欢迎分享CVPR 2024 论文和代码 / Welcome to share the paper and code of CVPR 2024

[amusi]

[The format of the issue] Paper name/title: Paper link: Code link:

[aeolusguan]

Paper name/title: Neural Markov Random Field for Stereo Matching Paper link: https://arxiv.org/abs/2403.11193 Code link: https://github.com/aeolusguan/NMRF

[Kiteretsu77]

Paper name/title: APISR: Anime Production Inspired Real-World Anime Super-Resolution Paper link: https://arxiv.org/abs/2403.01598 Code link: https://github.com/Kiteretsu77/APISR

[huangb23]

Paper name/title: VTimeLLM: Empower LLM to Grasp Video Moments Paper link: https://arxiv.org/abs/2311.18445 Code link: https://github.com/huangb23/VTimeLLM

[yangyijune]

Paper name/title: MMA-Diffusion: MultiModal Attack on Diffusion Models Paper link: https://arxiv.org/abs/2311.17516 Code link: https://github.com/yangyijune/MMA-Diffusion

[HyeonHo99]

Paper name/title: VMC: Video Motion Customization using Temporal Attention Adaption for Text-to-Video Diffusion Models Paper link: https://arxiv.org/abs/2312.00845 Code link: https://github.com/HyeonHo99/Video-Motion-Customization Project Page: https://video-motion-customization.github.io/

[xiuqhou]

Paper name/title: Salience DETR: Enhancing Detection Transformer with Hierarchical Salience Filtering Refinement Paper link: https://arxiv.org/abs/2403.16131 Code link: https://github.com/xiuqhou/Salience-DETR

[zhangce01]

Paper name/title: HiKER-SGG: Hierarchical Knowledge Enhanced Robust Scene Graph Generation Paper link: https://arxiv.org/abs/2403.12033 Code link: https://github.com/zhangce01/HiKER-SGG Project page: https://zhangce01.github.io/HiKER-SGG/

[cjerry1243]

Paper name/title: Learning from Synthetic Human Group Activities Paper link: https://arxiv.org/abs/2306.16772 Code link: https://github.com/cjerry1243/M3Act Project page: https://cjerry1243.github.io/M3Act/

[chen-si-jia]

Paper name/title: Delving into the Trajectory Long-tail Distribution for Muti-object Tracking Paper link: https://arxiv.org/abs/2403.04700 Code link: https://github.com/chen-si-jia/Trajectory-Long-tail-Distribution-for-MOT

[Vegetebird]

Paper name/title: Hourglass Tokenizer for Efficient Transformer-Based 3D Human Pose Estimation Paper link: https://arxiv.org/pdf/2311.12028.pdf Code link: https://github.com/NationalGAILab/HoT

[cherishleon]

Paper name/title: FairCLIP: Harnessing Fairness in Vision-Language Learning Paper link: https://arxiv.org/abs/2403.19949 Code link: https://github.com/Harvard-Ophthalmology-AI-Lab/FairCLIP Project Page: https://ophai.hms.harvard.edu/datasets/harvard-fairvlmed10k/

[QinYang79]

Paper name/title: Noisy-Correspondence Learning for Text-to-Image Person Re-identification Paper link: https://arxiv.org/pdf/2308.09911.pdf Code link: https://github.com/QinYang79/RDE

[littlepure2333]

Paper name/title: A Cross-Subject Brain Decoding Framework Project Page: https://littlepure2333.github.io/MindBridge/ Paper link: https://arxiv.org/abs/2404.07850 Code link: https://github.com/littlepure2333/MindBridge

[Osilly]

Paper name/title: A General and Efficient Training for Transformer via Token Expansion Paper link: https://arxiv.org/abs/2404.00672 Code link: https://github.com/Osilly/TokenExpansion

[YuqiYang213]

Paper name/title: Multi-Task Dense Prediction via Mixture of Low-Rank Experts Paper link: https://arxiv.org/abs/2403.17749 Code link: https://github.com/YuqiYang213/MLoRE

[YuqiYang213]

Paper name/title: Traffic Scene Parsing through the TSP6K Dataset Paper link: https://arxiv.org/pdf/2303.02835.pdf Code link: https://github.com/PengtaoJiang/TSP6K

[dahyun-kang]

Paper name/title: Contrastive Mean-Shift Learning for Generalized Category Discovery Paper link: https://arxiv.org/abs/2404.09451 Code link: https://github.com/sua-choi/CMS Project page: https://postech-cvlab.github.io/cms/

[littlepure2333]

Paper name/title: A Cross-Subject Brain Decoding Framework Project Page: https://littlepure2333.github.io/MindBridge/ Paper link: https://arxiv.org/abs/2404.07850 Code link: https://github.com/littlepure2333/MindBridge

Sorry, the title should be: MindBridge: A Cross-Subject Brain Decoding Framework

[pablomm]

Paper name/title: Open-Vocabulary Attention Maps with Token Optimization for Semantic Segmentation in Diffusion Models Paper link: https://arxiv.org/abs/2403.14291 Code link: https://github.com/vpulab/ovam

[Dayan-Guan]

Paper name/title: Efficient Test-Time Adaptation of Vision-Language Models Paper link: https://arxiv.org/abs/2403.18293 Code link: https://github.com/kdiAAA/TDA

[TQTQliu]

Paper name/title: Geometry-aware Reconstruction and Fusion-refined Rendering for Generalizable Neural Radiance Fields Paper link: https://arxiv.org/abs/2404.17528 Code link: https://github.com/TQTQliu/GeFu Project page: https://gefucvpr24.github.io/

[2y7c3]

Paper name/title: Adversarial Score Distillation: When score distillation meets GAN Arxiv link: https://arxiv.org/abs/2312.00739 (updating) Paper link: https://2y7c3.github.io/pdfs/asd.pdf Code link: https://github.com/2y7c3/ASD

[ZhaoChuyang]

Paper name/title: MS-DETR: Efficient DETR Training with Mixed Supervision Paer link: https://arxiv.org/pdf/2401.03989 Code link: https://github.com/Atten4Vis/MS-DETR

[youngLBW]

Paper name/title: DiffusionGAN3D: Boosting Text-guided 3D Generation and Domain Adaptation by Combining 3D GANs and Diffusion Priors Paper link: https://arxiv.org/abs/2312.16837 Project page: https://younglbw.github.io/DiffusionGAN3D-homepage Code link: https://github.com/youngLBW/DiffusionGAN3D

[demo4ai]

Paper name/title: BlockGCN: Redefine Topology Awareness for Skeleton-Based Action Recognition Paper link: https://www.researchgate.net/publication/379411619_BlockGCN_Redefining_Topology_Awareness_for_Skeleton-Based_Action_Recognition Code link: https://github.com/ZhouYuxuanYX/BlockGCN

[jaewonalive]

Paper name/title: PeerAiD: Improving Adversarial Distillation from a Specialized Peer Tutor Paper link: https://arxiv.org/abs/2403.06668 Code link: https://github.com/jaewonalive/PeerAiD

[LQY404]

Paper name/title: CLIP as RNN: Segment Countless Visual Concepts without Training Endeavor Project link: https://torrvision.com/clip_as_rnn/ Code link: https://github.com/kevin-ssy/CLIP_as_RNN

[LQY404]

Paper name/title: ASAM: Boosting Segment Anything Model with Adversarial Tuning Project link: https://link.zhihu.com/?target=https%3A//asam2024.github.io/ Code link: https://github.com/luckybird1994/ASAM

[caiyuanhao1998]

Paper name/title: Structure-Aware Sparse-View X-ray 3D Reconstruction Paper link: https://arxiv.org/abs/2311.10959 Code link: https://github.com/caiyuanhao1998/SAX-NeRF

[Nicholas0228]

Paper name/title: CGI-DM: Digital Copyright Authentication for Diffusion Models via Contrasting Gradient Inversion Paper link: https://arxiv.org/abs/2403.11162 Code link: https://github.com/Nicholas0228/Revelio

[Linwei-Chen]

Paper name/title: CVPR 2024 Poster (Highlight): Frequency-Adaptive Dilated Convolution for Semantic Segmentation Paper link: https://arxiv.org/abs/2403.05369 Code link: https://github.com/Linwei-Chen/FADC

[gswycf]

[The format of the issue] Paper name/title: SignGraph: A Sign Sequence is Worth Graphs of Nodes Paper link: https://openaccess.thecvf.com/content/CVPR2024/papers/Gan_SignGraph_A_Sign_Sequence_is_Worth_Graphs_of_Nodes_CVPR_2024_paper.pdf Code link: https://github.com/gswycf/SignGraph

[xxayt]

Paper name/title: Holistic Features are almost Sufficient for Text-to-Video Retrieval Paper link: https://openaccess.thecvf.com/content/CVPR2024/papers/Tian_Holistic_Features_are_almost_Sufficient_for_Text-to-Video_Retrieval_CVPR_2024_paper.pdf Code link: https://github.com/ruc-aimc-lab/TeachCLIP