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 6 / 7 页

  1. ICML 2023Reinforcement Learning from Passive Data via Latent Intentions
  2. ICML 2023Reliable Measures of Spread in High Dimensional Latent Spaces
  3. ICML 2023SpotEM: Efficient Video Search for Episodic Memory
  4. ICML 2023Temporally Consistent Transformers for Video Generation
  5. ICML 2023Towards a better understanding of representation dynamics under TD-learning
  6. ICML 2023Towards Theoretical Understanding of Inverse Reinforcement Learning
  7. ICML 2023Towards Understanding and Improving GFlowNet Training
  8. ICML 2023Towards Understanding and Reducing Graph Structural Noise for GNNs
  9. ICML 2023Towards Understanding Ensemble Distillation in Federated Learning
  10. ICML 2023Transformers Meet Directed Graphs
  11. ICML 2023Understanding Backdoor Attacks through the Adaptability Hypothesis
  12. ICML 2023Understanding Gradient Regularization in Deep Learning: Efficient Finite-Difference Computation and Implicit Bias
  13. ICML 2023Understanding Incremental Learning of Gradient Descent: A Fine-grained Analysis of Matrix Sensing
  14. ICML 2023Understanding Int4 Quantization for Language Models: Latency Speedup, Composability, and Failure Cases
  15. ICML 2023Understanding Oversquashing in GNNs through the Lens of Effective Resistance
  16. ICML 2023Understanding Plasticity in Neural Networks
  17. ICML 2023Understanding Self-Distillation in the Presence of Label Noise
  18. ICML 2023Understanding Self-Predictive Learning for Reinforcement Learning
  19. ICML 2023Understanding the Role of Feedback in Online Learning with Switching Costs
  20. ICML 2023What Can Be Learnt With Wide Convolutional Neural Networks?
  21. ICML 2023When and How Does Known Class Help Discover Unknown Ones? Provable Understanding Through Spectral Analysis
  22. ICML 2023WL meet VC
  23. NeurIPS 2023A Multi-modal Global Instance Tracking Benchmark (MGIT): Better Locating Target in Complex Spatio-temporal and Causal Relationship
  24. NeurIPS 2023ASL Citizen: A Community-Sourced Dataset for Advancing Isolated Sign Language Recognition
  25. NeurIPS 2023Balance, Imbalance, and Rebalance: Understanding Robust Overfitting from a Minimax Game Perspective
  26. NeurIPS 2023Bitstream-Corrupted Video Recovery: A Novel Benchmark Dataset and Method
  27. NeurIPS 2023CAST: Cross-Attention in Space and Time for Video Action Recognition
  28. NeurIPS 2023Compressed Video Prompt Tuning
  29. NeurIPS 2023Curriculum Learning With Infant Egocentric Videos
  30. NeurIPS 2023Diversifying Spatial-Temporal Perception for Video Domain Generalization
  31. NeurIPS 2023Dynamic Non-monotone Submodular Maximization
  32. NeurIPS 2023Ego4D Goal-Step: Toward Hierarchical Understanding of Procedural Activities
  33. NeurIPS 2023EgoDistill: Egocentric Head Motion Distillation for Efficient Video Understanding
  34. NeurIPS 2023EgoEnv: Human-centric environment representations from egocentric video
  35. NeurIPS 2023EgoSchema: A Diagnostic Benchmark for Very Long-form Video Language Understanding
  36. NeurIPS 2023EPIC Fields: Marrying 3D Geometry and Video Understanding
  37. NeurIPS 2023Explore In-Context Learning for 3D Point Cloud Understanding
  38. NeurIPS 2023From ViT Features to Training-free Video Object Segmentation via Streaming-data Mixture Models
  39. NeurIPS 2023HA-ViD: A Human Assembly Video Dataset for Comprehensive Assembly Knowledge Understanding
  40. NeurIPS 2023HT-Step: Aligning Instructional Articles with How-To Videos
  41. NeurIPS 2023InfoPrompt: Information-Theoretic Soft Prompt Tuning for Natural Language Understanding
  42. NeurIPS 2023Language-based Action Concept Spaces Improve Video Self-Supervised Learning
  43. NeurIPS 2023NurViD: A Large Expert-Level Video Database for Nursing Procedure Activity Understanding
  44. NeurIPS 2023On the choice of Perception Loss Function for Learned Video Compression
  45. NeurIPS 2023Opening the Vocabulary of Egocentric Actions
  46. NeurIPS 2023Revealing the unseen: Benchmarking video action recognition under occlusion
  47. NeurIPS 2023RVD: A Handheld Device-Based Fundus Video Dataset for Retinal Vessel Segmentation
  48. NeurIPS 2023Scan and Snap: Understanding Training Dynamics and Token Composition in 1-layer Transformer
  49. NeurIPS 2023Self-supervised video pretraining yields robust and more human-aligned visual representations
  50. NeurIPS 2023Small batch deep reinforcement 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