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 5 / 6 页

  1. ICML 2024Learning in Deep Factor Graphs with Gaussian Belief Propagation
  2. ICML 2024LoRA Training in the NTK Regime has No Spurious Local Minima
  3. ICML 2024Memory Consolidation Enables Long-Context Video Understanding
  4. ICML 2024Momentor: Advancing Video Large Language Model with Fine-Grained Temporal Reasoning
  5. ICML 2024Multi-Factor Adaptive Vision Selection for Egocentric Video Question Answering
  6. ICML 2024NExT: Teaching Large Language Models to Reason about Code Execution
  7. ICML 2024On the Nonlinearity of Layer Normalization
  8. ICML 2024OT-CLIP: Understanding and Generalizing CLIP via Optimal Transport
  9. ICML 2024PID: Prompt-Independent Data Protection Against Latent Diffusion Models
  10. ICML 2024Position: Understanding LLMs Requires More Than Statistical Generalization
  11. ICML 2024Position: Why We Must Rethink Empirical Research in Machine Learning
  12. ICML 2024Privately Learning Smooth Distributions on the Hypercube by Projections
  13. ICML 2024Prompting a Pretrained Transformer Can Be a Universal Approximator
  14. ICML 2024Prototypical Transformer As Unified Motion Learners
  15. ICML 2024Provably Neural Active Learning Succeeds via Prioritizing Perplexing Samples
  16. ICML 2024ReLU Network with Width $d+\mathcal{O}(1)$ Can Achieve Optimal Approximation Rate
  17. ICML 2024S3O: A Dual-Phase Approach for Reconstructing Dynamic Shape and Skeleton of Articulated Objects from Single Monocular Video
  18. ICML 2024Towards a Better Theoretical Understanding of Independent Subnetwork Training
  19. ICML 2024Towards an Understanding of Stepwise Inference in Transformers: A Synthetic Graph Navigation Model
  20. ICML 2024Towards Generalization beyond Pointwise Learning: A Unified Information-theoretic Perspective
  21. ICML 2024Towards Theoretical Understanding of Learning Large-scale Dependent Data via Random Features
  22. ICML 2024Towards Understanding Inductive Bias in Transformers: A View From Infinity
  23. ICML 2024Towards Understanding the Word Sensitivity of Attention Layers: A Study via Random Features
  24. ICML 2024Trustworthy Actionable Perturbations
  25. ICML 2024Understanding Adam Optimizer via Online Learning of Updates: Adam is FTRL in Disguise
  26. ICML 2024Understanding and Diagnosing Deep Reinforcement Learning
  27. ICML 2024Understanding Diffusion Models by Feynman's Path Integral
  28. ICML 2024Understanding Finetuning for Factual Knowledge Extraction
  29. ICML 2024Understanding Forgetting in Continual Learning with Linear Regression
  30. ICML 2024Understanding Heterophily for Graph Neural Networks
  31. ICML 2024Understanding Inter-Concept Relationships in Concept-Based Models
  32. ICML 2024Understanding MLP-Mixer as a wide and sparse MLP
  33. ICML 2024Understanding Reasoning Ability of Language Models From the Perspective of Reasoning Paths Aggregation
  34. ICML 2024Understanding Server-Assisted Federated Learning in the Presence of Incomplete Client Participation
  35. ICML 2024Understanding Stochastic Natural Gradient Variational Inference
  36. ICML 2024Understanding the Effects of Iterative Prompting on Truthfulness
  37. ICML 2024Understanding the Impact of Introducing Constraints at Inference Time on Generalization Error
  38. ICML 2024Understanding the Learning Dynamics of Alignment with Human Feedback
  39. ICML 2024Understanding the Training Speedup from Sampling with Approximate Losses
  40. ICML 2024Understanding Unimodal Bias in Multimodal Deep Linear Networks
  41. ICML 2024Video-LaVIT: Unified Video-Language Pre-training with Decoupled Visual-Motional Tokenization
  42. ICML 2024Video-of-Thought: Step-by-Step Video Reasoning from Perception to Cognition
  43. ICML 2024VideoPrism: A Foundational Visual Encoder for Video Understanding
  44. ICML 2024Weisfeiler-Leman at the margin: When more expressivity matters
  45. ICML 2024Why Larger Language Models Do In-context Learning Differently?
  46. ICML 2023A Category-theoretical Meta-analysis of Definitions of Disentanglement
  47. ICML 2023Differentially Private Sharpness-Aware Training
  48. ICML 2023Dissecting the Effects of SGD Noise in Distinct Regimes of Deep Learning
  49. ICML 2023Does Sparsity Help in Learning Misspecified Linear Bandits?
  50. ICML 2023How Do Transformers Learn Topic Structure: Towards a Mechanistic 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