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 148 篇，第 3 / 3 页

  1. ICLR 2026Towards a Theoretical Understanding of In-context Learning: Stability and Non-I.I.D Generalisation
  2. ICLR 2026Towards Spatial Supersensing in Video
  3. ICLR 2026Towards Understanding Subliminal Learning: When and How Hidden Biases Transfer
  4. ICLR 2026Towards Understanding The Calibration Benefits of Sharpness-Aware Minimization
  5. ICLR 2026Towards Understanding the Shape of Representations in Protein Language Models
  6. ICLR 2026Towards Understanding Valuable Preference Data for Large Language Model Alignment
  7. ICLR 2026TPDiff: Temporal Pyramid Video Diffusion Model
  8. ICLR 2026TPRU: Advancing Temporal and Procedural Understanding in Large Multimodal Models
  9. ICLR 2026Trace Anything: Representing Any Video in 4D via Trajectory Fields
  10. ICLR 2026TripleSumm: Adaptive Triple-Modality Fusion for Video Summarization
  11. ICLR 2026U2-BENCH: Benchmarking Large Vision-Language Models on Ultrasound Understanding
  12. ICLR 2026UltraViCo: Breaking Extrapolation Limits in Video Diffusion Transformers
  13. ICLR 2026Understanding and Improving Hyperbolic Deep Reinforcement Learning
  14. ICLR 2026Understanding and Improving Length Generalization in Hierarchical Sparse Attention Models
  15. ICLR 2026Understanding and improving Shampoo and SOAP via Kullback-Leibler Minimization
  16. ICLR 2026Understanding and Relaxing the Limitations of Transformers for Linear Algebra
  17. ICLR 2026Understanding In-Context Learning on Structured Manifolds: Bridging Attention to Kernel Methods
  18. ICLR 2026Understanding Language Prior of LVLMs by Contrasting Chain-of-Embedding
  19. ICLR 2026Understanding Routing Mechanism in Mixture-of-Experts Language Models
  20. ICLR 2026Understanding Task Vectors in In-Context Learning: Emergence, Functionality, and Limitations
  21. ICLR 2026Understanding the Dynamics of Forgetting and Generalization in Continual Learning via the Neural Tangent Kernel
  22. ICLR 2026Understanding the Emergence of Seemingly Useless Features in Next-Token Predictors
  23. ICLR 2026Understanding the Learning Phases in Self-Supervised Learning via Critical Periods
  24. ICLR 2026Understanding the Mechanisms of Fast Hyperparameter Transfer
  25. ICLR 2026Understanding the Mixture-of-Experts with Nadaraya-Watson Kernel
  26. ICLR 2026Understanding the Robustness of Distributed Self-Supervised Learning Frameworks Against Non-IID Data
  27. ICLR 2026Understanding the Role of Training Data in Test-Time Scaling
  28. ICLR 2026UNDERSTANDING TRANSFORMERS FOR TIME SEIRES FORECASTING: A CASE STUDY ON MOIRAI
  29. ICLR 2026Unified In-Context Video Editing
  30. ICLR 2026UniTrack: Differentiable Graph Representation Learning for Multi-Object Tracking
  31. ICLR 2026UrbanFeel：A Comprehensive Benchmark for Temporal and Perceptual Understanding of City Scenes through Human Perspective
  32. ICLR 2026V2P-Bench: Evaluating Video-Language Understanding with Visual Prompts for Better Human-Model Interaction
  33. ICLR 2026Variation in Verification: Understanding Verification Dynamics in Large Language Models
  34. ICLR 2026VenusX: Unlocking Fine-Grained Functional Understanding of Proteins
  35. ICLR 2026Vid-LLM: A Compact Video-based 3D Multimodal LLM with Reconstruction–Reasoning Synergy
  36. ICLR 2026Vid2World: Crafting Video Diffusion Models to Interactive World Models
  37. ICLR 2026VidBridge-R1: Bridging QA and Captioning for RL-based Video Understanding Models with Intermediate Proxy Tasks
  38. ICLR 2026Video Scene Segmentation with Genre and Duration Signals
  39. ICLR 2026Video-GPT via Next Clip Diffusion
  40. ICLR 2026Video-LevelGauge: Investigating Contextual Positional Bias in Video Language Models.
  41. ICLR 2026VideoJudge: Bootstrapping Enables Scalable Supervision of MLLM-as-a-Judge for Video Understanding
  42. ICLR 2026VideoMathQA: Benchmarking Mathematical Reasoning via Multimodal Understanding in Video
  43. ICLR 2026VideoNSA: Native Sparse Attention Scales Video Understanding
  44. ICLR 2026VideoReasonBench: Can MLLMs Perform Vision-Centric Complex Video Reasoning?
  45. ICLR 2026VMoBA: Mixture-of-Block Attention for Video Diffusion Models
  46. ICLR 2026VUDG: A Dataset for Video Understanding Domain Generalization
  47. ICLR 2026WavePolyp: Video Polyp Segmentation via Hierarchical Wavelet-Based Feature Aggregation and Inter-Frame Divergence Perception
  48. ICLR 2026When More is Less: Understanding Chain-of-Thought Length in LLMs

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