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
- Liang-Tien ChiaSuggested from co-authorship
Is this you? Claim this profile to confirm or dismiss it.
Works185 from public data
- 2D Gaussian Splatting for Geometrically Accurate Radiance Fields1,708
2D Gaussian Splatting (2DGS), a novel approach to model and reconstruct geometrically accurate radiance fields from multi-view images from multi-view images by introducing a perspective-accurate 2D splatting process utilizing ray-splat intersection and rasterization.
- Future Frame Prediction for Anomaly Detection - A New Baseline1,542
This paper proposes to tackle the anomaly detection problem within a video prediction framework by introducing a motion (temporal) constraint in video prediction by enforcing the optical flow between predicted frames and ground truth frames to be consistent, and is the first work that introduces a temporal constraint into the video prediction task.
- 913
- 597
- InstantMesh: Efficient 3D Mesh Generation from a Single Image with Sparse-view Large Reconstruction Models569
InstantMesh is presented, a feed-forward framework for instant 3D mesh generation from a single image, featuring state-of-the-art generation quality and significant training scalability, and is able to create diverse 3D assets within 10 seconds.
- 472
- Structured3D: A Large Photo-Realistic Dataset for Structured 3D Modeling462
This paper presents a new synthetic dataset, Structured3D, with the aim of providing large-scale photo-realistic images with rich 3D structure annotations for a wide spectrum of structured 3D modeling tasks, and takes advantage of the availability of professional interior designs to automatically extract 3D structures from them.
- Kernel Sparse Representation for Image Classification and Face Recognition386
KSR is essentially the sparse coding technique in a high dimensional feature space mapped by implicit mapping function that outperforms sparse coding and EMK, and achieves state-of-the-art performance for image classification and face recognition on publicly available datasets.
- 369
- 361
- 317
- Liquid Warping GAN: A Unified Framework for Human Motion Imitation, Appearance Transfer and Novel View Synthesis292
A 3D body mesh recovery module is proposed to disentangle the pose and shape, which can not only model the joint location and rotation but also characterize the personalized body shape and is able to support a more flexible warping from multiple sources.
- 291
- Fast-MVSNet: Sparse-to-Dense Multi-View Stereo With Learned Propagation and Gauss-Newton Refinement289
This paper presents a Fast-MVSNet, a novel sparse- to-dense coarse-to-fine framework, for fast and accurate depth estimation in MVS, while achieving comparable or even better results on the challenging Tanks and Temples dataset as well as the DTU dataset.
- Michelangelo: Conditional 3D Shape Generation based on Shape-Image-Text Aligned Latent Representation285
The proposed approach can generate higher-quality and more diverse 3D shapes that better semantically conform to the visual or textural conditional inputs, validating the effectiveness of the shape-image-text-aligned space for cross-modality 3D shape generation.
- 262
- 251
- Appearance-Motion Memory Consistency Network for Video Anomaly Detection240
This work proposes an Appearance-Motion Memory Consistency Network (AMMC-Net), which first makes full use of the prior knowledge of appearance and motion signals to explicitly capture the correspondence between them in the high-level feature space, and combines the multi-view features to obtain a more essential and robust feature representation of regular events.
- Learning to Parse Wireframes in Images of Man-Made Environments240
A learning-based approach to the task of automatically extracting a "wireframe" representation for images of cluttered man-made environments and two convolutional neural networks that are suitable for extracting junctions and lines with large spatial support are proposed.
- 219
- Dream3D: Zero-Shot Text-to-3D Synthesis Using 3D Shape Prior and Text-to-Image Diffusion Models209
This paper makes the first attempt to introduce explicit 3D shape priors into the CLIP-guided 3D optimization process, and proposes to jointly optimize a learnable text prompt and fine-tune the text-to-image diffusion model for rendering-style image generation.
- 203
- 178
- 162
- DeepPROTACs is a deep learning-based targeted degradation predictor for PROTACs154
A deep neural network model - DeepPROTACs is introduced to help design potent PROTACs molecules and can predict the degradation capacity of a proposed PROTAC molecule based on structures of given target protein and E3 ligase.
- Margin Learning Embedded Prediction for Video Anomaly Detection with A Few Anomalies149
A Margin Learning Embedded Prediction (MLEP) framework that helps with the detection of abnormal events, even for anomalies that have never been previously observed, and pushes the application of anomaly detection towards real scenarios.
- Encoding Structure-Texture Relation with P-Net for Anomaly Detection in Retinal Images148
This work first extracts the structure of the retinal images, then it combines both the structure features and the last layer features extracted from original health image to reconstruct the original input healthy image, and measures the difference between structure extracted from Original and the reconstructed image.
- Look Before You Leap: Learning Landmark Features for One-Stage Visual Grounding135
This work mimics the human behavior of ‘Look Before You Leap’ to design an LBYL-Net, which takes full consideration of contextual information, and outperforms all state-of-the-art two-stage and one-stage methods on ReferitGame.
- 129
- Locality-Constrained Spatial Transformer Network for Video Crowd Counting121
A Locality-constrained Spatial Transformer Network (LSTN) is proposed to alleviate issues in video crowd counting by leveraging a Convolutional Neural Networks to estimate the density map for each frame.
- DearKD: Data-Efficient Early Knowledge Distillation for Vision Transformers120
This work proposes an early knowledge distillation framework, which is termed as DearKD, to improve the data efficiency required by transformers and proposes a boundary-preserving intra-divergence loss based on DeepInversion to further close the performance gap against the full-data counterpart.
- Single-Image Piece-Wise Planar 3D Reconstruction via Associative Embedding117
A novel two-stage method based on associative embedding, inspired by its recent success in instance segmentation, that is able to detect an arbitrary number of planes and facilitate many real-time applications such as visual SLAM and human-robot interaction.
- Saliency Detection in 360$$^\circ $$ Videos112
This paper proposes to implement the spherical convolution on panorama by stretching and rotating the kernel based on the location of patch to be convolved, and proposes a sequential saliency detection by leveraging a spherical U-Net.
- Constructing a Nonnegative Low-Rank and Sparse Graph With Data-Adaptive Features111
Extensive NNLRS experiments demonstrate that the proposed method outperforms the state-of-the-art graph construction method by a large margin for both semisupervised classification and discriminative analysis, which verifies the effectiveness of this proposed method.
- Believe It or Not, We Know What You Are Looking At!105
This work builds a video gaze following dataset, where the ground truth is annotated by the observers in the videos, and significantly outperforms existing methods, which validates the effectiveness of the two-stage solution based gaze following.
- PPGNet: Learning Point-Pair Graph for Line Segment Detection100
This paper proposes to describe junctions, line segments and relationships between them with a simple graph, which is more structured and informative than end-point representation used in existing line segment detection methods and introduces the PPGNet, a convolutional neural network that directly infers a graph from an image.
- Speech Drives Templates: Co-Speech Gesture Synthesis with Learned Templates99
This paper designs a method that learns a set of gesture template vectors to model the latent conditions, which relieve the ambiguity of co-speech gesture generation and adopts the lip-sync error as a proxy metric to tune and evaluate the synchronization ability of the model.
- Improving Training of Deep Neural Networks via Singular Value Bounding97
This work proposes to constrain the solutions of weight matrices in the orthogonal feasible set during the whole process of network training, and achieves this by a simple yet effective method called Singular Value Bounding (SVB).
- Towards Fast Adaptation of Neural Architectures with Meta Learning96
A novel Transferable Neural Architecture Search method based on meta-learning, which learns a meta-architecture that is able to adapt to a new task quickly through a few gradient steps, which makes the transferred architecture suitable for the specific task.
- Normal graph: Spatial temporal graph convolutional networks based prediction network for skeleton based video anomaly detection96
This is the first work to apply graph convolutional networks on skeleton-based video anomaly detection and achieves the-state-of-art performance, compared to those image-level reconstruction-based or prediction-based methods, as well as RNN based methods upon joints.
- 92
- Amodal Segmentation Based on Visible Region Segmentation and Shape Prior91
A framework to mimic the behavior of human and solve the ambiguity in the learning, it firstly estimates a coarse visible mask and a coarse amodal mask, then based on the coarse prediction, the model infers the ammodal mask by concentrating on the visible region and utilizing the shape prior in the memory.
- Multi-Cell Multi-Task Convolutional Neural Networks for Diabetic Retinopathy Grading91
A Multi-Cell Multi-Task Convolutional Neural Networks (M2CNN) solution is a general framework, which can be readily integrated with many other deep neural network architectures.
- 88
- 85
- P$$^{2}$$Net: Patch-Match and Plane-Regularization for Unsupervised Indoor Depth Estimation84
This paper argues that the poor performance of the unsupervised depth estimation task in indoor environments suffers from the non-discriminative point-based matching, and proposes the P$^2Net, which outperforms existing approaches by a large margin.
- Sparse-Gan: Sparsity-Constrained Generative Adversarial Network for Anomaly Detection in Retinal OCT Image82
A novel anomaly detection framework termed Sparsity-constrained Generative Adversarial Network (Sparse-GAN) for disease screening where only healthy data are available in the training set is proposed and the results show that the proposed method outperforms the state-of-the-art methods.
- 82
- Scaling Mesh Generation via Compressive Tokenization81
This work proposes a compressive yet effective mesh tokenization, Blocked and Patchified Tokenization (BPT), facilitating the generation of meshes exceeding 8k faces, and demonstrates the capability to generate meshes with intricate details and accurate topology.
- TransRAC: Encoding Multi-scale Temporal Correlation with Transformers for Repetitive Action Counting80
This work introduces a new large-scale repetitive action counting dataset covering a wide variety of video lengths, along with more realistic situations where action interruption or action inconsistencies occur in the video, and proposes a density map regression-based method to predict the action period.
- 80
- MLLM-Tool: A Multimodal Large Language Model for Tool Agent Learning78
This paper proposes MLLM-Tool, a system incorporating open-source LLMs and multi-modal encoders so that the learned LLMs can be conscious of multi-modal input instruction and then select the function-matched tool correctly.
- 78
- Laplacian Auto-Encoders: An explicit learning of nonlinear data manifold76
This paper proposes a novel unsupervised manifold learning method termed Laplacian Auto-Encoders (LAEs), which regularizes training of auto-encoders so that the learned encoding function has the locality-preserving property for data points on the manifold.
- 74
- 72
- Assessment of Generative Adversarial Networks Model for Synthetic Optical Coherence Tomography Images of Retinal Disorders71
Whether a generative adversarial network (GAN) could synthesize realistic optical coherence tomography images that satisfactorily serve as the educational images for retinal specialists, and the training datasets for the classification of various retinal disorders using deep learning (DL) is assessed.
- SkrGAN: Sketching-Rendering Unconditional Generative Adversarial Networks for Medical Image Synthesis65
Experimental results show that the proposed SkrGAN achieves the state-of-the-art results in synthesizing images for various image modalities, including retinal color fundus, X-Ray, Computed Tomography (CT) and Magnetic Resonance Imaging (MRI).
- Neither Global Nor Local: Regularized Patch-Based Representation for Single Sample Per Person Face Recognition64
Experimental results show that the regularized patch-based face representation method outperforms sparse coding related face recognition methods as well as some other specially designed single sample per person face representation methods, and achieves the best performance.
- 61
- Domain Adversarial Reinforcement Learning for Partial Domain Adaptation60
This work proposes a domain adversarial reinforcement learning (DARL) framework to progressively select source instances to learn transferable features between domains by reducing the domain shift and employs a deep Q-learning to learn policies for an agent to make selection decisions by approximating the action-value function.
- Personalized Saliency and Its Prediction60
This work proposes to decompose a personalized saliency map into a universalSaliency map (referred to as PSM) predictable by existing saliency detection models and a new discrepancy map across users that characterizes personalized Saliency.
- LivelySpeaker: Towards Semantic-Aware Co-Speech Gesture Generation59
This work introduces LivelySpeaker, a framework that realizes semantics-aware co-speech gesture generation and offers several control handles, and devise a simple but effective diffusion-based gesture generation backbone simply using pure MLPs, that is conditioned on only audio signals and learns to gesticulate with realistic motions.
- PlaneDepth: Self-Supervised Depth Estimation via Orthogonal Planes58
The PlaneDepth is proposed, a novel orthogonal planes based presentation, including vertical planes and ground planes, which can extract the ground plane in an unsupervised manner, which is important for autonomous driving.
- 57
- Liquid Warping GAN With Attention: A Unified Framework for Human Image Synthesis53
This paper proposes to use a 3D body mesh recovery module to disentangle the pose and shape and builds a new dataset, namely Impersonator (iPER) dataset, for the evaluation of human motion imitation, appearance transfer, and novel view synthesis.
- FreeSplatter: Pose-free Gaussian Splatting for Sparse-view 3D Reconstruction51
This work introduces FreeSplatter, a scalable feed-forward framework that generates high-quality 3D Gaussians from uncalibrated sparse-view images while estimating camera parameters within seconds, and develops two specialized variants-for object-centric and scene-level reconstruction-trained on comprehensive datasets.
- Ki-GAN: Knowledge Infusion Generative Adversarial Network for Photoacoustic Image Reconstruction In Vivo50
This work proposes a novel Knowledge Infusion Generative Adversarial Network (Ki-GAN) architecture that combines conventional delay-and-sum algorithm to reconstruct PA image and shows better image reconstruction performance in cases of both full-sampled data and sparse-sampling data compared with state-of-the-art methods.
- Discovering joint audio–visual codewords for video event detection50
This paper proposes a new representation—called bi-modal words—to explore representative joint audio–visual patterns, and finds that average pooling is particularly suitable for bi-modal representation, and using multiple kernel learning to combine multi-modal representations at various granularities is helpful.
- 49
- Multi-level feature fusion based Locality-Constrained Spatial Transformer network for video crowd counting48
A Multi-Level Feature Fusion Based Locality-Constrained Spatial Transformer Network (MLSTN) is proposed, which consists of two components, namely density map regression module and Locality
- 47
- 43
- RGBD Based Gaze Estimation via Multi-Task CNN40
This paper proposes a CNN-based multi-task learning framework to simultaneously refine depth images and predict gaze points to decompose gaze point estimation into eyeball pose, head pose, and 3D eye position estimation.
- 39
- Cold-Start Heterogeneous-Device Wireless Localization39
This work provides a principled and expressive robust feature representation to solve the challenging cold-start heterogeneous-device localization problem and evaluates the model on two public real-world data sets, showing that it significantly outperforms the best baseline.
- 38
- 38
- ROML: A Robust Feature Correspondence Approach for Matching Objects in A Set of Images37
This work considers simultaneously matching object instances in a set of images, where both inlier and outlier features are extracted, and proposes a novel framework, termed Robust Object Matching using Low-rank constraint (ROML), to address this problem.
- 36
- 34
- Layout-Guided Novel View Synthesis from a Single Indoor Panorama32
This paper makes the first attempt to generate novel views from a single indoor panorama and take the large camera translations into consideration and uses Convolutional Neural Networks to extract the deep features and estimate the depth map from the source-view image.
- Evaluating Capability of Deep Neural Networks for Image Classification via Information Plane32
An information plane based framework is designed to evaluate the capability of DNNs for image classification tasks and shows the information plane is more informative than loss curve and applies mutual information to infer the model’s capability for recognizing objects of each class.
- Locality Constrained Deep Supervised Hashing for Image Retrieval31
A novel Locality-Constrained Deep Supervised Hashing which preserves the similarity between image pairs in hashing which boosts the accuracy of image retrieval and demonstrates 10 times faster than state-ofthe-art methods in the training phase.
- GeoFormer: Learning Point Cloud Completion with Tri-Plane Integrated Transformer29
A GeoFormer is introduced that simultaneously enhances the global geometric structure of the points and improves the local details through cross attention between the multi-scale features extracted from the partial input and the features derived from previously estimated points.
- High signal-to-noise ratio reconstruction of low bit-depth optical coherence tomography using deep learning29
The proper integration of OCT and deep learning could benefit the development of healthcare in low-resource settings by using deep learning to reconstruct high SNR OCT images from low bit-depth acquisition.
- Utilizing Information Bottleneck to Evaluate the Capability of Deep Neural Networks for Image Classification29
An information plane-based framework to evaluate the capability of DNNs (including CNNs) for image classification and explains the efficiency of transfer learning in the deep learning area.
- Beyond Universal Saliency: Personalized Saliency Prediction with Multi-task CNN27
This study produces the first database of personalized saliency maps (PSMs) based on universal saliency map (USM) shared by different participants and adopts a multitask CNN framework to estimate the discrepancy between PSM and USM.
- Unsupervised Feature Learning for RGB-D Image Classification26
Compared with conventional handcrafted feature-based RGB-D image representation, the proposed deep R\(^2\)ICA is a feedforward network, Hence, it is more efficient for image representation.
- SVIP: Sequence VerIfication for Procedures in Videos24
A simple but effective baseline based on the transformer encoder with a novel sequence alignment loss is introduced to better characterize long-term dependency between steps, which outperforms other action recognition methods.
- 24
- Dual-Space NeRF: Learning Animatable Avatars and Scene Lighting in Separate Spaces22
This paper proposes a dual-space NeRF that models the scene lighting and the human body with two MLPs in two separate spaces using the barycentric mapping, which surprisingly achieves superior results than LBS with neural blending weights.
- Learning to Recommend Frame for Interactive Video Object Segmentation in the Wild22
The frame selection problem in the interactive VOS is formulated as a Markov Decision Process, where an agent is learned to recommend the frame under a deep reinforcement learning framework, making the interactive setting more practical in the wild.
- Weakly Supervised Video Representation Learning with Unaligned Text for Sequential Videos21
Extensive experiments on video sequence verification and text-to-video matching show that the weakly supervised sequential video understanding method outperforms baselines by a large margin, which validates the effectiveness of the proposed approach.
- 21
- Perceptual-Assisted Adversarial Adaptation for Choroid Segmentation in Optical Coherence Tomography21
An unsupervised perceptual-assisted adversarial adaptation (PAAA) framework for efficiently segmenting the choroid area by narrowing the domain discrepancies between different domains and results show that the proposed PAAA segmentation framework outperforms other state-of-the-art methods.
- 21
- Automatic image tagging via category label and web data20
A novel semi-auto image tagging technique that can automatically recommend other tags to the image, thus reducing the human annotation efforts and guaranteeing tags' diversity due to abundant web data is proposed.
- Surfel-Based Gaussian Inverse Rendering for Fast and Relightable Dynamic Human Reconstruction From Monocular Videos19
SGIA (Surfel-based Gaussian Inverse Avatar) is presented, which introduces efficient training and rendering for relightable dynamic human reconstruction and significantly enhances the realistic relighting of dynamic human avatars, providing a substantial speed advantage.
- 19
- 18
- 18
- Image saliency detection via multi-scale iterative CNN18
This work proposes a multi-scale iterative CNN for salient object detection, which has two complementary subnetworks at different spatial scales, which can estimate the saliency map much more efficiently.
- RoomDesigner: Encoding Anchor-latents for Style-consistent and Shape-compatible Indoor Scene Generation16
This work proposes a two-stage model integrating shape priors into the indoor scene generation by encoding furniture as anchor latent representations, which can synthesis furniture in diverse shapes and produce physically plausible arrangements with shape-compatible and style-consistent furniture.
- InstructP2P: Learning to Edit 3D Point Clouds with Text Instructions16
This paper presents InstructP2P, an end-to-end framework for 3D shape editing on point clouds, guided by high-level textual instructions, that extends the capabilities of existing methods by synergizing the strengths of a text-conditioned point cloud diffusion model, Point-E, and powerful language models, enabling color and geometry editing using language instructions.
- 16
- 16
- 15
- PREF: Phasorial Embedding Fields for Compact Neural Representations14
An efficient frequency-based neural representation termed PREF is presented: a shallow MLP augmented with a phasor volume that covers significant border spectra than previous Fourier feature mapping or Positional Encoding, and a tailored and efficient Fourier transform that combines both Fast Fouriertransform and local interpolation to accelerate na\"ive Fourier mapping.
- 14
- Learning Class-to-Image Distance via Large Margin and L1-Norm Regularization14
This paper proposes an optimization algorithm using L1-norm regularization and large margin constraint to learn the C2I distance, which will not only reduce the number of local features in the class feature set, but also improve the performance of C2i distance due to the use of label information.
- Fundus Image Quality-Guided Diabetic Retinopathy Grading13
This work proposes Fundus Image Quality (FIQ)-guided DR grading method based on multi-task deep learning, which is the first work using fundus image quality to help grade DR.
- Digital resolution enhancement in low transverse sampling optical coherence tomography angiography using deep learning12
The quantitative analysis using the perceptual similarity measures shows the generated OCTA images are closer to the native 3 x 3 mm2 scans, and results show the proposed method could also enhance signal-to-noise ratio.
- RGB-D-based gaze point estimation via multi-column CNNs and facial landmarks global optimization12
This work utilizes a multi-column CNNs framework to estimate the gaze point of a person sitting in front of a display from an RGB-D image of the person, and outperforms existing methods by a large margin on both the dataset and the Eyediap dataset.
- 12
- Hybrid Explicit Representation for Ultra-Realistic Head Avatars11
Experiments demonstrate that this approach adapts the appropriate type of primitives to represent the different parts of the dynamic scene and outperforms all the baseline methods in both quantitative and qualitative comparisons without losing render speed.
- 11
- KGDet: Keypoint-Guided Fashion Detection10
This work designs a simple yet effective Keypoint-Guided clothing Detector, named KGDet, which obtains superior performance on the DeepFashion2 dataset and the FLD dataset with high efficiency.
- 9
- SUNNet: A novel framework for simultaneous human parsing and pose estimation9
A novel Separation-and-UnioN Network (SUNNet) for simultaneous human parsing and pose estimation and a novel Gated Feature Fusion (GFF) block is designed to automatically decide whether to use or skip the priors from the reconstructed 3D human body.
- 9
- Space-time 2D Gaussian Splatting for Accurate Surface Reconstruction under Complex Dynamic Scenes8
To improve geometric quality in dynamic scenes, canonical 2D Gaussian splats are learned and deform these 2D Gaussian splats while enforcing the disks of the Gaussian located on the surface of the objects by introducing depth and normal regularizers.
- 8
- Web image concept annotation with better understanding of tags and visual features8
This paper proposes the Grouping-Based-Precision & Recall-Aided (GBPRA) feature selection strategy for concept annotation, and constructs a more robust middle level feature by concatenating the k-NN results for each type of visual feature.
- PhenoScreen: A Dual-Space Contrastive Learning Framework-based Phenotypic Screening Method by Linking Chemical Perturbations to Cellular Morphology7
The model was validated across multiple screening tasks and successfully predicted active compounds inducing user-specified phenotypes with varying inhibitory effects in the osteosarcoma phenotypic model, underscoring PhenoScreen’s potential to accelerate drug discovery by identifying novel therapeutic pathways and increasing the diversity of viable drug candidates.
- High-Level Feature Guided Decoding for Semantic Segmentation7
The proposed High-Level Feature Guided Decoder achieves state-of-the-art results among methods that do not use extra training data, demonstrating its effectiveness and generalization ability.
- 3D StreetUnveiler with Semantic-aware 2DGS -- a simple baseline7
A novel time-reversal framework to inpaint frames in reverse order and use later frames as references for earlier frames to fully utilize the long-trajectory observations of the empty street.
- 7
- Pseudo-Plane Regularized Signed Distance Field for Neural Indoor Scene Reconstruction6
This work proposes to leverage a novel Pseudo-plane regularized Signed Distance Field (PPlaneSDF) for indoor scene reconstruction by considering adjacent pixels with similar colors to be on the same pseudo-planes and proposing a keypoint-guided rays sampling strategy that attends to the informative textured regions with large color variations.
- 6
- Revisiting Event-Based Video Frame Interpolation6
This work proposes a divide-and-conquer strategy in which event-based intermediate frame synthesis happens incrementally in multiple simplified stages rather than in a single, long stage, and shows that these modifications lead to more reliable and realistic intermediate frame results than previous video frame interpolation methods.
- ResNeRF: Geometry-Guided Residual Neural Radiance Field for Indoor Scene Novel View Synthesis6
The ResNeRF, a novel geometry-guided two-stage framework for indoor scene novel view synthesis, is represented and it is proposed to characterize the density distribution of the scene based on a base density estimated from scene geometry and a residual density parameterized by the geometry.
- 6
- Wireframe Parsing With Guidance of Distance Map6
Experimental results show that the proposed end-to-end method for simultaneously detecting local junctions and global wireframe in man-made environment outperforms the previous state-of-the-art wireframe parser by a descent margin.
- Background subtraction via coherent trajectory decomposition6
With the low-rank decomposition and the MRF, this method can better handle videos with moving camera and obtain coherent foreground and Experimental results on a video dataset show the method achieves very competitive performance.
- 6
- 5
- 5
- P$^2$SDF for Neural Indoor Scene Reconstruction5
This work proposes to leverage a novel Pseudo Plane-regularized Signed Distance Field (P$^2$SDF) for indoor scene reconstruction, and proposes a keypoint-guided rays sampling strategy that attends to the informative textured regions with large color variations, and the implicit network gets a better reconstruction, compared with the original uniform ray sampling strategy.
- Partially Common-Semantic Pursuit for RGB-D Object Recognition5
A novel supervised feature learning method for RGB-D object recognition, named Partially Common-Semantic Learning (PCSL), which jointly captures the complementary and consistency semantic information from RGB and depth modalities.
- FCA-RAC: First Cycle Annotated Repetitive Action Counting4
Experimental results demonstrate that the FCA-RAC approach achieves superior outcomes on RepCount-A and related datasets, highlighting the efficacy of the framework in improving model performance on seen and unseen actions.
- Omni-Line-of-Sight Imaging for Holistic Shape Reconstruction4
Omni-LOS marries LOS and NLOS together, leveraging their complementary advantages to jointly recover the holistic shape of the object from a single scan position, and develops a proof-of-concept Omni-LOS hardware prototype for real-world validation.
- Cross-domain Trajectory Prediction with CTP-Net4
A Cross-domain Trajectory Prediction Network (CTP-Net) is proposed, in which encoders are used in both domains to encode the observed trajectories, then their features are aligned by a cross-domain feature discriminator.
- Bi-Level Multi-column Convolutional Neural Networks for Facial Landmark Point Detection4
The coordinates of all landmark and their displacement are simultaneously estimated in Global and Local CNNs, hence global shape constraints are naturally and implicitly imposed to make it very robust to significant variations in pose, expression, occlusion, and illumination.
- Understanding tag-cloud and visual features for better annotation of concepts in NUS-WIDE dataset4
Experimental results have shown that the method can achieve very high average precision for the NUS-WIDE dataset, which greatly facilitates the construction of large-scale web image data set.
- VertMatch: A Semi-supervised Framework for Vertebral Structure Detection in 3D Ultrasound Volume3
VertMatch is a two-step framework to detect vertebral structures in 3D ultrasound volume by utilizing unlabeled data in semi-supervised manner and outperforms state-of-the-art methods.
- MOS: A Low Latency and Lightweight Framework for Face Detection, Landmark Localization, and Head Pose Estimation3
Online feedback sampling is proposed to augment the training samples across different scales, which increases the diversity of training data automatically and achieves the state-of-the-art performance in low computational resources.
- Correction to “Noise Adaptation Generative Adversarial Network for Medical Image Analysis”3
In the above article [1] , Tables II, III, and V and Fig. 6 are incorrect.
- Efficient Sparsity Estimation via Marginal-Lasso Coding3
The proposed method is more robust than the conventional marginal regression based methods and an adaptive regularization parameter selection scheme and a dictionary learning method incorporated with the proposed sparsity estimation algorithm.
- 2
- 2
- Protein contact map prediction using multiple sequence alignment dropout and consistency learning for sequences with fewer homologs2
This work randomly selected a small part of sequence homologs for proteins with large Nf to generate MSAs with small Nf, which effectively improves the prediction accuracy of protein contact maps withSmall Nf.
- 2
- T-SDN architecture for space and ground integrated optical transport network2
According to the characteristics of SGIOTN, this work proposes an transport SDN architecture for it, with hierarchical control plane and data plane composed of packet networks and optical transport networks.
- 1
- 1
- Identification of a nuclear transcription factor-Y (NF-Y) gene family in pepper and analysis of a CaNF-YC1-CaTIFY7-CaCBF1a/b transcription factor module under cold stress1
A crucial role is indicated for the CaNF-YC1-CaTIFY7-CaCBF1a/b molecular module in regulating core factors of low-temperature signaling in peppers.
- HeroMaker: Human-centric Video Editing with Motion Priors1
HeroMaker performs human-centric video editing by manipulating the dual canonical fields and combining them with motion priors to synthesize temporally coherent and visually plausible results.
- Electrical Tunable Spintronic Neuron with Trainable Activation Function1
This work exploits the physics behind the spin torque induced magnetization switching to enable the dynamic change of the activation function during the training process, which enables a faster or slower change of output required by the backpropagation algorithm.
- 1
- 1
- Discovering Class-Specific Informative Patches and Its Application in Landmark Charaterization1
A new representation of image is introduced: Ordered-BoW Image (BoWI), whose elements summarizes information of the patch centered at the element in original image, whose elements are robust and informative enough for an object class representation.
- –
- –
- –
- –
- –
- –
- –
- –
- –
- –
- –
- –
- –
- –
- Genome-wide identification and expression profiling analysis of GATA transcription factors in pepper–
- –
- –
- –
- –
- –
- –
- –
- –
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.