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
- Shuicheng YanSuggested from co-authorship
- Hanqing LuSuggested from co-authorship
Is this you? Claim this profile to confirm or dismiss it.
Works253 from public data
- Single Image Dehazing via Multi-scale Convolutional Neural Networks1,759
A multi-scale deep neural network for single-image dehazing by learning the mapping between hazy images and their corresponding transmission maps by combining a coarse-scale net which predicts a holistic transmission map based on the entire image, and a fine-scale network which refines results locally.
- 767
- 566
- RGB-Infrared Cross-Modality Person Re-Identification via Joint Pixel and Feature Alignment558
A novel and end-to-end Alignment Generative Adversarial Network (AlignGAN) for the RGB-IR RE-ID task, which consists of a pixel generator, a feature generator and a joint discriminator that is able to not only alleviate the cross-modality and intra- modality variations, but also learn identity-consistent features.
- Robust Visual Tracking via Structured Multi-Task Sparse Learning427
The results demonstrate that mining the interdependencies between particles improves tracking performance and overall computational complexity.
- 392
- Deep People Counting in Extremely Dense Crowds388
This paper proposes an end-to-end deep convolutional neural networks (CNN) regression model for counting people of images in extremely dense crowds that achieves superior performance than the state-of-the-arts in term of the mean and variance of absolute difference.
- PPDM: Parallel Point Detection and Matching for Real-Time Human-Object Interaction Detection337
A single-stage Human-Object Interaction (HOI) detection method that has outperformed all existing methods on HICO-DET dataset at 37 fps on a single Titan XP GPU is proposed, and is the first real-time HOI detection method.
- Deep Human Parsing with Active Template Regression308
In this work, the human parsing task, namely decomposing a human image into semantic fashion/body regions, is formulated as an active template regression (ATR) problem, where the normalized mask is expressed as the linear combination of the learned mask templates.
- Hi, magic closet, tell me what to wear!290
This paper collects a large clothing What-to-Wear dataset, and thoroughly annotates the whole dataset with 7 multi-value clothing attributes and 10 occasion categories via Amazon Mechanic Turk, to learn a generalize-well model and comprehensively evaluate it.
- BeautyGAN283
A dual input/output Generative Adversarial Network that enables the network to learn translation on instance-level through unsupervised adversarial learning, and could generate visually pleasant makeup faces and accurate transferring results.
- General Instance Distillation for Object Detection264
This work proposes a novel distillation method for detection tasks based on discriminative instances without considering the positive or negative distinguished by GT, which is called general instance distillation (GID).
- Robust Visual Tracking Via Consistent Low-Rank Sparse Learning261
A consistent low-rank sparse tracker that builds upon the particle filter framework for tracking that adaptively prunes and selects candidate particles by using linear sparse combinations of dictionary templates is proposed.
- Delving Into the Devils of Bird’s-Eye-View Perception: A Review, Evaluation and Recipe252
A full suite of practical guidebook to improve the performance of BEV perception tasks, including camera, LiDAR and fusion inputs is introduced, and the future research directions in this area are pointed out.
- Referring Image Segmentation via Cross-Modal Progressive Comprehension250
A Cross-Modal Progressive Comprehension (CMPC) module and a Text-Guided Feature Exchange (TGFE) module to effectively address the challenging task of referring image segmentation.
- 250
- GEN-VLKT: Simplify Association and Enhance Interaction Understanding for HOI Detection222
Guided-Embedding Network (GEN) is proposed to attain a two-branch pipeline without post-matching and Visual-Linguistic Knowledge Transfer (VLKT) training strategy to enhance interaction understanding by transferring knowledge from a visual-linguistic pre-trained model CLIP is proposed.
- Linguistic Structure Guided Context Modeling for Referring Image Segmentation211
A "gather-propagate-distribute" scheme to model multimodal context by cross-modal interaction and implement this scheme as a novel Linguistic Structure guided Context Modeling (LSCM) module.
- Cross-Modal Progressive Comprehension for Referring Segmentation202
This paper proposes a cross-modal progressive comprehension (CMPC) scheme to effectively mimic human behaviors and implements it as a CMPC-I (Image) module and aCMPC-V (Video) module to improve referring image and video segmentation models.
- 199
- Reformulating HOI Detection as Adaptive Set Prediction190
This paper reformulate HOI detection as an adaptive set prediction problem, with this novel formulation, it is proposed an Adaptive Set-based one-stage framework (AS-Net) with parallel instance and interaction branches and an effective instance-aware attention module.
- 184
- 176
- 173
- Discriminative Triad Matching and Reconstruction for Weakly Referring Expression Grounding171
This paper proposes the triad-level matching and reconstruction modules which are lightweight yet effective for the weakly-supervised training, making it three times lighter and faster than the previous state-of-the-art methods.
- PSGAN: Pose and Expression Robust Spatial-Aware GAN for Customizable Makeup Transfer170
Pose and expression robust Spatial-aware GAN (PSGAN) is proposed, which not only achieves state-of-the-art results even when large pose and expression differences exist but also is able to perform partial and shade-controllable makeup transfer.
- Matching-CNN meets KNN: Quasi-parametric human parsing169
This work aims to develop a new solution with the advantages of both methodologies, namely supervision from annotated data and the flexibility to use newly annotated (possibly uncommon) images, and present a quasi-parametric human parsing model.
- 167
- Human-Centric Spatio-Temporal Video Grounding With Visual Transformers163
This work introduces a novel task – Human-centric Spatio-Temporal Video Grounding (HC-STVG), which aims to localize a spatio-temporal tube of the target person from an untrimmed video based on a given textural description.
- 3D-SPS: Single-Stage 3D Visual Grounding via Referred Point Progressive Selection158
A 3D Single-Stage Referred Point Progressive Selection (3D-SPS) method, which progressively selects keypoints with the guidance of language and directly locates the target at a single stage, bridges the gap between detection and matching in the 3D visual grounding task.
- Video steganography: A review156
The performance assessment for video Steganography and the future popular video steganography including H.265 video stegansography, robust video steGANography and reversible video steaganography are introduced.
- 149
- Video Background Music Generation with Controllable Music Transformer142
This work establishes the rhythmic relationships between video and background music, and proposes CMT, a Controllable Music Transformer that enables the local control of the aforementioned rhythmic features, as well as the global Control of the music genre and the used instrument specified by users.
- TransRefer3D: Entity-and-Relation Aware Transformer for Fine-Grained 3D Visual Grounding139
This work exploits Transformer for its natural suitability on permutation-invariant 3D point clouds data and proposes a TransRefer3D network to extract entity-and-relation aware multimodal context among objects for more discriminative feature learning.
- 133
- Tree-Structured Policy Based Progressive Reinforcement Learning for Temporally Language Grounding in Video127
A novel Tree-Structured Policy based Progressive Reinforcement Learning (TSP-PRL) framework to sequentially regulate the temporal boundary by an iterative refinement process, which contributes to efficiently decomposing complex policies into an interpretable primitive action.
- Object-Aware Distillation Pyramid for Open-Vocabulary Object Detection116
An Object-Aware Distillation Pyramid (OADP) framework, including an Object- aware Knowledge Extraction (OAKE) module and adistillation Pyramid mechanism, is proposed, which introduces global and block distillation for more comprehensive knowledge transfer to compensate for the missing relation information in object distillation.
- Face Aging with Contextual Generative Adversarial Nets114
A novel Contextual Generative Adversarial Nets (C-GANs) is proposed to specifically take face aging into consideration, and produces appealing results by comparing with the state-of-the-art and ground truth.
- AdversarialNAS: Adversarial Neural Architecture Search for GANs108
The AdversarialNAS is the first method that can search the architectures of generator and discriminator simultaneously in a differentiable manner and only takes 1 GPU day to search for a superior generative model in the proposed large search space.
- 107
- SAFDNet: A Simple and Effective Network for Fully Sparse 3D Object Detection104
This work proposes a fully sparse adaptive feature diffusion network (SAFDNet) for LiDAR-based 3D object detection, designed to address the center feature missing problem, and conducts extensive experiments on Waymo Open, nuScenes, and Argoverse2 datasets.
- 99
- Communication-Efficient Collaborative Perception via Information Filling with Codebook98
Results show that CodeFilling outperforms previous SOTA Where2comm on DAIR-V2X/OPV2VH+ with 1,333/1,206× lower communication volume.
- Anchor3DLane: Learning to Regress 3D Anchors for Monocular 3D Lane Detection97
3D lane anchors are defined in the 3D space and a BEV-free method named Anchor3DLane is proposed to predict 3D lanes directly from FV representations directly to develop a global optimization method that makes use of the equal-width property between lanes to reduce the lateral error of predictions.
- "Wow! you are so beautiful today!"97
A multiple tree-structured super-graphs model is proposed to explore the complex relationships among the high-level beauty attributes, mid-level beauty-related attributes and low-level image features and then based on this model, the most compatible beauty attributes for a given facial image can be efficiently inferred.
- Towards Vehicle-to-everything Autonomous Driving: A Survey on Collaborative Perception94
A comprehensive review of CP methods for V2X scenarios, bringing a profound and in-depth understanding to the community, and examines the sim-to-real generalization ability of existing CP methods.
- Target-Driven Structured Transformer Planner for Vision-Language Navigation89
This article devise an Imaginary Scene Tokenization mechanism for explicit estimation of the long-term target (even located in unexplored environments) and design a Structured Transformer Planner which elegantly incorporates the explored room layout into a neural attention architecture for structured and global planning.
- 89
- Fast Deep Matting for Portrait Animation on Mobile Phone87
A real-time automatic deep matting approach for mobile devices based on densely connected blocks and the dilated convolution, which is designed to predict a coarse binary mask for portrait image and an automatic portrait animation system built on mobile devices, which does not need any interaction and can realize real- time matting with 15 fps.
- 81
- Differentiable Multi-Granularity Human Representation Learning for Instance-Aware Human Semantic Parsing78
A new bottom-up regime is proposed to learn category-level human semantic segmentation as well as multi- person pose estimation in a joint and end-to-end manner that exploits structural information over different human granularities and eases the difficulty of person partitioning.
- Language-Bridged Spatial-Temporal Interaction for Referring Video Object Segmentation77
A Language-Bridged Duplex Transfer (LBDT) module is proposed which utilizes language as an intermediary bridge to accomplish explicit and adaptive spatial-temporal interaction earlier in the encoding phase.
- Rule-Guided Compositional Representation Learning on Knowledge Graphs73
This paper proposes a novel Rule and Path-based Joint Embedding (RPJE) scheme, which takes full advantage of the explainability and accuracy of logic rules, the generalization of KG embedding as well as the supplementary semantic structure of paths.
- A new data hiding method for H.265/HEVC video streams without intra-frame distortion drift72
The experimental results show that this data hiding algorithm can effectively avert intra-frame distortion drift and get good visual quality.
- 70
- 69
- Surveillance Video Parsing with Single Frame Supervision65
A Single frame Video Parsing (SVP) method which requires only one labeled frame per video in training stage, and experimental results on two surveillance video datasets show the superiority of SVP over state-of-the-arts.
- 63
- Sense beauty via face, dressing, and/or voice63
This work performs a comprehensive study of female attractiveness conveyed by single/multiple modalities of cues, i.e., face, dressing and/or voice, and aims to uncover how different modalities individually and collectively affect the human sense of beauty.
- 62
- Collaborative Spatial-Temporal Modeling for Language-Queried Video Actor Segmentation61
This work proposes a collaborative spatial-temporal encoder-decoder framework which contains a 3D temporal encoder over the video clip to recognize the queried actions, and a 2D spatial encoding over the target frame to accurately segment the querying actors.
- Video Background Music Generation: Dataset, Method and Evaluation60
This work presents SymMV, a video and symbolic music dataset with various musical annotations, which is the first video-music dataset with rich musical annotations and proposes a benchmark video background music generation framework named V-MusProd, which utilizes music priors of chords, melody, and accompaniment along with video- music relations of semantic, color, and motion features.
- Reinforced Structured State-Evolution for Vision-Language Navigation60
This paper proposes a novel Structured state-Evolution (SEvol) model, which utilises the graph-based feature to represent the navigation state instead of the vector-based state, and devise a Reinforced Layout clues Miner (RLM) to mine and detect the most crucial layout graph for long-term navigation via a customised reinforcement learning strategy.
- 59
- Object as Query: Lifting any 2D Object Detector to 3D Detection58
This paper designs Multi-View 2D Objects guided 3D Object Detector (MV2D), which can lift any 2D object detector to multi-view 3D object detection and exhibits a state-of-the-art performance among existing methods.
- Analyzing Infrastructure LiDAR Placement with Realistic LiDAR Simulation Library56
A pipeline that can efficiently and effectively find optimal installation positions for infrastructure sensors in a realistic simulated environment is proposed and the correlation between perception performance and LiDAR point cloud distribution is analyzed to validate that density and uniformity can be indicators of performance.
- 56
- 52
- DiffDance: Cascaded Human Motion Diffusion Model for Dance Generation51
Through comprehensive experiments performed on the benchmark dataset AIST++, it is demonstrated that DiffDance is capable of generating realistic dance sequences that align effectively with the input music, comparable to those achieved by state-of-the-art autoregressive methods.
- 51
- 49
- Distribution-Aware Single-Stage Models for Multi-Person 3D Pose Estimation45
The proposed Distribution-Aware Single-stage DAS model simultaneously localizes person positions and their corresponding body joints in the 3D camera space in a one-pass manner, leading to a simplified pipeline with enhanced efficiency and its stat-of-the-art accuracy for multi-person 3D pose estimation.
- PSGAN++: Robust Detail-Preserving Makeup Transfer and Removal45
Experiments demonstrate that PSGAN++ not only achieves state-of-the-art results with fine makeup details even in cases of large pose/expression differences but also can perform partial or degree-controllable makeup transfer.
- 40
- Ensemble Soft-Margin Softmax Loss for Image Classification40
A soft-margin softmax function is introduced to explicitly encourage the discrmination between different classes of CNN models for image classification, and a novel loss, named as Ensemble Soft-Margin Softmax (EM-Softmax), is designed.
- Towards decrypting attractiveness via multi-modality cues39
A novel Latent Dual-supervised Feature-Attribute-Task (LDFAT) network is proposed, where latent attributes are combined with manual attributes to contribute to the final attractiveness estimation, and extensive experimental evaluations well demonstrate the effectiveness of the proposed DFAT and LDFAT networks.
- 38
- Cross-Domain Human Parsing via Adversarial Feature and Label Adaptation38
The proposed model explicitly learns a feature compensation network, which is specialized for mitigating the cross-domain differences, and introduces a structured label adversarial network to guide the parsing results of the target domain to follow the high-orders of the structured labels shared across domains.
- Novel fusion computing method for bio-medical image of WSN based on spherical coordinate38
Experimental results indicate the novel method is effective and very useful for transmission of big-data bio-medical image, which can solve the problem of data redundancy, more energy cost and low quality.
- A Robust and Improved Visual Quality Data Hiding Method for HEVC37
It is experimentally proven that the proposed method can achieve greater robustness, better visual quality, and higher embedding capacity than previously studied methods.
- 36
- 36
- 35
- Boosted multi-class semi-supervised learning for human action recognition35
A boosted multi-class semi-supervised learning algorithm in which the co-EM algorithm is adopted to leverage the information from unlabeled data to deal with the insufficient labeled data and high computational expense is proposed.
- 33
- 32
- 30
- 29
- 29
- 29
- 28
- Confidence-aware Non-repetitive Multimodal Transformers for TextCaps28
A Confidence-aware Non-repetitive Multimodal Transformers (CNMT) that outperforms state-of-the-art models on TextCaps dataset, improving from 81.0 to 93.0 in CIDEr and addressing the issue of word redundancy in captions.
- 28
- 28
- Improving Weakly Supervised Temporal Action Localization by Bridging Train-Test Gap in Pseudo Labels26
- 26
- 26
- 24
- 23
- 23
- 23
- 22
- 22
- 22
- 21
- LLMs as Visual Explainers: Advancing Image Classification with Evolving Visual Descriptions21
This paper proposes a novel framework that integrates LLMs and VLMs to find the optimal class descriptors, and develops an LLM-based agent with an evolutionary optimization strategy to iteratively refine class descriptors.
- 21
- 21
- 19
- 19
- 19
- 19
- Anchor3DLane++: 3D Lane Detection via Sample-Adaptive Sparse 3D Anchor Regression17
A novel BEV-free method named Anchor3DLane++ is proposed which defines 3D lane anchors as structural representations and makes predictions directly from FV features and outperforms previous state-of-the-art methods.
- 17
- 17
- 17
- 17
- 17
- 16
- 16
- 15
- 15
- 15
- 15
- 14
- The 3rd Workshop on UAVs in Multimedia: Capturing the World from a New Perspective13
This workshop will cover various topics related to UAV multimedia, including aerial image and video processing, machine learning for UAV data analysis, UAV swarm technology, and UAV-based multimedia applications.
- 13
- 13
- 12
- 12
- 12
- 12
- 12
- 11
- 11
- 11
- 11
- 11
- 10
- 10
- 10
- 10
- 9
- 9
- 9
- PSGAN: Pose-Robust Spatial-Aware GAN for Customizable Makeup Transfer.9
A novel Pose-robust Spatial-aware GAN (PSGAN) for transferring the makeup style from a reference image to a source image that achieves state-of-the-art results on the existing datasets and is able to perform the customizable part-by-part, shade controllable and pose- Robust makeup transfer.
- 9
- 9
- 9
- 9
- 9
- 8
- 8
- 7
- Knowledge Distillation via Query Selection for Detection Transformer7
A novel Group Query Selection strategy is introduced, which diverges from traditional query selection in DETR distillation by segmenting queries based on their Generalized Intersection over Union with ground truth objects, thereby uncovering valuable hard-negative queries for distillation.
- 7
- 7
- 6
- 6
- 6
- 6
- 6
- Magic-wall6
An edge-aware fully convolutional neural network (FCN) is proposed for indoor semantic scene parsing, in which a novel edge-prior branch is introduced to better identify the boundary of different semantic regions.
- 6
- 5
- 5
- 5
- 5
- 5
- 5
- 5
- 5
- 5
- 5
- 5
- 5
- 5
- 4
- 4
- Beautify As You Like4
The first fast makeup transfer system named as Fast Pose and expression robust Spatial-Aware GAN (FPSGAN) is presented, which is robust to face pose and expression and light-weighted and fast.
- 4
- 4
- 4
- 3
- 3
- 3
- 3
- 3
- 3
- 3
- 3
- 3
- 2
- 2
- 2
- 2
- 2
- 2
- 2
- 2
- 2
- 2
- 2
- 1
- 1
- 1
- 1
- 1
- 1
- 1
- 1
- 1
- 1
- 1
- 1
- 1
- 1
- 1
- 1
- 1
- 1
- RoboSoft'25: The 1st International Workshop on Vision-Language in Soft Robot–
This workshop centers on multimodal perception and decision-making in soft robotics, gathering researchers to explore cutting-edge technologies, challenges, and solutions across areas like embodied navigation, manipulation, and control.
- –
- –
- –
- –
- –
- –
- –
- –
- –
- –
- –
- –
- –
- –
- –
- –
- –
- –
- –
- –
- –
- –
- –
- –
- –
- –
- –
- –
- –
- –
- –
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 2026-10-13. 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.