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 279 篇，第 4 / 6 页

  1. ICML 2025Train for the Worst, Plan for the Best: Understanding Token Ordering in Masked Diffusions
  2. ICML 2025TUMTraf VideoQA: Dataset and Benchmark for Unified Spatio-Temporal Video Understanding in Traffic Scenes
  3. ICML 2025Understanding and Improving Length Generalization in Recurrent Models
  4. ICML 2025Understanding and Mitigating Memorization in Diffusion Models for Tabular Data
  5. ICML 2025Understanding and Mitigating Memorization in Generative Models via Sharpness of Probability Landscapes
  6. ICML 2025Understanding and Mitigating Miscalibration in Prompt Tuning for Vision-Language Models
  7. ICML 2025Understanding Chain-of-Thought in LLMs through Information Theory
  8. ICML 2025Understanding Fixed Predictions via Confined Regions
  9. ICML 2025Understanding Generalization in Quantum Machine Learning with Margins
  10. ICML 2025Understanding High-Dimensional Bayesian Optimization
  11. ICML 2025Understanding Input Selectivity in Mamba: Impact on Approximation Power, Memorization, and Associative Recall Capacity
  12. ICML 2025Understanding Mode Connectivity via Parameter Space Symmetry
  13. ICML 2025Understanding Model Reprogramming for CLIP via Decoupling Visual Prompts
  14. ICML 2025Understanding Multimodal LLMs Under Distribution Shifts: An Information-Theoretic Approach
  15. ICML 2025Understanding Nonlinear Implicit Bias via Region Counts in Input Space
  16. ICML 2025Understanding Sharpness Dynamics in NN Training with a Minimalist Example: The Effects of Dataset Difficulty, Depth, Stochasticity, and More
  17. ICML 2025Understanding the difficulties of posterior predictive estimation
  18. ICML 2025Understanding the Emergence of Multimodal Representation Alignment
  19. ICML 2025Understanding the Forgetting of (Replay-based) Continual Learning via Feature Learning: Angle Matters
  20. ICML 2025Understanding the Kronecker Matrix-Vector Complexity of Linear Algebra
  21. ICML 2025Understanding the Limits of Deep Tabular Methods with Temporal Shift
  22. ICML 2025Understanding the Statistical Accuracy-Communication Trade-off in Personalized Federated Learning with Minimax Guarantees
  23. ICML 2025Understanding the Unfairness in Network Quantization
  24. ICML 2025Unifying Specialized Visual Encoders for Video Language Models
  25. ICML 2025Video-Enhanced Offline Reinforcement Learning: A Model-Based Approach
  26. ICML 2025VideoJAM: Joint Appearance-Motion Representations for Enhanced Motion Generation in Video Models
  27. ICML 2025VideoRoPE: What Makes for Good Video Rotary Position Embedding?
  28. ICML 2025WikiBigEdit: Understanding the Limits of Lifelong Knowledge Editing in LLMs
  29. ICML 2024A Mechanistic Understanding of Alignment Algorithms: A Case Study on DPO and Toxicity
  30. ICML 2024An Infinite-Width Analysis on the Jacobian-Regularised Training of a Neural Network
  31. ICML 2024AST-T5: Structure-Aware Pretraining for Code Generation and Understanding
  32. ICML 2024Boximator: Generating Rich and Controllable Motions for Video Synthesis
  33. ICML 2024Conditional Language Learning with Context
  34. ICML 2024Convex Relaxations of ReLU Neural Networks Approximate Global Optima in Polynomial Time
  35. ICML 2024DoraemonGPT: Toward Understanding Dynamic Scenes with Large Language Models (Exemplified as A Video Agent)
  36. ICML 2024Enhancing Sufficient Dimension Reduction via Hellinger Correlation
  37. ICML 2024EVEREST: Efficient Masked Video Autoencoder by Removing Redundant Spatiotemporal Tokens
  38. ICML 2024EvTexture: Event-driven Texture Enhancement for Video Super-Resolution
  39. ICML 2024Exploring the Complexity of Deep Neural Networks through Functional Equivalence
  40. ICML 2024Feature Reuse and Scaling: Understanding Transfer Learning with Protein Language Models
  41. ICML 2024Few-Shot Character Understanding in Movies as an Assessment to Meta-Learning of Theory-of-Mind
  42. ICML 2024FRAG: Frequency Adapting Group for Diffusion Video Editing
  43. ICML 2024High-Dimensional Kernel Methods under Covariate Shift: Data-Dependent Implicit Regularization
  44. ICML 2024How Does Goal Relabeling Improve Sample Efficiency?
  45. ICML 2024How Smooth Is Attention?
  46. ICML 2024Improving Context Understanding in Multimodal Large Language Models via Multimodal Composition Learning
  47. ICML 2024Improving fine-grained understanding in image-text pre-training
  48. ICML 2024Initial Guessing Bias: How Untrained Networks Favor Some Classes
  49. ICML 2024IOI: Invisible One-Iteration Adversarial Attack on No-Reference Image- and Video-Quality Metrics
  50. ICML 2024LangCell: Language-Cell Pre-training for Cell Identity Understanding

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