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 2,261 篇，第 36 / 46 页

  1. ICLR 2024Understanding In-Context Learning in Transformers and LLMs by Learning to Learn Discrete Functions
  2. ICLR 2024Understanding prompt engineering may not require rethinking generalization
  3. ICLR 2024Understanding Reconstruction Attacks with the Neural Tangent Kernel and Dataset Distillation
  4. ICLR 2024Understanding the Robustness of Multi-modal Contrastive Learning to Distribution Shift
  5. ICLR 2024Understanding the Robustness of Randomized Feature Defense Against Query-Based Adversarial Attacks
  6. ICLR 2024Understanding Transferable Representation Learning and Zero-shot Transfer in CLIP
  7. ICLR 2024Understanding when Dynamics-Invariant Data Augmentations Benefit Model-free Reinforcement Learning Updates
  8. ICLR 2024Unraveling the Key Components of OOD Generalization via Diversification
  9. ICLR 2024Video Decomposition Prior: Editing Videos Layer by Layer
  10. ICLR 2024Video Language Planning
  11. ICLR 2024VONet: Unsupervised Video Object Learning With Parallel U-Net Attention and Object-wise Sequential VAE
  12. ICLR 2024What Algorithms can Transformers Learn? A Study in Length Generalization
  13. ICML 2024A Mechanistic Understanding of Alignment Algorithms: A Case Study on DPO and Toxicity
  14. ICML 2024An Infinite-Width Analysis on the Jacobian-Regularised Training of a Neural Network
  15. ICML 2024AST-T5: Structure-Aware Pretraining for Code Generation and Understanding
  16. ICML 2024Boximator: Generating Rich and Controllable Motions for Video Synthesis
  17. ICML 2024Conditional Language Learning with Context
  18. ICML 2024Convex Relaxations of ReLU Neural Networks Approximate Global Optima in Polynomial Time
  19. ICML 2024DoraemonGPT: Toward Understanding Dynamic Scenes with Large Language Models (Exemplified as A Video Agent)
  20. ICML 2024Enhancing Sufficient Dimension Reduction via Hellinger Correlation
  21. ICML 2024EVEREST: Efficient Masked Video Autoencoder by Removing Redundant Spatiotemporal Tokens
  22. ICML 2024EvTexture: Event-driven Texture Enhancement for Video Super-Resolution
  23. ICML 2024Exploring the Complexity of Deep Neural Networks through Functional Equivalence
  24. ICML 2024Feature Reuse and Scaling: Understanding Transfer Learning with Protein Language Models
  25. ICML 2024Few-Shot Character Understanding in Movies as an Assessment to Meta-Learning of Theory-of-Mind
  26. ICML 2024FRAG: Frequency Adapting Group for Diffusion Video Editing
  27. ICML 2024High-Dimensional Kernel Methods under Covariate Shift: Data-Dependent Implicit Regularization
  28. ICML 2024How Does Goal Relabeling Improve Sample Efficiency?
  29. ICML 2024How Smooth Is Attention?
  30. ICML 2024Improving Context Understanding in Multimodal Large Language Models via Multimodal Composition Learning
  31. ICML 2024Improving fine-grained understanding in image-text pre-training
  32. ICML 2024Initial Guessing Bias: How Untrained Networks Favor Some Classes
  33. ICML 2024IOI: Invisible One-Iteration Adversarial Attack on No-Reference Image- and Video-Quality Metrics
  34. ICML 2024LangCell: Language-Cell Pre-training for Cell Identity Understanding
  35. ICML 2024Learning in Deep Factor Graphs with Gaussian Belief Propagation
  36. ICML 2024LoRA Training in the NTK Regime has No Spurious Local Minima
  37. ICML 2024Memory Consolidation Enables Long-Context Video Understanding
  38. ICML 2024Momentor: Advancing Video Large Language Model with Fine-Grained Temporal Reasoning
  39. ICML 2024Multi-Factor Adaptive Vision Selection for Egocentric Video Question Answering
  40. ICML 2024NExT: Teaching Large Language Models to Reason about Code Execution
  41. ICML 2024On the Nonlinearity of Layer Normalization
  42. ICML 2024OT-CLIP: Understanding and Generalizing CLIP via Optimal Transport
  43. ICML 2024PID: Prompt-Independent Data Protection Against Latent Diffusion Models
  44. ICML 2024Position: Understanding LLMs Requires More Than Statistical Generalization
  45. ICML 2024Position: Why We Must Rethink Empirical Research in Machine Learning
  46. ICML 2024Privately Learning Smooth Distributions on the Hypercube by Projections
  47. ICML 2024Prompting a Pretrained Transformer Can Be a Universal Approximator
  48. ICML 2024Prototypical Transformer As Unified Motion Learners
  49. ICML 2024Provably Neural Active Learning Succeeds via Prioritizing Perplexing Samples
  50. ICML 2024ReLU Network with Width $d+\mathcal{O}(1)$ Can Achieve Optimal Approximation Rate

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