigation scenario as a reference, and implements specific algorithms to solve each sub-task, and describes the hierarchical automata which integrates the control of the robot during the entire process.
- Measuring Numerical Common Sense: Is A Word Embedding Approach Effective?3
This work used a crowdsourcing service to obtain sufficient data for a subjective agreement on numerical common sense, and examined the performance of a regressor trained on the obtained data to examine whether common sense is attributed to current word embedding.
- 3
- 3
- 3
- 3
- Automatic Image Synthesis from Keywords Using Scene Context3
A system that can automatically synthesize objects to an image, given the background image and class name of the target synthesizing object, and a scene context, which indicates the position, scale, and appearance of synthesizing objects are proposed.
- 3
- Time-Series Human Motion Analysis with Kernels Derived from Learned Switching Linear Dynamics3
The empirical evaluation using real motion data shows that a classifier using SVM with the proposed kernel has much better performance than the classifiers with some conventional kernel techniques.
- 3
- 3
- RAW-Adapter: Adapting Pre-Trained Visual Model to Camera RAW Images and a Benchmark2
This work proposes RAW-Adapter, a novel framework that incorporates learnable ISP modules as input-level adapters to adjust RAW inputs and employs model-level adapters to seamlessly bridge ISP processing with high-level downstream architectures and serves as a general framework applicable to various computer vision frameworks.
- Offline Reinforcement Learning with Wasserstein Regularization via Optimal Transport Maps2
This work proposes an approach that utilizes the Wasserstein distance, which is robust to out-of-distribution data and captures the similarity between actions, and demonstrates comparable or superior performance to widely used existing methods on the D4RL benchmark dataset.
- Intend to Move: A Multimodal Dataset for Intention-Aware Human Motion Understanding2
Intend to Move (I2M) is introduced, a large-scale, multi-modal dataset for intention-grounded motion modeling that serves not only as a dataset but as a benchmark for embodied intelligence, enabling research on models that can reason about, predict, and act upon the “why” behind human motion.
- 2
- 2
- Learning by Asking Questions for Knowledge-Based Novel Object Recognition2
A framework for acquiring external knowledge by generating questions that enable the model to instantly recognize novel objects and demonstrates that the proposed pipeline effectively acquires knowledge about novel objects compared to several baselines, and realizes novel object recognition utilizing the obtained knowledge.
- Soft Curriculum for Learning Conditional GANs with Noisy-Labeled and Uncurated Unlabeled Data2
This work proposes soft curriculum learning, which assigns instance-wise weights for adversarial training while assigning new labels for unlabeled data and correcting wrong labels for labeled data, and matches the performance of (semi-)supervised GANs even with less than half the labeled data.
- 2
- Name Your Colour For the Task: Artificially Discover Colour Naming via Colour Quantisation Transformer2
A novel colour quantisation transformer, CQFormer, that quantises colour space while maintaining the accuracy of machine recognition on the quantised images, and observes the consistent evolution pattern between the authors' artificial colour system and basic colour terms across human languages.
- 2
- 2
- 2
- 2
- 2
- 2
- 2
- 2
- 2
- The Development of Color CHLAC Features for Object Exploration in 3D Map2
A new feature “Color Cubic Higher-order Auto-Correlation (Color CHLAC) features” to recognize objects in the real world versatilely and robustly and obtain high recognition accuracy in both situations is presented.
- 2
- Online Action Recognition with Margin-Based Query Learning2
The experimental results show that the proposed margin-based query learning is very effective to achieve high performance of the recognition system with very small sized query and annotation process.
- 2
- 2
- 2
- 2
- 2
- 2
- 2
- 1
- WgPy: GPU-accelerated NumPy-like array library for web browsers1
WgPy provides array computation capabilities on the GPU with a NumPy-compatible interface in the web browser and allows the users to write custom kernels that can run on GPUs with minimal syntax knowledge, allowing you to run a variety of algorithms with minimal overhead.
- Few-shot Imitation Learning by Variable-Length Trajectory Retrieval from a Large and Diverse Dataset1
- Gradual Transition from Bellman Optimality Operator to Bellman Operator in Online Reinforcement Learning1
This paper proposes an annealing approach that gradually transitions from the Bellman optimality operator to the Bellman operator, thereby accelerating learning while mitigating bias, and significantly outperforms existing approaches across various locomotion and manipulation tasks.
- 1
- Improved 3D Scene Stylization via Text-Guided Generative Image Editing with Region-Based Control1
This paper introduces techniques that enhance the quality of 3D stylization while maintaining view consistency and providing optional region-controlled style transfer, and proposes Multi-Region Importance-Weighted Sliced Wasserstein Distance Loss, allowing styles to be applied to distinct image regions using segmentation masks from off-the-shelf models.
- Symmetric Q-learning: Reducing Skewness of Bellman Error in Online Reinforcement Learning1
A method called Symmetric Q-learning is proposed, in which the synthetic noise generated from a zero-mean distribution is added to the target values to generate a Gaussian error distribution, which improved the sample efficiency of a state-of-the-art reinforcement learning method by reducing the skewness of the error distribution.
- Improving segmentation of calcified and non-calcified plaques on CCTA-CPR scans via masking of the artery wall1
This paper proposes a novel methodology for segmenting calcified and noncalcified plaques in CCTA-CPR scans of coronary arteries, and results in a prominent boost in segmentation performance, in both quantitative and qualitative evaluation.
- 1
- 1
- Generation of Variable-Length Time Series from Text using Dynamic Time Warping-Based Method1
A Dynamic Time Warping-Like method for Variable-Length data (DTWL-VL), which determines the corresponding elements of the GT and the generated data, allowing for the time difference between them, and makes them closer is proposed.
- Precise Discrimination for Multiple Underlying Pathologies of Dementia Cases Based on Deep-Learning with Electroencephalography1
Electroencephalogram data of patients with dementia were successfully discriminated from healthy volunteers based on deep learning and could produce a new purpose of EEG measurement in screening for dementia diseases.
- 1
- Unsupervised Keyword Extraction for Full-Sentence VQA1
A novel unsupervised keyword extraction method based on the principle that the full-sentence answers can be decomposed into two parts that contains new information answering the question, and one that contains information already included in the question.
- Invariant Tensor Feature Coding.1
It is proved that the group-invariant feature vector contains sufficient discriminative information when learning a linear classifier using convex loss minimization.
- 1
- Alternating Circulant Random Features for Semigroup Kernels1
Novel random features called "alternating circulant random features,'' which consist of a random mixture of independent random structured matrices, are proposed, which facilitates rapid calculation by employing structuredMatrices and preserves the weight distribution because sign flipping is not implemented.
- Towards Human-Friendly Referring Expression Generation1
This paper addresses the generation of referring expressions that not only refer to objects correctly but also ease human comprehension, and outperformed previous methods both on machine evaluation and on crowd-sourced human evaluation.
- Scene Image Synthesis from Natural Sentences Using Hierarchical Syntactic Analysis1
This application highlighted the capability of the proposed system to generate novel images as well as its ability to succinctly convey ideas.
- 1
- MIL at ImageCLEF 2013: Personal Photo Retrieval1
This paper trains a ranking function using rankSVM, extracts Fisher Vectors from several local descriptors as visual features, and uses Bag-of-Words (BoW) as metadata features to achieve the best performance in the Personal Photo Retrieval Task.
- 1
- 1
- 1
- Realization of Portable Radio Communication Device and Ad Hoc Wireless Network for Lifelog based Physical and Informational Support System1
Experimental results prove that the operational system is useful and developed device is sufficient performance for Lifelog based support systems.
- 1
- Development of Individual Identification System utilizing Time Series of Floor Pressure Distribution1
- 1
- 1
- 1
- 1
- 1
- 1
- 1
- 1
- 1
- –
- –
- SceneProp: Combining Neural Network and Markov Random Field for Scene-Graph Grounding–
SceneProp is introduced, a novel method that resolves the issue of scene-graph grounding as a Maximum a Posteriori (MAP) inference problem in a Markov Random Field (MRF) by performing global inference over the entire query graph.
- –
- –
- –
- –
- Emergence of Painting Ability via Recognition-Driven Evolution–
This paper presents a model with a stroke branch and a palette branch that together simulate human-like painting that achieves superior performance in high-level recognition tasks, delivering artistic expression and aesthetic appeal, especially in abstract sketches.
- –
- Paleoinspired Vision: From Exploring Colour Vision Evolution to Inspiring Camera Design–
This model condenses millions of years of evolution within seconds on GPU, providing an experimental framework to test long-standing hypotheses in evolutionary biology, such as vision of early mammals, primate trichromacy from gene duplication, retention of colour blindness, blue-shift of fish rod and multiple rod opsins with bioluminescence.
- Frame-Level Event Representation Learning for Semantic-Level Generation and Editing of Avatar Motion–
This work proposes obtaining frame-level event representation from the pair of motion and text and using it to edit events in motion and predict motion from the text, and evaluated the method on the HumanML3D dataset and demonstrated that it can generate motion fromThe text while editing motion flexibly.
- Self-Supervised Learning for Group Equivariant Neural Networks–
A method to construct pretext tasks for self-supervised learning on group equivariant neural networks and invariant contrastive loss is proposed, to ensure that training is consistent with the equivariance.
- 3D Lighter: Learning to Generate Emissive Textures–
A novel approach to generate emissive textures for luminous objects, using direct 3D supervision from a 3D model dataset, and proposes 3D Lighter, a method using neural fields with generative latent optimization.
- –
- –
- Memory Efficient Temporal & Visual Graph Model for Unsupervised Video Domain Adaptation–
This work proposes a memory-efficient graph-based video DA approach that only constructs one graph with a graph attention mechanism for one video, reducing the memory cost substantially.
- –
- –
- –
- –
- –
- Accurate Parts Visualization for Explaining CNN Reasoning via Semantic Segmentation–
A novel method for explaining classi-fication in neural networks, the Parts Detection Module, which is capable of determining the accurate position of the interpretable components in the image by performing upsampling and convolution stepwise, similarly to semantic segmentation.
- –
- –
- –
- –
- –
- $\mathbf{ \textit{Viewpoint} }$-aware Video Summarization–
This paper introduced a novel variant of video summarization, namely building a summary that depends on the particular aspect of a video the viewer focuses on, and developed a novel dataset to investigate how well the generated summary reflects the underlying $\textit{viewpoint}$.
- –
- –
- –
- –
- –
- –
- –
- –
- –
- –
- –
- –
- –
- –
- Large-Scale Generic Image Recognition and Image Representation–
入手可能とな り,この大規模な情報を用いて一般画像認識を構築する 試みが盛んになってきている.
- –
- The significance of early second-look laparoscopy after myomectomy by laparotomy–
Because the rate and the seriousness of post-operative adenexal adhesions were high after myomectomy by laparotomy, great care in preventing adhesion formation should be taken in all other gynecological operations as well.
- –
- 2P1-E20 Estimatation of the flow of people by range image for information detection on mobile robots–
- –
- –
- Fast Scene Recognition from Moving Vehicle Using HLAC Features–
This paper proposes a fast and accurate scene recognition system from moving vehicle, which is a combination of Higher-order Local Auto-Correlation features and the linear discriminant analysis, and shows that the algorithm not only has comparable recognition accuracy compared with the state-of-the-art methods but also outperforms those methods in computational speed.
- –
- –
- –
- –
- –
- –
- –
- –
- –
- –
- –
- –
- –
- –
- –
- –
- –
- –
- –
- –
- –
- –
- –
- –
- –
- –
- Evaluation of Error on Measuring Systems for High Voltage Impulses and their Comparison Measurements–
- –
- –
- –
- –
- –
- –
Publication data from OpenAlex, with missing venues and authors filled in from Crossref; citation counts are the higher of OpenAlex and Semantic Scholar, last synced 2026-10-15. One-sentence summaries under some papers are written by Semantic Scholar’s model. Citation counts may be lower than on Google Scholar, which indexes more sources.
Report an error
Wrong papers, two people merged into one, or a profile that should not be here? Tell us and we will fix or hide it.