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
- Charles WangSuggested from co-authorship
Is this you? Claim this profile to confirm or dismiss it.
Works171 from public data
- MS-Celeb-1M: A Dataset and Benchmark for Large-Scale Face Recognition2,241
A benchmark task to recognize one million celebrities from their face images, by using all the possibly collected face images of this individual on the web as training data, which could lead to one of the largest classification problems in computer vision.
- Large Scale Incremental Learning1,588
This work found that the last fully connected layer has a strong bias towards the new classes, and this bias can be corrected by a linear model, and with two bias parameters, this method performs remarkably well on two large datasets.
- CRIS: CLIP-Driven Referring Image Segmentation567
This paper designs a vision-language decoder to propagate fine-grained semantic information from textual representations to each pixel-level activation, which promotes consistency between the two modalities and presents text-to-pixel contrastive learning.
- Recognize Anything: A Strong Image Tagging Model461
The Recognize Anything Model makes a substantial step for foundation models in computer vision, demonstrating the zero-shot ability to recognize any common category with high accuracy, by leveraging large-scale image-text pairs for training instead of manual annotations.
- Advancing Image Understanding in Poor Visibility Environments: A Collective Benchmark Study351
The UG2+ challenge Track 2 competition in IEEE CVPR 2019 is launched, aiming to evoke a comprehensive discussion and exploration about whether and how low-level vision techniques can benefit the high-level automatic visual recognition in various scenarios.
- RoboMamba: Efficient Vision-Language-Action Model for Robotic Reasoning and Manipulation157
This work introduces RoboMamba, an end-to-end robotic VLA model that leverages Mamba to deliver both robotic reasoning and action capabilities, while maintaining efficient fine-tuning and inference.
- Structured Local Radiance Fields for Human Avatar Modeling151
This work introduces a novel representation on the basis of recent neural scene rendering techniques that enables automatic construction of animatable human avatars for various types of clothes without the need for scanning subject-specific templates, and can generate realistic images with dynamic details for novel poses.
- Personalized Image Aesthetics Assessment with Rich Attributes132
Experimental results indicate that the conditional PIAA model can outperform the control group, which is also the first attempt to demonstrate how image aesthetics and subject characters interact to produce the intricate personalized tastes on image aesthetics.
- Tag2Text: Guiding Vision-Language Model via Image Tagging121
This paper presents Tag2Text, a vision language pre-training (VLP) framework, which introduces image tagging into vision-language models to guide the learning of visual-linguistic features and effectively enhances the performance of vision-language models on both generation-based and aligning tasks.
- Discriminative Multi-Modality Speech Recognition118
A two-stage speech recognition model that consistently achieves the state-of-the-art performance by a significant margin is proposed, which demonstrates the necessity and effectiveness of AE-MSR.
- PiMAE: Point Cloud and Image Interactive Masked Autoencoders for 3D Object Detection117
This work proposes Pi-MAE, a self-supervised pre-training framework that promotes 3D and 2D interaction through three aspects, and designs a unique cross-modal reconstruction module to enhance representation learning for both modalities.
- View-Guided Point Cloud Completion117
This paper addresses this task by introducing ViPC (view-guided point cloud completion) that takes the missing crucial global structure information from an extra single-view image by leveraging a framework that sequentially performs effective cross-modality and cross-level fusions.
- Self-Distillation from the Last Mini-Batch for Consistency Regularization103
Experimental results on three classification benchmarks illustrate that the proposed self KD framework can consistently outperform state-of-the-art self-distillation approaches with different network architectures and shows strong compatibility with augmentation strategies by gaining additional performance improvement.
- Perceptual Extreme Super Resolution Network with Receptive Field Block102
A super resolution network with receptive field block based on Enhanced SRGAN based on RFB for the purpose of extracting multi-scale information and enhance the feature discriminability and the ensemble of 10 models of different iteration is used to improve the robustness of model and reduce the noise introduced by each individual model.
- 94
- 90
- 89
- 87
- Learning Audio-Visual Source Localization via False Negative Aware Contrastive Learning76
This work proposes a new learning strategy named False Negative Aware Contrastive (FNAC), which utilizes the intra-modal similarities to identify potentially similar samples and construct corresponding adjacency matrices to guide contrastive learning.
- Learning to Detect Head Movement in Unconstrained Remote Gaze Estimation in the Wild60
Novel end-to-end appearance-based gaze estimation methods that could more robustly incorporate different levels of head-pose representations into gaze estimation are proposed that consistently outperforms the state-of-the-art by a significant margin.
- NTIRE 2020 Challenge on Perceptual Extreme Super-Resolution: Methods and Results54
This paper reviews the NTIRE 2020 challenge on perceptual extreme super-resolution with focus on proposed solutions and results and gauges the state-of-the-art in single image super- resolution.
- 51
- 47
- 46
- SoccerNet 2022 Challenges Results42
The SoccerNet 2022 challenges were the second annual video understanding challenges organized by the SoccerNet team, and tasks (3-6) were novel, including their underlying data and annotations.
- 39
- 39
- 39
- BEV-SAN: Accurate BEV 3D Object Detection via Slice Attention Networks37
This paper proposes a novel method named BEV Slice Attention Network (BEV-SAN), which first sample along the height dimension to build the global and local BEV slices, and proposes a LiDAR-guided sampling strategy to leverage the statistical distribution of LiDar to determine the heights of local slices.
- 37
- Deep class-skewed learning for face recognition37
A novel feature augmentation method termed Large Margin Feature Augmentation (LMFA) is put forward to augment hard features and equalize class distribution, leading to balanced classification boundaries between rich and poor classes.
- 34
- The 3rd Anti-UAV Workshop & Challenge: Methods and Results32
A brief summary of the 3rd Anti-UAV Workshop&Challenge is provided including brief introductions to the top three methods in each track including brief introduction to the bottom three methods.
- 32
- 32
- 28
- 28
- 27
- 27
- 25
- 24
- 24
- 23
- 22
- 22
- 22
- 21
- 21
- 20
- 20
- Video2Act: A Dual-System Video Diffusion Policy with Robotic Spatio-Motional Modeling19
Video2Act is a framework that efficiently guides robotic action learning by explicitly integrating spatial and motion-aware representations and surpasses previous state-of-the-art VLA methods by 7.7% in simulation and 21.7% in real-world tasks in terms of average success rate, further exhibiting strong generalization capabilities.
- Open-Vocabulary Segmentation with Unpaired Mask-Text Supervision19
A novel weakly-supervised open-vocabulary segmentation framework that learns from unpaired image-mask and image-text pairs, which can be independently and efficiently collected, and designs a multi-scale matching strategy to reduce noisy mask-entity pairs.
- 19
- 19
- On the Efficacy of Small Self-Supervised Contrastive Models without Distillation Signals18
The validated techniques are combined and improve the baseline performances of five small architectures with considerable margins, which indicates that training small self-supervised contrastive models is feasible even without distillation signals.
- 17
- 17
- 17
- 17
- 16
- 16
- 15
- 15
- 14
- 14
- 14
- 14
- 13
- 13
- 12
- 11
- 11
- 11
- 11
- 10
- 10
- 10
- 10
- 9
- 9
- 9
- 8
- BEVUDA: Multi-geometric Space Alignments for Domain Adaptive BEV 3D Object Detection8
A Multi-space Alignment Teacher-Student (MATS) framework to ease the domain shift accumulation, which consists of a Depth-Aware Teacher (DAT) and a Geometric-space Aligned Student (GAS) model.
- 8
- 8
- 8
- 8
- BEV-LGKD: A Unified LiDAR-Guided Knowledge Distillation Framework for BEV 3D Object Detection8
A unified framework named BEV-LGKD to transfer the knowledge in the teacher-student manner is proposed and the quality of depth estimation is crucial for BEV perception, and depth distillation is introduced to the framework.
- 8
- 8
- 8
- 7
- RepCaM: Re-parameterization Content-aware Modulation for Neural Video Delivery7
This paper introduces a novel Re-parameterization Content-aware Modulation (RepCaM) method to modulate all the video chunks with an end-to-end training strategy, achieving state-of-the-art results in video restoration quality and delivery bandwidth compression.
- 7
- 7
- 7
- 7
- 7
- 6
- 6
- 6
- 6
- 6
- 6
- 5
- 5
- 5
- 5
- 5
- 5
- 5
- 5
- 5
- Adaptive Video Presentation for Small Display While Maximize Visual Information5
An intact and generic framework to adapt video presentation (AVP) is presented and a novel method for choosing the optimal cropped region is introduced to minimize the information loss over adapting video presentation.
- 4
- 4
- 4
- 4
- 4
- 4
- 4
- 4
- 4
- 4
- Denoising Saliency Map for Region of Interest Extraction4
The filter presented in this paper makes use of the property of saliency maps and can remove almost all the Gauss noise and pepper-salt noise while preserve the details of attention area.
- 3
- 3
- 3
- 3
- 2
- Training-Free Robust Interactive Video Object Segmentation2
This paper proposes a training-free prompt tracking framework for interactive video object segmentation (I-PT), leveraging the powerful generalization of SAM, and introduces a cross-round space-time module (CRSTM), which adaptively aggregates mask features from previous rounds and frames, enhancing the segmentation stability.
- 2
- 2
- 2
- 2
- 2
- 2
- 2
- 2
- 1
- 1
- 1
- 1
- 1
- –
- –
- –
- –
- –
- –
- –
- –
- –
- The SkatingVerse Workshop & Challenge: Methods and Results–
A brief summary of the SkatingVerse Workshop&Challenge is provided including brief introductions to the top three methods including brief introductions to the top three methods.
- –
- Technical Report for ActivityNet Challenge 2022 -- Temporal Action Localization–
Faster-TAD simplifies the pipeline of TAD and gets remarkable performance, obtaining comparable results as those of multi-step approaches.
- –
- –
- –
- –
- –
- –
- –
- –
- –
- –
- –
- –
- –
- –
- –
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.