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 1,037 篇，第 19 / 21 页

  1. CVPR 2023Global-to-Local Modeling for Video-Based 3D Human Pose and Shape Estimation
  2. CVPR 2023Hand Avatar: Free-Pose Hand Animation and Rendering From Monocular Video
  3. CVPR 2023HARP: Personalized Hand Reconstruction From a Monocular RGB Video
  4. CVPR 2023Hierarchical B-Frame Video Coding Using Two-Layer CANF Without Motion Coding
  5. CVPR 2023Hierarchical Semantic Correspondence Networks for Video Paragraph Grounding
  6. CVPR 2023Hierarchical Temporal Transformer for 3D Hand Pose Estimation and Action Recognition From Egocentric RGB Videos
  7. CVPR 2023Hierarchical Video-Moment Retrieval and Step-Captioning
  8. CVPR 2023HierVL: Learning Hierarchical Video-Language Embeddings
  9. CVPR 2023High-Fidelity and Freely Controllable Talking Head Video Generation
  10. CVPR 2023High-Fidelity Event-Radiance Recovery via Transient Event Frequency
  11. CVPR 2023High-Fidelity Facial Avatar Reconstruction From Monocular Video With Generative Priors
  12. CVPR 2023How Can Objects Help Action Recognition?
  13. CVPR 2023How You Feelin'? Learning Emotions and Mental States in Movie Scenes
  14. CVPR 2023Hybrid Active Learning via Deep Clustering for Video Action Detection
  15. CVPR 2023HyperCUT: Video Sequence From a Single Blurry Image Using Unsupervised Ordering
  16. CVPR 2023HyperReel: High-Fidelity 6-DoF Video With Ray-Conditioned Sampling
  17. CVPR 2023Improving Visual Representation Learning Through Perceptual Understanding
  18. CVPR 2023Instant Volumetric Head Avatars
  19. CVPR 2023InstantAvatar: Learning Avatars From Monocular Video in 60 Seconds
  20. CVPR 2023Is BERT Blind? Exploring the Effect of Vision-and-Language Pretraining on Visual Language Understanding
  21. CVPR 2023Iterative Proposal Refinement for Weakly-Supervised Video Grounding
  22. CVPR 2023Joint Video Multi-Frame Interpolation and Deblurring Under Unknown Exposure Time
  23. CVPR 2023Language-Guided Music Recommendation for Video via Prompt Analogies
  24. CVPR 2023Large-Capacity and Flexible Video Steganography via Invertible Neural Network
  25. CVPR 2023LAVENDER: Unifying Video-Language Understanding As Masked Language Modeling
  26. CVPR 2023Learning Action Changes by Measuring Verb-Adverb Textual Relationships
  27. CVPR 2023Learning Event Guided High Dynamic Range Video Reconstruction
  28. CVPR 2023Learning Personalized High Quality Volumetric Head Avatars From Monocular RGB Videos
  29. CVPR 2023Learning Procedure-Aware Video Representation From Instructional Videos and Their Narrations
  30. CVPR 2023Learning Situation Hyper-Graphs for Video Question Answering
  31. CVPR 2023Learning Spatial-Temporal Implicit Neural Representations for Event-Guided Video Super-Resolution
  32. CVPR 2023Learning Video Representations From Large Language Models
  33. CVPR 2023LidarGait: Benchmarking 3D Gait Recognition With Point Clouds
  34. CVPR 2023LightedDepth: Video Depth Estimation in Light of Limited Inference View Angles
  35. CVPR 2023LOGO: A Long-Form Video Dataset for Group Action Quality Assessment
  36. CVPR 2023Long Range Pooling for 3D Large-Scale Scene Understanding
  37. CVPR 2023Look Before You Match: Instance Understanding Matters in Video Object Segmentation
  38. CVPR 2023MAGVIT: Masked Generative Video Transformer
  39. CVPR 2023MammalNet: A Large-Scale Video Benchmark for Mammal Recognition and Behavior Understanding
  40. CVPR 2023MARLIN: Masked Autoencoder for Facial Video Representation LearnINg
  41. CVPR 2023Mask-Free Video Instance Segmentation
  42. CVPR 2023Masked Motion Encoding for Self-Supervised Video Representation Learning
  43. CVPR 2023MDQE: Mining Discriminative Query Embeddings To Segment Occluded Instances on Challenging Videos
  44. CVPR 2023MED-VT: Multiscale Encoder-Decoder Video Transformer With Application To Object Segmentation
  45. CVPR 2023Meta-Personalizing Vision-Language Models To Find Named Instances in Video
  46. CVPR 2023MIST: Multi-Modal Iterative Spatial-Temporal Transformer for Long-Form Video Question Answering
  47. CVPR 2023MM-3DScene: 3D Scene Understanding by Customizing Masked Modeling With Informative-Preserved Reconstruction and Self-Distilled Consistency
  48. CVPR 2023MMVC: Learned Multi-Mode Video Compression With Block-Based Prediction Mode Selection and Density-Adaptive Entropy Coding
  49. CVPR 2023MobileVOS: Real-Time Video Object Segmentation Contrastive Learning Meets Knowledge Distillation
  50. CVPR 2023Modeling Video As Stochastic Processes for Fine-Grained Video Representation Learning

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