Is this you? Claim this profile to correct it, add a bio and choose the work people see first.
Claim this profileWorks335 from public data
- 390
- MGMT Status as a Clinical Biomarker in Glioblastoma343
MGMT as a biomarker is discussed and the discordance between MGMT methylation, expression, and patient outcome is elucidated, which currently challenges the implementation of this biomarker in clinical practice.
- 137
- 133
- 124
- 124
- 116
- 112
- 112
- 100
- Scene graph captioner: Image captioning based on structural visual representation97
This work proposes a novel framework to embed a scene graph into the structural representation, which captures the semantic concepts and the graph topology and develops the scene-graph-driven method to generate the attention graph.
- Beta-d-glucan-based drug delivery system and its potential application in targeting tumor associated macrophages94
Use of polysaccharides as carriers in drug delivery system is a hot topic, especially those with specific recognition of immune cells, enabling them to be applied in targeting delivery system and β-d-glucans can be developed as promising carriers for targeting delivery with stability, biocompatibility and specificity when applied in immunotherapy.
- 89
- Coupled hidden conditional random fields for RGB-D human action recognition88
The extensive experiments show that the proposed model can boost the performance of human action recognition by taking advance of complementary characteristics from both RGB and depth modalities.
- 87
- 83
- PC-YOLO11s: A Lightweight and Effective Feature Extraction Method for Small Target Image Detection79
Experiments have shown that PC-YOLO11s exhibits excellent performance in small object detection tasks, with strong accuracy improvement and good generalization ability, which can meet the needs of small object detection in practical applications.
- Exposing digital video forgery by ghost shadow artifact74
A novel approach is proposed for detecting video forgery based on ghost shadow artifact, which is accurately detected by inconsistencies of the moving foreground segmented from the video frames and the moving track obtained from the accumulative frame differences, thus video forgeries is exposed.
- Graph-based characteristic view set extraction and matching for 3D model retrieval70
A novel method for characteristic view extraction and similarity measurement is proposed using the graph clustering method for view grouping and the random-walk algorithm is applied to adaptively update the weight of each view.
- 68
- 67
- 67
- Novel Targeting of Transcription and Metabolism in Glioblastoma66
TG02 inhibits multiple survival mechanisms and synergistically decreases energy production with temozolomide, representing a promising therapeutic strategy in GBM, currently under investigation in an ongoing clinical trial.
- Learning robust affinity graph representation for multi-view clustering64
An improved feature selection algorithm that integrates the advantages of hypergraph embedding and sparse regression to select significant features such that more robust graph Laplacian matrices for various views on this basis can be constructed and a Consistent Affinity Graph Learning (CAGL) algorithm to fuse all views.
- A video steganalytic algorithm against motion-vector-based steganography64
The experimental results show that the proposed steganalytic method can detect the hidden data effectively in motion-vector-based steganography algorithms.
- 60
- 58
- Single/multi-view human action recognition via regularized multi-task learning58
The pyramid partwise bag of words (PPBoW) representation is proposed which implicitly encodes both local visual characteristics and human body structure and can achieve competing performance against the state-of-the-art methods for human action recognition on KTH and MV-TJU.
- 57
- 56
- Spatiotemporal Joint Mitosis Detection Using CNN-LSTM Network in Time-Lapse Phase Contrast Microscopy Images52
A framework to aid humans in annotating mitosis with high efficiency and accuracy in raw phase contrast microscopy images based on the joint detection results using the proposed method is developed.
- Kidney tonifying traditional Chinese medicine: Potential implications for the prevention and treatment of osteoporosis49
To develop a safe, synergistic, effective, and homogenized TCM formula with robust scientific evidence to provide faster and more economical alternatives, the anti-osteoporosis ingredients and pharmacological mechanisms of kidney tonifying traditional Chinese medicine are recapitulated from the perspective of molecular and cell biology.
- 47
- Human Action Recognition Based on Selected Spatio-Temporal Features via Bidirectional LSTM47
This paper proposes a novel framework that can select the discriminative part in the spatial dimension and enrich the modeling action of motion in the temporal dimension using multiple layers of a long short-term memory framework, which can learn compositional representations in space and time.
- 47
- 46
- 45
- 44
- 42
- 41
- Photo-realistic image bit-depth enhancement via residual transposed convolutional neural network39
A novel neural network is proposed with summation and concatenation skip connections among transposed convolutional layers to cope with the gradient vanishing problem and outperforms state-of-the-art algorithms objectively and subjectively with suppressed false contour artifacts and preserved textures.
- 39
- 38
- 38
- LSTM-based multi-label video event detection38
A novel architecture for jointly recognizing multiple events in a given surveillance video, motivated by the sequence to sequence network is proposed, which can predict what happens in a video directly without the preprocessing of object detection and tracking.
- Multi-modal Correlated Network for emotion recognition in speech37
A novel Multi-modal Correlated Network for emotion recognition aiming at exploiting the information from both audio and visual channels to achieve more robust and accurate detection and demonstrates the correlation information of multiple modals is crucial for automatic emotion recognition.
- 37
- Single/cross-camera multiple-person tracking by graph matching37
This work is the first to unify two kinds of tracking problems with the same framework by graph matching, and is mathematically formulated into the Rayleigh Quotients Maximization.
- Graph Disentangled Contrastive Learning with Personalized Transfer for Cross-Domain Recommendation36
A Graph Disentangled Contrastive framework for CDR (GDCCDR) with personalized transfer by meta-networks and an adaptive parameter-free filter is proposed to gauge the significance of diverse interactions, thereby facilitating more refined disentangled representations.
- 36
- Hierarchical & multimodal video captioning: Discovering and transferring multimodal knowledge for vision to language36
A Hierarchical & Multimodal Video Caption (HMVC) model is proposed to jointly learn the dynamics within both visual and textual modalities for video caption task, which infers an arbitrary length sentence according to the input video with arbitrary number of frames.
- DETECTION OF DOUBLE MPEG-2 COMPRESSION BASED ON DISTRIBUTIONS OF DCT COEFFICIENTS35
A new algorithm is presented to detect double MPEG-2 compression based on convex patterns in the distribution of quantized DCT coefficients and it is shown that the proposed scheme can effectively detect doublyMP-2 compressed videos with CBR mode and the target output bit rate can vary in a large range.
- Median filtering forensics in digital images based on frequency-domain features34
Experimental results obtained on widely used databases show that the proposed method achieves outstanding performance in distinguishing median-filtered images from original images or images that have undergone other types of manipulations, demonstrating its great advantage to be applied in real-time processing of big multimedia data.
- 34
- 31
- DS-Net: Dynamic spatiotemporal network for video salient object detection30
A symmetric two-bypass network to explicitly extract spatial and temporal features is constructed and it is demonstrated that the proposed method achieves superior performance than state-of-the-art algorithms.
- Smooth filtering identification based on convolutional neural networks30
A new approach based on convolutional neural networks (CNNs) is proposed, where distinguishable frequency-domain features are put into a conventional CNN model, to identify the template parameters of various types of spatial smooth filtering operations, such as average, Gaussian and median filtering.
- 3D object retrieval based on sparse coding in weak supervision30
This paper applies the sparse coding method in a weakly supervision manner to address 3D model retrieval and uses FDDL to learn dictionary to reconstruct query sample for retrieval.
- 30
- 29
- Sparsity-Based Image Inpainting Detection via Canonical Correlation Analysis With Low-Rank Constraints29
The potential connection between sparsity-based inpainting and canonical correlation analysis (CCA) is revealed and a modified objective function of CCA and a corresponding optimization algorithm are proposed to enhance the inter-class difference in the feature set.
- Multi-Level Policy and Reward Reinforcement Learning for Image Captioning29
This work proposes a novel multi-level policy and reward RL framework for image captioning that contains a Multi-Level Policy Network that can adaptively fuse the word- level policy and the sentence-levelpolicy for the word generation and a guidance term to bridge thepolicy and the reward for RL optimization.
- 29
- Multi-modal & Multi-view & Interactive Benchmark Dataset for Human Action Recognition29
This paper introduces a Multi-modal & Multi-view & Interactive (M2I) dataset, which is designed for the evaluation of the performances of human action recognition under multi-view scenario, and evaluates three representative methods for the single-view, cross view, and cross domain humanaction recognition on this dataset.
- 28
- 28
- Targeting CDK9 for the Treatment of Glioblastoma27
It is discussed how CDK9 inhibition can impact transcription, metabolism, DNA damage repair, epigenetics, and the immune response to facilitate an anti-tumor response to overcome the challenges in glioblastoma management.
- HGAN27
A novel Holistic Generative Adversarial Network (HGAN) is proposed to solve the cross-domain feature representation problem and make the feature space of virtual characteristic view more inclined to thefeature space of the real picture.
- 26
- 26
- Convolutional deep learning for 3D object retrieval26
A feature extraction model based on convolutional neural networks (CNN) that extracts a set of 2D images from 3D model to represent each 3D object and nearest neighbor is used to compute the similarity between different 3D models in order to handle the retrieval problem.
- 25
- Hierarchical Deep Neural Network for Image Captioning25
A hierarchical deep neural network is proposed, which consists of the bottom layer and the top layer, which extracts the visual and high-level semantic information from image and detected regions, respectively, while the latter integrates both of them with adaptive attention mechanism for the caption generation.
- 25
- 25
- 24
- A Fine-Grained Spatial-Temporal Attention Model for Video Captioning24
The proposed FSTA model achieves the spatial-hard attention at a fine-grained region level of objects through the mask pooling module and compute the temporal soft attention by using a two-layer LSTM network with attention mechanism to generate sentences.
- Cross-Domain 3D Model Retrieval via Visual Domain Adaption24
The proposed method can significantly outperform the most recent method for cross-domain 3D model retrieval and the champion of Shrec’16 Large-Scale 3D Shape Retrieval from ShapeNet Core55.
- MMFN22
MMFN is proposed, a novel multimodal fusion network for 3D shape recognition that employs correlations between the different modalities to generate a fused descriptor, which is more robust.
- Cross-view action recognition by cross-domain learning22
A novel cross-domain learning method to handle action recognition by discovering and sharing common knowledge among different video sets captured in multiple viewpoints and applying the block-wise weighted kernel function to leverage cross-view information.
- 22
- Balance between object and background: Object-enhanced features for scene image classification22
An unsupervised object-enhanced feature generation mechanism is proposed, which balances the different effects of object regions and background regions for scene image classification and can be easily embedded in the extraction process of existing prominent histogram-based feature representations.
- 21
- pH-sensitive PEG-coated hyper-branched β-d-glucan derivative as carrier for CpG oligodeoxynucleotide delivery21
This delivery system exhibited a favorable biocompatibility and facilitated the cellular uptake of CpG ODN at pH 6.8 with the possibility of having higher accumulation in acidic cancer microenvironment and could enhance the secretion of cytokines including interleukin-6 and interferon-α as well as capable of interferons-α induction.
- 21
- Low-rank regularized tensor discriminant representation for image set classification21
A novel tensor discriminant representation learning method to better solve the image classification task and demonstrates that the proposed algorithm not only converges with few iterations, but also achieves better accuracy compared with state-of-the-art methods.
- Dynamic Causal Disentanglement Model for Dialogue Emotion Detection20
A Dynamic Causal Disentanglement Model is proposed, which effectively decomposes the content of dialogues and investigates the temporal accumulation of emotions, thereby enabling more precise emotion recognition.
- 20
- 20
- Hierarchical image resampling detection based on blind deconvolution20
By modeling the recovery of edited images using an inverse filtering process, a novel resampling detection framework based on blind deconvolution is proposed, which is more robust than other state-of-the-art approaches in the case of strong JPEG compression and substantial Gaussian noise.
- Nonnegative Mixed-Norm Convex Optimization for Mitotic Cell Detection in Phase Contrast Microscopy20
This method can overcome the difficulty in feature formulation for deformable objects and is independent of tracking or temporal inference model and can produce competing results with the state-of-the-art methods.
- 20
- Video splicing detection and localization based on multi-level deep feature fusion and reinforcement learning19
This paper proposes a novel framework for video splicing detection by modeling this forensic task as a video object segmentation problem, and employs a deep reinforcement learning-based method for tracking suspected regions.
- Evaluation of Bodily Pain Associated with Polycystic Ovary Syndrome: A Review of Health-Related Quality of Life and Potential Risk Factors19
Pain perception is significantly more prevalent in patients with PCOS than in healthy controls, and obesity and infertile status could be the rationales associated with pain development, Nevertheless, underlying causes remain undetermined due to the limited information from SF-36.
- 19
- 19
- Detection of Blue Screen Special Effects in Videos19
The experimental results show that the proposed algorithm can successfully detect the blue screen compositing in videos.
- Efficient Spatio-Temporal Video Grounding with Semantic-Guided Feature Decomposition18
A novel Semantic-Guided Feature Decomposition based Network (SGFDN) is proposed to decompose the 3D spatio-temporal feature into 2D motions and 1D object embedding without losing much object-related semantic information, and the computational complexity in computationally expensive operations such as attention mechanisms can be effectively reduced.
- HDAC-an important target for improving tumor radiotherapy resistance18
This article systematically expounds for the first time the specific mechanism by which HDACs promote tumor radiotherapy resistance in vivo and in vitro and the clinical application prospects of HDAC inhibitors, aiming to provide a reference for HDAC-related drug development and guide the future research direction ofHDAC inhibitors that improve tumor radi therapy resistance.
- SHREC'18: RGB-D object-to-CAD retrieval18
Evaluation results show that while the RGB-D to CAD retrieval problem is indeed challenging due to incomplete RGB-D reconstructions, it can be addressed to a certain extent using deep learning techniques trained on multi-view 2D images or 3D point clouds.
- RGB-D Object-to-CAD Retrieval18
Evaluation results show that while the RGB-D to CAD retrieval problem is indeed challenging due to incomplete RGB-D reconstructions, it can be addressed to a certain extent using deep learning techniques trained on multi-view 2D images or 3D point clouds.
- 18
- Detection of JPEG double compression and identification of smartphone image source and post-capture manipulation18
This study conducted a study to identify smartphone source and post-capture manipulation by utilizing marginal density and neighboring joint density features together, and indicates that applying unsupervised clustering and supervised classification together leads to improvement in identifying smartphone sources and manipulations.
- 18
- Rank canonical correlation analysis and its application in visual search reranking18
Experimental results show that Rank-CCA is superior to standard CCA and semi-supervised CCA (Semi- CCA) algorithm, and achieves comparable performance with several state-of-the-art reranking methods while preserving the superiority of low dimensional features.
- 17
- 17
- Deep low-rank matrix factorization with latent correlation estimation for micro-video multi-label classification17
A deep matrix factorization with latent correlation estimation (DMFLCE) for micro-video multi-label classification is proposed and two inverse covariance estimation components are constructed to automatically encode correlation patterns with respect to the latent attributes and labels.
- HEp-2 cells Classification via clustered multi-task learning17
The extensive experiments on the Hep 2, cell dataset released by the HEp-2 Cells Classification contest show that the proposed method can discover and share the latent relatedness among multiple tasks and consequently augment the performance.
- 17
- 16
- 16
- 16
- 16
- 16
- Comprehensive image quality assessment via predicting the distribution of opinion score15
This work focuses on the distribution of opinion scores (DOS) and aims to comprehensively evaluate image quality via automatically predicting DOS and is the first to introduce label distribution learning approach for image quality assessment.
- HyperSSR: A hypergraph based semi-supervised ranking method for visual search reranking15
This paper proposes a hypergraph based semi-supervised ranking method called HyperSSR for image search reranking that jointly incorporate the hypergraph regularizer and the prior pairwise preferences information into a unified ranking learning framework.
- Cross-domain semantic transfer from large-scale social media15
A cross-domain semantic modeling method for automatic image annotation for visual information from social network platforms, which leverages cross- domain datasets to discover the common knowledge of each semantic concept from UGCs and boost the performance of semantic annotation by semantic transfer.
- 15
- 15
- 14
- BE-ACGAN: Photo-realistic residual bit-depth enhancement by advanced conditional GAN14
A residual BE algorithm based on advanced conditional generative adversarial network (BE-ACGAN), in which the discriminator adversarially helps assess image quality and train the generator to achieve more photo-realistic recovery performance, which outperforms the state-of-the-art methods on large-scale benchmark datasets.
- LCC: Learning to Customize and Combine Neural Networks for Few-Shot Learning14
This work aims to meta-learn how to effectively combine several base-learners and proposes to learn not only a single base-learner but an ensemble of several base-learners to obtain more robust results.
- 2D Scene Sketch-Based 3D Scene Retrieval14
The objective of this track is to evaluate the performance of different 2D scene sketch-based 3D scene retrieval algorithms using a 2D sketch query dataset and a 3D Warehouse model dataset and suggest several future research directions to tackle this research problem.
- Subgraph learning for graph matching14
A novel approach is proposed to handle graph matching problem based on Markov Chain Monte Carlo framework that can effectively save matching pairwise under one-to-one matching constraints and also avoid the effect of outliers and deformation.
- 14
- Jointly Learning Multiple Sequential Dynamics for Human Action Recognition14
This work theoretically proposes the multi-task conditional random fields model and explores its application on human action recognition, and proposes the part-induced spatiotemporal action unit sequence to represent each action sample with multiple partwise sequential feature subspaces.
- 14
- MarkPlugger: Generalizable Watermark Framework for Latent Diffusion Models Without Retraining13
This work proposes MarkPlugger, a generalizable plug-and-play watermark framework without LDM retraining that effectively harmonizes image quality and watermark recovery rate and is generalized to multiple official versions and modified variants of LDMs, even without retraining the watermark model.
- 13
- 13
- Effective 3D object detection based on detector and tracker13
This paper proposes a novel 3D object detection approach in real-world scenes combined RGB image based on MV-RED dataset and shows further major gains in accuracy when the training data from the target scenes is used, outperforming state-of-the-art approaches with far better efficiency.
- 3D Object Retrieval with Multimodal Views13
The evaluation results show a promising scenario about multimodal view-based 3D retrieval methods, and reveal interesting insights in dealing with multi-modal data.
- Partwise bag‐of‐words‐based multi‐task learning for human action recognition13
The authors present partwise BoW representation and furthermore formulate the action recognition task as a joint multi-task learning problem by transfer learning penalised by a graph structure and sparsity to discover latent correlation and boost performances.
- Information Hiding for H.264/AVC13
During the intra prediction step of H.264/AVC video compression standard, information hiding is implemented by modifications of qualified intra 4×4 luma blocks based on the mapping rules between these modes and the hidden bits.
- 13
- 12
- 12
- 12
- SVHAN: Sequential View Based Hierarchical Attention Network for 3D Shape Recognition12
This work proposes a novel sequential view based hierarchical attention network (SVHAN) for 3D shape recognition, and introduces a novel hierarchical feature aggregation module (HFAM) and a novel selective fusion module (SFM) for feature aggregation.
- 12
- 12
- Open-view human action recognition based on linear discriminant analysis12
This work introduces a novel multi-view surveillance action dataset and proposes a novel open-view action recognition method based on the linear discriminant analysis that can learn a common space for action samples under different view by using their category information, which can achieve a good result in open-View action recognition.
- AMFNet: An Adversarial Network for Median Filtering Detection12
A generative adversarial network is proposed for median filtering detection in RGB images to improve the robustness and enhance the statistical difference between original images and median filtered images.
- Sparse Coding Induced Transfer learning for HEp-2 Cell Classification12
This work is the first to transfer the human-crafted visual feature, sensitive to the variation of appearance and shape during cell movement, to the high level representation which directly denotes the correlation of one sample and the bases in the learnt dictionary.
- 12
- 11
- 11
- 11
- A comparison of methods for 3D scene shape retrieval11
A comprehensive comparison of all the above methods and an additional new retrieval methods are performed by evaluating them on the two benchmarks to solicit state-of-the-art approaches.
- The assessment of 3D model representation for retrieval with CNN-RNN networks11
The Euclidean distance is used to obtain the similarity measure between two different models for the retrieval problem and several classic 3D model retrieval and classification methods are leveraged as comparison methods in this paper.
- Hierarchical Graph Structure Learning for Multi-View 3D Model Retrieval11
An unsupervised hierarchical graph structure learning method for 3D model retrieval that can avoid the difficulty in definition and computation in the traditional high-order graph and can achieve competing performance against the most recent supervised & deep learning method.
- Mitosis event recognition and detection based on evolution of feature in time domain11
This paper presents an approach which utilized the evolution of feature in the time domain to represent the feature of mitosis and constructs the levels of motorists according to the steps of mitotic cells.
- Graph regularized low-rank tensor representation for feature selection11
A graph regularized low-rank tensor representation (GRLTR) is proposed for feature selection and the idea of embedded-based feature selection is employed into the model for optimizing the feature representation and clustering result simultaneously.
- Video logo removal detection based on sparse representation11
A video forensics framework for logo removal detection that uses sparse representation and spatial priors and temporal correlations to refine the location of the removal regions and a spatiotemporal suspected region can obviously show the edited regions.
- Tensor-driven low-rank discriminant analysis for image set classification11
A transductive Tensor-driven Low-rank Discriminant Analysis (TLRDA) model is proposed, in which the tensor-driven low-rank approximation and the discriminant graph embedding are integrated to improve the representativeness of image sets.
- Scene image classification with biased spatial block and pLSA11
A novel scene image classification method based on biased spatial block information and an improved coding approach in bag-of-visual-words (BOW) model is proposed to achieve better discrimination power for image classification.
- 10
- 10
- Predicting the popularity of micro-videos via a feature-discrimination transductive model10
A feature-discrimination transductive model is presented that divides the micro-videos into different levels of popularity via the attribute features and predicted the popularity scores via the low-level features precisely, and seeks a latent common feature subspace, where themicro-videos can be comprehensively represented.
- Multi-graph Convolutional Network for Unsupervised 3D Shape Retrieval10
A novel multi-graph network (MGN) is proposed for unsupervised 3D shape retrieval, which utilizes the correlations among modalities and structural similarity between two models to guide the shape representation learning process without category information.
- 10
- Multimedia venue semantic modeling based on multimodal data10
This paper utilizes Recurrent Convolutional Networks to build the correlation between multimedia UGCs and text, and employs a graph clustering method to detect the latent multimedia topics for each venue and proposes techniques to model multimedia location topics and perform semantic-based location summarization, venue prediction and image description.
- 10
- 3D object retrieval based on Spatial+LDA model10
This paper applies LDA model for visual topics extraction and utilized the topic distribution visual feature of image to handle 3D object retrieval problem and proposes a multi-topic model to improve retrieval performance.
- 10
- Ranking Fisher discriminant analysis10
A novel dimensionality reduction algorithm based on Fisher discriminant analysis is proposed, in which relevance degree information—the data label in ranking applications, is introduced to a semi-supervised form of FDA, inWhich both local information and unlabeled data are employed.
- 10
- 9
- Privacy-preserving Multi-source Cross-domain Recommendation Based on Knowledge Graph9
This work constructs a knowledge graph comprehensively leveraging items from multiple auxiliary domains to avoid the leakage of user privacy when user information is transferred to multiple domains, and proposes a knowledge graph-based retrieval and fusion method to transfer knowledge derived from multiple auxiliary domains.
- 9
- 9
- 9
- 9
- Multi-guiding long short-term memory for video captioning9
A novel cell-wise ensemble, where the weight matrix of each cell of LSTM is extended to be a set of attribute-dependent and attention-dependent weight matrices, by which the guiders induce each cell optimization over time.
- Structured low-rank inverse-covariance estimation for visual sentiment distribution prediction9
The proposed model incorporates low-rank and inverse-covariance regularization terms into a unified framework to learn more robust feature representation and more reasonable prediction model simultaneously.
- 9
- 9
- 8
- 8
- 8
- Multimodal Attentive Representation Learning for Micro-video Multi-label Classification8
A multimodal attentive representation network (MARNET) is introduced to learn complete and robust representations to benefit micro-video multi-label classification and an attentive graph neural network module is designed to adaptively learn the correlation matrix and representations of labels for better compatibility with training data.
- 8
- 8
- 8
- 8
- Consistent Domain Structure Learning and Domain Alignment for 2D Image-Based 3D Objects Retrieval8
A domain alignment framework with consistent domain structure learning to reduce the large gap between 2D images and 3D objects and the experimental results demonstrate the proposed method outperforms the state-of-the-art methods.
- A spatial-temporal iterative tensor decomposition technique for action and gesture recognition8
This paper proposes a technique for handling classification of video sequences in unequal length of time, namely Spatial-Temporal Iterative Tensor Decomposition (S-TITD) for uniform length and conducts a series of experiments on three public datasets in gesture and action recognition, showing that the proposed S- TITD approach achieves better performances than the state-of-the-art algorithms.
- Adaptive resource allocation algorithm for internet of things with bandwidth constraint8
An adaptive resource allocation algorithm is proposed, which dynamically assigns the network bandwidth and priority among components according to their signals’ frequency domain characteristics, which can reduce the accumulated and maximum errors of UGV path tracking by over 60% compared with the conventional static algorithm.
- A NOVEL SOURCE MPEG-2 VIDEO IDENTIFICATION ALGORITHM8
A new source video system identification algorithm is proposed based on the features in the video stream, which takes full advantage of the different characteristics in the rate control module and the motion prediction module, and combines a support vector machine classifier to build an intelligent computing system for video source identification.
- 7
- Cholinesterase Inhibitor Reveals Synergistic Potential for Neural Stem Cell-Based Therapy in the 5xFAD Mouse Model of Alzheimer’s Disease7
The combined treatment with donepezil and NSC transplantation more effectively increased synaptic density and improved behavioral performance in AD mice compared to NSC transplantation alone.
- StyleEDL: Style-Guided High-order Attention Network for Image Emotion Distribution Learning7
A style-guided high-order attention network for image emotion distribution learning termed StyleEDL, which interactively learns stylistic-aware representations of images by exploring the hierarchical stylistic information of visual contents is proposed.
- 7
- 3D models retrieval algorithm based on multimodal data7
A novel algorithm based on multimodal 3D model data to handle model retrieval problem is proposed, and a universal graph matching is employed to handle similarity measure in different modals respectively.
- Digital Video Steganalysis Based on a Spatial Temporal Detector7
The experimental results demonstrate the great advantage of the features relative to those of the rich model (RM), the subtractive pixel adjacency model (SPAM) and subtractive prediction error adjacencies matrix (SPEAM), especially for compressed videos, which constitute most Internet videos.
- Automatic report generation based on multi-modal information7
A new framework which can utilize multi-modal social media information to automatically generate related reports for users or government to demonstrate the effectiveness and the practicability of this approach is proposed.
- Quality models for venue recommendation in location-based social network7
A quality model for venue recommendation is proposed by utilizing multimedia data to predict the interested level of each venue and the weighted bipartite matching algorithm is implemented to generate the venue multimedia topics by bridging the textual information and the visual information.
- Venue Semantics: Multimedia Topic Modeling of Social Media Contents7
This paper proposes a novel multimedia topic modeling approach for extracting venue semantics from heterogeneous location-related UGCs and proposes the semantic based venue summarization, which verifies the effectiveness of the proposed framework.
- 7
- 7
- 6
- 6
- Identification of natural compound garcinone E as a novel autophagic flux inhibitor with anticancer effect in nasopharyngeal carcinoma cells6
GE acts as an autophagic flux inhibitor, which may have potential chemotherapeutic use for NPC treatment and may have an application in basic research to explore the mechanisms of autophagy.
- 6
- 6
- Low-rank regularized multi-view inverse-covariance estimation for visual sentiment distribution prediction6
This paper proposes a novel supervised visual sentiment distribution prediction model, termed as low-rank regularized multi-view inverse-covariance estimation, in which feature embedding and distribution prediction are jointly performed and develops an alternative heuristic optimization algorithm to solve the objective function of the proposed model.
- Multi-view feature extraction based on slow feature analysis6
This paper built the input data in order to guarantee it suitable for SFA mode according to structure information of3D model and employed graph matching to handle similarity measure problem between two different 3D model.
- 6
- 6
- T2IW: Joint Text to Image & Watermark Generation5
This T2IW framework is employed to ensure minimal damage to image quality when generating a compound image by forcing the semantic feature and the watermark signal to be compatible in pixels and strengthens the watermark robustness of this approach by subjecting the compound image to various post-processing attacks.
- 5
- 5
- SMPC: boosting social media popularity prediction with caption5
This paper proposes social media popularity prediction with caption (SMPC), a novel architecture that integrates the caption as the global representation into the existing multi-model-feature-based popularity prediction method.
- Multimodel Imaging Evidence of Traction Component in Lamellar Macular Hole with Epiretinal Proliferation5
The findings indicated that epiretinal traction, evaluated by multimodal imaging, is the norm rather than the exception in LMHs showing LHEP and the presence of tractional forces should be taken into consideration when treatment was planned in LMHs.
- Semantically guided projection for zero-shot 3D model classification and retrieval5
This work proposes the semantically guided projection method to classify and retrieve unseen3D models by exploring the semantic relationship between seen and unseen 3D models, and learns bidirectional projections from visual features to semantics and from semantics to visual features, which can eliminate the gap between Seen and unseen domains.
- 5
- 5
- Two-Stream Network Based on Visual Saliency Sharing for 3D Model Recognition5
The experimental result on two public datasets, ModelNet40 and ShapeNetCore55, demonstrates the correlation information of multiple views is crucial for view-based 3D model recognition methods and the proposed method can achieve the state-of-the-art performance on both 3D object classification and retrieval.
- SODA²:Salient Object Detection With Structure-Adaptive & Scale-Adaptive Receptive Field5
A novel dual-adaptive salient object detection algorithm with structure- Adaptive and scale- adaptive receptive field (abbreviated as SODA2) is proposed, and the deformable convolution is introduced to transform the kernels’ sampling locations by augmenting extra offsets.
- Unsupervised Feature Learning With Graph Embedding for View-Based 3D Model Retrieval5
The proposed method utilizes both similarity and dissimilarity information to better leverage the unsupervised problem and estimates the labels which are further used for metric learning.
- Multi-Camera Action Dataset (MCAD): A Dataset for Studying Non-overlapped Cross-Camera Action Recognition.5
A new dataset, namely Multi-Camera Action Dataset (MCAD), is introduced, which is designed to evaluate the open view classification problem under the surveillance environment and designed to design a standard evaluation protocol to enable comparison against existing works.
- Multiple Person Tracking based on Spatial-temporal Information by Global Graph Clustering5
A graph clustering method based on spatio-temporal information of moving objects for multiple person tracking using the graph shift method to handle tracklet association problem and consequently generate the completed trajectory for individual object.
- Max‐margin discriminative random fields for multimodal human action recognition5
A comparison experiment shows that the proposed model can boost the performance of human action recognition by taking advantage of complementary characteristics from multiple modalities.
- EXPOSING DIGITAL VIDEO LOGO-REMOVAL FORGERY BY INCONSISTENCY OF BLUR5
Experimental results show that the proposed method is robust to video lossy compression for logo-removal forgery detection with the advantages of high classification accuracy and low computation cost.
- 4
- 4
- Linoleate-pazopanib conjugation as active pharmacological ingredient to abolish hepatocellular carcinoma growth4
Oral feeding of linoleate-fluorescein isothiocyanate conjugates showed that the compound was well distributed in a spontaneous HCC mouse model, and a rationale design was developed for chemically synthesizing a linoleate-pazopanib conjugate (LAPC), which showed excellent HCC ablative efficacy with altered MOA.
- Progressive Positive Association Framework for Image and Text Retrieval4
A novel Progressive Positive Association Framework is proposed, which models association uncertainty as a normal distribution and progressively mines direct and potential positive associations according to the characteristics of the association distribution and applies KL loss constraint on cross-modal association distribution in order to enhance local semantic alignment.
- Mitosis detection in biomedical images4
This chapter introduces the mitosis process during the cell life cycle, and gives a detailed description of theMitosis detection problem, and introduces some advanced research in mitosis detection areas in recent years.
- Low-Rank Regularized Multimodal Representation for Micro-Video Event Detection4
A low-rank regularized multimodal representation method for micro-video event detection and results demonstrated the superior performance of the proposed method compared with state-of-the-art methods.
- Single image super-resolution via low-rank tensor representation and hierarchical dictionary learning4
This paper proposes a hierarchical dictionary learning approach to learn the latent UR-LR dictionary pair by preserving the internal structure coherence with the LR-DR dictionary pair and proposes a low-rank tensor approximation (LRTA) algorithm based on nuclear-norm regularization to embed input image patches into aLow-dimensional space.
- Fast Context-Adaptive Bit-Depth Enhancement via Linear Interpolation4
A fast yet efficient context-adaptive algorithm via linear interpolation that can well reconstruct natural images with low computational complexity and outperforms the state-of-the-art algorithms on average in terms of both objective and subjective evaluations.
- Visual attribute detction for pedestrian detection4
Two baseline methods are utilized to demonstrate the performance of the attribute in pedestrian detection and an evaluation protocol is proposed for researchers to evaluate pedestrian attribute classification algorithms.
- 4
- 4
- 3
- 3
- 3
- 3
- Multi-View Graph Matching for 3D Model Retrieval3
A multi-view graph matching method (MVGM) for 3D model retrieval that can avoid the difficulty in the definition and computation of the traditional high-order graph and does not require a large-scale 3D dataset for model learning.
- 3
- Domain-Specific Alignment Network for Multi-Domain Image-Based 3D Object Retrieval3
The proposed method is the first unsupervised work to align multiple-domain 2D images with 3D objects in an end-to-end manner and the extensive experimental results demonstrate the superiority of the proposed method.
- A structure-transfer-driven temporal subspace clustering for video summarization3
A novel structure-transfer-driven temporal subspace clustering segmentation (STSC) method for video summarization that first learns the structure information from source videos and then transfer it to target videos to create the final video summary.
- Towards a sparse low-rank regression model for memorability prediction of images3
A sparse low-rank regression framework for image memorability prediction is proposed, in which a projection matrix and a sparse coefficient vector are jointly learnt to guarantee the superior performance.
- 3
- Improving Bit-Depth Expansion via Context-Aware MMSE Optimization (CAMO)3
This paper proposes a pixel-wise context-aware minimum average mean squared error (MMSE) optimization scheme (CAMO) whose optimal solution can be directly derived to effectively improve the BD expansion performance.
- View-based 3D model retrieval via supervised multi-view feature learning3
An effective view-based 3D model retrieval method via supervised multi-view feature learning (SMFL) via Singular Value Decomposition (SVD) algorithm, which helps to calculate the similarities between two different 3D models.
- View-Based 3D Model Retrieval via Multi-graph Matching3
A composition-based multi-graph matching method that seeks the optimal intermediate graph by diverse graph matching orders, according to the consistency of global matching, using the classic optimization method.
- LingoSent — A Platform for Linguistic Aware Sentiment Analysis for Social Media Messages3
This article designs the sentiment analysis approach as a framework with data preprocessing, linguistic feature extraction and sentiment calculation being separate components and shows that the system outperforms existing state-of-the-art lexicon-based sentiment analysis solutions.
- Spatial Context Constrained Characteristic View Extraction for 3D Model Retrieval3
A view-based 3D model retrieval method based on spatial context constrained characteristic view extraction method that applies Bayesian model to compute the similarity between query model and candidate3D model to find the best matching 3D models.
- 3
- An Algorithm for Image Copy-Paste Forgery Detection by Pixel Matching3
Experimental results show that the proposed image forensics approach, based on image pixel matching, can achieve an effective and accurate location for tampered areas and is reasonably robust to various types of copypaste post processing such as filtering, lossy JPEG,JPEG2000 compression and the combination of these operations.
- 3
- Image fusion algorithm based on wavelet transform and fuzzy reasoning3
A new image fusion algorithm based on wavelet transform and fuzzy reasoning is proposed, which was more effective and robust than the traditional fusion algorithms based onWavelet transform.
- Predictive value of pretreatment peripheral blood N/CD4 and N/CD8 ratios for the efficacy of radiotherapy for esophageal cancer2
N/CD4 and N/CD8 have emerged as viable prognostic predictors for patients undergoing radiotherapy for EC, offering valuable insights for clinicians to strategize further treatment options.
- 2
- Exploring contextual information for view-wised 3D model retrieval2
An novel framework is proposed, which utilizes the visual and contextual information to construct the rank graphs and fuses these two graphs to enhance the similarity measure, and defines four strategies to measure the similarity among models according to the relation between the query model and the gallery models.
- An End-to-End Perceptual Quality Assessment Method via Score Distribution Prediction2
This paper proposes to predict the distribution of opinion scores via an end-to-end convolutional neural network based on a pre-trained ResNet with 50 layers and a novel Statistical Region-of-Interest Pooling layer is introduced for lower model complexity, which enables effective training with few datum.
- Low‐rank approximation‐based tensor decomposition model for subspace clustering2
This Letter proposes a low-rank approximation-based tensor decomposition (LRATD) algorithm for subspace clustering and develops an accelerated proximal gradient algorithm to solve the problem of LRATD.
- Tianjin University and National University of Singapore at TRECVID 2017: Video to Text Description.2
This framework builds on the LSTM unit for sentence generation with one attention layer for sentence generation with one attention layer and is optimized with the combination of heterogeneous pair-wise examples.
- Discovering latent attributes for human action recognition in depth sequence2
A latent attribute model to take advantage of the partwise and bodywise action attributes and their concurrence for action modelling is presented and can avoid the explicit definition of a completed action attribute set by designing a hidden layer as latent attributes.
- Image Search Reranking with Semi-supervised LPP and Ranking SVM2
This paper studies the task of image search reranking, and proposes a novel system scheme based on Locality Preserving Projections (LPP) and RankingSVM and improves LPP by incorporating the relevance degree information into it, and names it as semi-supervised LPP (Semi-LPP).
- Overview of content-based image and video search reranking2
This paper analyzes the status of re ranking technique systematically, discusses the characteristics of various types of reranking technique and applications in detail, and summarizes the existing evaluation methods and databases.
- 2
- Overlaid caption extraction in news video based on SVM2
An effective overlaid caption extraction approach for news video by first scanning the video key frames using a small window, and then classify the blocks into the text and non-text ones via support vector machine (SVM), with statistical features extracted from the gray level co-occurrence matrices.
- 1
- 1
- Spatio-temporal progressive optimization network for video bit depth enhancement1
A two-stage Spatio-Temporal Progressive Optimization network tailored for video bit-depth enhancement, aiming to deliver superior performance on High Bit Depth devices, and outperforms other traditional and deep learning methods in terms of both subjective and objective evaluations on multiple datasets.
- A New Mouse Model for Usher Syndrome Crossing Kunming Mice with CBA/J Mice1
The hearing-loss phenotype of inbred mice with USH into CBA/J mice provides a good animal model for future studies on the important physiological roles of the Adgrv1 gene in inner-ear structure and for therapeutic studies targeting Adgrv1-mutated USH.
- Dual-statistic white balance guided 3DLUT for image enhancement1
A new solution Dual-statistic white balance guided 3DLUT to compensate for the color deviation of the 3DLUT due to its own structure is presented and can be applied in image retouching and tone mapping tasks with fairly good generality.
- A deep low-rank semantic factorization method for micro-video multi-label classification1
A deep low-rank semantic factorization (DLRSF) method to perform multi-label classification of micro-videos is developed, which introduces a semantic embedding matrix to bridge explicit labels and implicit semantics, and a low-rank-regularized semantic learning module to explore the intrinsic lowest-rank semantic attributes.
- 1
- Principal views selection based on growing graph convolution network for multi-view 3D model recognition1
This paper focuses on the multi-view 3D model data and proposes a novel growing graph convolution network (GGCN) to handle the principal views selection problem, which can guarantee the performance of3D model representation and effectively reduce the cost time.
- 1
- Pooled time series representation for mitosis event recognition1
A new feature representation for mitotic event detection in time-lapse phase contrast microscopy image sequences of stem cell populations by keeping track of how descriptor values are changing over time and summarize them to represent appearance in the cell sequence.
- 3D model retrieval via single image based on feature mapping1
A novel 3D model retrieval algorithm by cross-modal feature mapping (CMFM), which utilize one single image as query information to address 3D models retrieval problem, and is the first method to handle3D model retreival based on one single 2D image.
- Geo-location driven image tagging via cross-domain learning1
A novel cross-domain learning method for automatic image annotation with geo-location information is proposed and the topic model-based method for popular concept extraction to adaptively construct cross- domain datasets is proposed.
- An Effective Tracking System for Multiple Object Tracking in Occlusion Scenes1
An effective multi-object tracking system which can handle the partial occlusion in the tracking process and employs the part-based model to localize the person and body parts in every frame is proposed.
- TJUT-TJU@TRECVID 2011: Surveillance Event Detection1
A spatio-temporal interest point detector is adopted, which explicitly encodes appearance features together with motion information, to extract robust point features in a sliding window and the bag-of-word (BoW) approach is employed.
- Image Search Reranking with Transductive Learning to Rank Framework1
A semi-supervised learning to rank framework based on Ranking SVM to better compute the similarity between images, a new similarity measure algorithm named SM-PCA, which is relying on Principle Component Analysis, is proposed and introduced into semi- supervised learning.
- Digital video encryption in AVS compressed stream for real-time transmission1
Simulating results show that the presented encrypting method has low complexity, trivial impact on coding efficiency, and almost no degrading on the subjective and objective video quality.
- Design of Adaptive Watermarking Algorithms for Video Signals Using Subjective Tests1
Experimental results show that the presented watermarking scheme achieves comparatively high detection rate than spatial non-adaptive water marking scheme and the simple human visual system based adaptive watermarked scheme.
- 1
- Watermarking for Authentication of LZ-77 Compressed Documents1
The experimental results show that the experimental algorithm, called LZSC-77, compared to the LZS-77 algorithm, can improve compression rates on many files of the Cargary corpus and Canterbury corpus.
- 1
- –
- –
- –
- –
- –
- Barriers to barrier-free films for people with visual impairments: a case in China–
It is argued that the low penetration rate of accessible facilities reduces the motivation of people with visual impairments and Copyright restrictions result in outdated and insufficiently accessible content.
- –
- –
- –
- –
- Identification of genes predicting chemoresistance and short survival in ovarian cancer–
A group of genes potentially linked to OC chemoresistance was identified, which dysregulated in 90 chemoresistant tissues compared with 197 sensitive tissues, and specifically the CASP2 might be potentially used as predictive marker, prognostic marker and therapeutic target in management of OC.
- –
- –
- –
- –
- –
- –
- –
- –
- –
- –
- –
- –
- –
- The research progress of Alzheimer's disease based on gray matter volume and cerebral blood flow–
The studies were reviewed which applied the structural MRI and arterial spin labeling MRI(ASL-MRI) in AD over the past 20 years, and found more gray matter volume loss in multiple brain structures in individuals with AD spectrum.
- –
- –
- Multi-layers CNNs for 3D Model Retrieval–
A multi-layers CNNs (MLCNN) structure for 3D model representation is proposed and the Euclidean metric is leveraged to compute the similarity between two different 3D models to complete the retrieval problem.
- –
- –
- –
- –
- Automatic Cell Cycle Localization Using Latent-Dynamic Conditional Random Fields–
This paper proposes an automatic cell cycle localization method based on the Latent-Dynamic Conditional Random Fields model, which can simultaneously model the visual dynamics within one stage and visual transition between adjacent stages in one mitosis sequence.
- TJU-TJUT@TRECVID 2015: Surveillance Event Detection.–
An event detection system evaluated in 2015 TRECVID-SED and an interactive visual analytics system, which can enable effective rank detection results with score relations and utilize user feedbacks to improve surveillance event detection are presented.
- Mobile Watermarking against Geometrical Distortions–
Experimental results demonstrate that the proposed watermarking approach is computationally efficient and robust to geometrical distortions.
- Balance between Diversity and Relevance for Image Search Results–
A DIR (DDrank-based Image search Rerank) algorithm, which can enrich the topic coverage while keeping the relevance with minimal impact, is proposed, which is based on vertex reinforced random walk and can automatically balance the relevance and diversity of the top ranked vertices in a principle way.
- –
- –
- Video Steganalysis Based on Bispectrum–
The proposed method not only successfully detects the hidden data in stego-video at different compression bit rates, but also estimates the embedding strength in the steganographic algorithm.
- –
- –
- A Motion Estimation Algorithm Based on Adaptive Template–
Three important methods: non-symmetrical cross search, 5×5 templates search and non-uniform multi-level hexagonal grid search mode, is optimized to improve the speed of this algorithm.
- Digital Video Watermarking in AVS Compressed Stream for Copy Control–
The experimental results show that the presented watermarking method achieves com-paratively high embedding rate without increasing the bitrate of data, and has almost no impact on video quality sub-jectively as well as objectively.
- –
- Video shot classification with concept detection–
This research proposes a novel shot classification algorithm with concept detection for news video programs, in which anchorperson and reporter and monologue shots are distinguished by Conditional Random Fields (CRFs), and the last three categories are picked out by rule-based methods.
- –
- News Video Story Segmentation Technique:An Overview–
An overview of the existing methods for news video story segmentation is given and they are divided into three categories: the single-modality approach, the multi- modality fusion approach and the context-based approach.
- –
- –
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 2026-10-12. 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.