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 37 / 46 页

  1. ICML 2024S3O: A Dual-Phase Approach for Reconstructing Dynamic Shape and Skeleton of Articulated Objects from Single Monocular Video
  2. ICML 2024Towards a Better Theoretical Understanding of Independent Subnetwork Training
  3. ICML 2024Towards an Understanding of Stepwise Inference in Transformers: A Synthetic Graph Navigation Model
  4. ICML 2024Towards Generalization beyond Pointwise Learning: A Unified Information-theoretic Perspective
  5. ICML 2024Towards Theoretical Understanding of Learning Large-scale Dependent Data via Random Features
  6. ICML 2024Towards Understanding Inductive Bias in Transformers: A View From Infinity
  7. ICML 2024Towards Understanding the Word Sensitivity of Attention Layers: A Study via Random Features
  8. ICML 2024Trustworthy Actionable Perturbations
  9. ICML 2024Understanding Adam Optimizer via Online Learning of Updates: Adam is FTRL in Disguise
  10. ICML 2024Understanding and Diagnosing Deep Reinforcement Learning
  11. ICML 2024Understanding Diffusion Models by Feynman's Path Integral
  12. ICML 2024Understanding Finetuning for Factual Knowledge Extraction
  13. ICML 2024Understanding Forgetting in Continual Learning with Linear Regression
  14. ICML 2024Understanding Heterophily for Graph Neural Networks
  15. ICML 2024Understanding Inter-Concept Relationships in Concept-Based Models
  16. ICML 2024Understanding MLP-Mixer as a wide and sparse MLP
  17. ICML 2024Understanding Reasoning Ability of Language Models From the Perspective of Reasoning Paths Aggregation
  18. ICML 2024Understanding Server-Assisted Federated Learning in the Presence of Incomplete Client Participation
  19. ICML 2024Understanding Stochastic Natural Gradient Variational Inference
  20. ICML 2024Understanding the Effects of Iterative Prompting on Truthfulness
  21. ICML 2024Understanding the Impact of Introducing Constraints at Inference Time on Generalization Error
  22. ICML 2024Understanding the Learning Dynamics of Alignment with Human Feedback
  23. ICML 2024Understanding the Training Speedup from Sampling with Approximate Losses
  24. ICML 2024Understanding Unimodal Bias in Multimodal Deep Linear Networks
  25. ICML 2024Video-LaVIT: Unified Video-Language Pre-training with Decoupled Visual-Motional Tokenization
  26. ICML 2024Video-of-Thought: Step-by-Step Video Reasoning from Perception to Cognition
  27. ICML 2024VideoPrism: A Foundational Visual Encoder for Video Understanding
  28. ICML 2024Weisfeiler-Leman at the margin: When more expressivity matters
  29. ICML 2024Why Larger Language Models Do In-context Learning Differently?
  30. NeurIPS 2024$E^3$: Exploring Embodied Emotion Through A Large-Scale Egocentric Video Dataset
  31. NeurIPS 20243DCoMPaT200: Language Grounded Large-Scale 3D Vision Dataset for Compositional Recognition
  32. NeurIPS 2024A Theoretical Understanding of Self-Correction through In-context Alignment
  33. NeurIPS 2024ActionAtlas: A VideoQA Benchmark for Domain-specialized Action Recognition
  34. NeurIPS 2024Advancing Video Anomaly Detection: A Concise Review and a New Dataset
  35. NeurIPS 2024Animal-Bench: Benchmarking Multimodal Video Models for Animal-centric Video Understanding
  36. NeurIPS 2024Artemis: Towards Referential Understanding in Complex Videos
  37. NeurIPS 2024AverNet: All-in-one Video Restoration for Time-varying Unknown Degradations
  38. NeurIPS 2024Beyond Euclidean: Dual-Space Representation Learning for Weakly Supervised Video Violence Detection
  39. NeurIPS 2024bit2bit: 1-bit quanta video reconstruction via self-supervised photon prediction
  40. NeurIPS 2024CALVIN: Improved Contextual Video Captioning via Instruction Tuning
  41. NeurIPS 2024CaptainCook4D: A Dataset for Understanding Errors in Procedural Activities
  42. NeurIPS 2024CharXiv: Charting Gaps in Realistic Chart Understanding in Multimodal LLMs
  43. NeurIPS 2024Chat-Scene: Bridging 3D Scene and Large Language Models with Object Identifiers
  44. NeurIPS 2024Cross-video Identity Correlating for Person Re-identification Pre-training
  45. NeurIPS 2024CulturePark: Boosting Cross-cultural Understanding in Large Language Models
  46. NeurIPS 2024Differentiable Task Graph Learning: Procedural Activity Representation and Online Mistake Detection from Egocentric Videos
  47. NeurIPS 2024Don't Look Twice: Faster Video Transformers with Run-Length Tokenization
  48. NeurIPS 2024E.T. Bench: Towards Open-Ended Event-Level Video-Language Understanding
  49. NeurIPS 2024End-to-End Video Semantic Segmentation in Adverse Weather using Fusion Blocks and Temporal-Spatial Teacher-Student Learning
  50. NeurIPS 2024Estimating Ego-Body Pose from Doubly Sparse Egocentric Video Data

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