视频理解论文趋势 2023–2026

视频识别与理解

统计范围：NeurIPS、ICLR、ICML、CVPR 四个会议，2023–2026 年，共 2,261 篇被归入该主题的论文。

主要结论

每年论文数

各会议论文数

按年份和会议统计

视频理解论文数，按年份和会议
年份NeurIPSICLRICMLCVPR合计
2023474434194319
20241134767204431
20252229564298679
2026229148114341832

代表论文

按年份和会议均匀挑选，方便快速看到每一届的样貌

全部视频理解论文

年份全部2023202420252026
会议全部NeurIPSICLRICMLCVPR

共 319 篇，第 4 / 7 页

  1. CVPR 2023Simultaneously Short- and Long-Term Temporal Modeling for Semi-Supervised Video Semantic Segmentation
  2. CVPR 2023Source-Free Video Domain Adaptation With Spatial-Temporal-Historical Consistency Learning
  3. CVPR 2023Spatial-Then-Temporal Self-Supervised Learning for Video Correspondence
  4. CVPR 2023Streaming Video Model
  5. CVPR 2023Structured Sparsity Learning for Efficient Video Super-Resolution
  6. CVPR 2023SVFormer: Semi-Supervised Video Transformer for Action Recognition
  7. CVPR 2023SViTT: Temporal Learning of Sparse Video-Text Transformers
  8. CVPR 2023System-Status-Aware Adaptive Network for Online Streaming Video Understanding
  9. CVPR 2023TarViS: A Unified Approach for Target-Based Video Segmentation
  10. CVPR 2023Test of Time: Instilling Video-Language Models With a Sense of Time
  11. CVPR 2023Therbligs in Action: Video Understanding Through Motion Primitives
  12. CVPR 2023TimeBalance: Temporally-Invariant and Temporally-Distinctive Video Representations for Semi-Supervised Action Recognition
  13. CVPR 2023Towards Effective Adversarial Textured 3D Meshes on Physical Face Recognition
  14. CVPR 2023Towards High-Quality and Efficient Video Super-Resolution via Spatial-Temporal Data Overfitting
  15. CVPR 2023Transformer-Based Unified Recognition of Two Hands Manipulating Objects
  16. CVPR 2023Two-Shot Video Object Segmentation
  17. CVPR 2023ULIP: Learning a Unified Representation of Language, Images, and Point Clouds for 3D Understanding
  18. CVPR 2023Ultrahigh Resolution Image/Video Matting With Spatio-Temporal Sparsity
  19. CVPR 2023Unbiased Multiple Instance Learning for Weakly Supervised Video Anomaly Detection
  20. CVPR 2023Understanding and Constructing Latent Modality Structures in Multi-Modal Representation Learning
  21. CVPR 2023Understanding and Improving Features Learned in Deep Functional Maps
  22. CVPR 2023Understanding and Improving Visual Prompting: A Label-Mapping Perspective
  23. CVPR 2023Understanding Deep Generative Models With Generalized Empirical Likelihoods
  24. CVPR 2023Understanding Imbalanced Semantic Segmentation Through Neural Collapse
  25. CVPR 2023Understanding Masked Autoencoders via Hierarchical Latent Variable Models
  26. CVPR 2023Understanding Masked Image Modeling via Learning Occlusion Invariant Feature
  27. CVPR 2023Use Your Head: Improving Long-Tail Video Recognition
  28. CVPR 2023Vid2Seq: Large-Scale Pretraining of a Visual Language Model for Dense Video Captioning
  29. CVPR 2023Video Compression With Entropy-Constrained Neural Representations
  30. CVPR 2023Video Dehazing via a Multi-Range Temporal Alignment Network With Physical Prior
  31. CVPR 2023Video Event Restoration Based on Keyframes for Video Anomaly Detection
  32. CVPR 2023Video Probabilistic Diffusion Models in Projected Latent Space
  33. CVPR 2023Video Test-Time Adaptation for Action Recognition
  34. CVPR 2023Video-Text As Game Players: Hierarchical Banzhaf Interaction for Cross-Modal Representation Learning
  35. CVPR 2023VideoFusion: Decomposed Diffusion Models for High-Quality Video Generation
  36. CVPR 2023VideoMAE V2: Scaling Video Masked Autoencoders With Dual Masking
  37. CVPR 2023VideoTrack: Learning To Track Objects via Video Transformer
  38. CVPR 2023VindLU: A Recipe for Effective Video-and-Language Pretraining
  39. CVPR 2023Vita-CLIP: Video and Text Adaptive CLIP via Multimodal Prompting
  40. CVPR 2023VIVE3D: Viewpoint-Independent Video Editing Using 3D-Aware GANs
  41. CVPR 2023VoP: Text-Video Co-Operative Prompt Tuning for Cross-Modal Retrieval
  42. CVPR 2023Weakly Supervised Video Emotion Detection and Prediction via Cross-Modal Temporal Erasing Network
  43. CVPR 2023Weakly Supervised Video Representation Learning With Unaligned Text for Sequential Videos
  44. CVPR 2023WINNER: Weakly-Supervised hIerarchical decompositioN and aligNment for Spatio-tEmporal Video gRounding
  45. ICLR 2023A Theoretical Understanding of Shallow Vision Transformers: Learning, Generalization, and Sample Complexity
  46. ICLR 2023AIM: Adapting Image Models for Efficient Video Action Recognition
  47. ICLR 2023Boosting Adversarial Transferability using Dynamic Cues
  48. ICLR 2023Characterizing intrinsic compositionality in transformers with Tree Projections
  49. ICLR 2023Deconstructing Distributions: A Pointwise Framework of Learning
  50. ICLR 2023DensePure: Understanding Diffusion Models for Adversarial Robustness

在 Claude、Cursor 里直接问这个趋势

接上 Paperlist MCP 后，写综述、挑方向或准备投稿时，不用离开对话框就能拿到这页的数字：每年各会议的论文数、增长倍数、涨得最快的子方向和代表论文，AI 会按你的问题整理。

可以直接复制这句话问 AI

用 paperlist 查视频理解在 CVPR 2023–2026 的论文趋势，哪一年涨得最快？

AI 会调用的工具：get_topic_stats {"topic": "video-understanding"}

两分钟接入 Paperlist MCP（Claude Code、Cursor、Codex、ChatGPT）

常见问题

2023–2026 年四大会议一共有多少篇视频理解论文？
共 2,261 篇，按年份分别是 2023 年 319 篇、2024 年 431 篇、2025 年 679 篇、2026 年 832 篇。
NeurIPS 2026 有多少篇视频理解论文？
NeurIPS 2026 有 229 篇视频理解论文，上一届是 222 篇。
ICLR 2026 有多少篇视频理解论文？
ICLR 2026 有 148 篇视频理解论文，上一届是 95 篇。
ICML 2026 有多少篇视频理解论文？
ICML 2026 有 114 篇视频理解论文，上一届是 64 篇。
CVPR 2026 有多少篇视频理解论文？
CVPR 2026 有 341 篇视频理解论文，上一届是 298 篇。
哪个会议的视频理解论文最多？
CVPR，2023–2026 年共 1,037 篇。

「计算机视觉」下的其他主题