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 611 篇，第 4 / 13 页

  1. NeurIPS 2026Sparkle: Realizing Lively Instruction-Guided Video Background Replacement via Decoupled Guidance
  2. NeurIPS 2026Sparse Video Generation Propels Real-World Beyond-the-View Vision-Language Navigation
  3. NeurIPS 2026Spectral Progressive Diffusion for Efficient Image and Video Generation
  4. NeurIPS 2026SphereVAD: Training-Free Video Anomaly Detection via Geodesic Inference on the Unit Hypersphere
  5. NeurIPS 2026StakeBench: Evaluating Language Understanding Grounded in Market Commitment
  6. NeurIPS 2026StreamGaze: Gaze-Guided Temporal Reasoning and Proactive Understanding in Streaming Videos
  7. NeurIPS 2026Streaming Interventions: Can Video LLMs Correct Mistakes as They Occur?
  8. NeurIPS 2026StreamOV: Streaming Omni-Video Understanding via Evidence-Guided Memory and Response Triggering
  9. NeurIPS 2026Structure Over Scale: Learning Visual Reasoning from Pedagogical Video
  10. NeurIPS 2026Subject-Relative Micro-Motion and Sleep Dynamics for Near-Infrared Video Sleep Staging
  11. NeurIPS 2026SUGAR: A Scalable Human-Video-Driven Generalizable Humanoid Loco-Manipulation Learning Framework
  12. NeurIPS 2026SynthForensics: Benchmarking and Evaluating People-Centric Synthetic Video Deepfakes
  13. NeurIPS 2026TACO: Towards Task-Consistent Open-Vocabulary Adaptation in Video Recognition
  14. NeurIPS 2026TailCon: Mitigating Tail Signal Erosion through Memory Consolidation for Long-Tailed Recognition
  15. NeurIPS 2026TeMPO: Frame-Causal Token Compression for Efficient Video Large Language Model
  16. NeurIPS 2026Temporal Slice Learning for AI-Generated Video Detection with 400× Fewer FLOPs
  17. NeurIPS 2026The Invisible Hand of Physics: When Video Diffusion Models Know More Than They Show
  18. NeurIPS 2026The VLM as Sensor: Bayesian Active Search for Long Video Understanding
  19. NeurIPS 2026Toward Interactive Understanding of Code APIs
  20. NeurIPS 2026Toward Multimodal Sheet Music Recognition and Understanding
  21. NeurIPS 2026Towards Generalizable Partially Relevant Video Retrieval
  22. NeurIPS 2026Towards Understanding and Measuring Cognitive Atrophy in LLM Behaviour
  23. NeurIPS 2026Towards Understanding Momentum Acceleration in River-Valley Loss Landscape
  24. NeurIPS 2026Towards Understanding Self-Pretraining for Sequence Classification
  25. NeurIPS 2026Towards Understanding the Power and Limits of the Muon Optimizer: A River-Valley Perspective
  26. NeurIPS 2026TRACE: Trajectory-Aware Conceps for Explainable Video Understanding
  27. NeurIPS 2026Track4D: Representing Dense 3D Tracking for Video Diffusion Models
  28. NeurIPS 2026TrackCraft3R: Repurposing Video Diffusion Transformers for Dense 3D Tracking
  29. NeurIPS 2026TrAction: Action Recognition with Sparse Trajectories
  30. NeurIPS 2026Transformers Converge to Invariant Algorithmic Cores
  31. NeurIPS 2026Transforming Image Editors into Video Editors
  32. NeurIPS 2026Tri-Prompting: Controllable Video Generation with Scene, Subject, and Motion Prompts
  33. NeurIPS 2026TTVidT: Decoupling the Temporal Axis for Efficient Motion-Centric Video Pretraining
  34. NeurIPS 2026U-Bench: A Comprehensive Understanding of U-Net through 100-Variant Benchmarking
  35. NeurIPS 2026Understanding and Defending VLM Jailbreaks via Jailbreak-Related Representation Shift
  36. NeurIPS 2026Understanding and Mitigating Under-Confidence in GNNs from the Final Layer
  37. NeurIPS 2026Understanding axial attention in TSFMs through single location regression
  38. NeurIPS 2026Understanding Circulant Permutation to Extend the CMinHash Estimator
  39. NeurIPS 2026Understanding diffusion models requires rethinking (again) generalization
  40. NeurIPS 2026Understanding Double Descent through Universal Compression
  41. NeurIPS 2026Understanding Generalization Requires Universal Induction
  42. NeurIPS 2026Understanding Layer Patching in Model Size Interpolation
  43. NeurIPS 2026Understanding Multi-View Transformers
  44. NeurIPS 2026Understanding Randomization in Greedy Model Search
  45. NeurIPS 2026Understanding Sample Efficiency in Predictive Coding
  46. NeurIPS 2026Understanding the Challenges in Iterative Generative Optimization with LLMs
  47. NeurIPS 2026Understanding the Co-evolutionary Solution Exchange of the MOEA/D: Minimal Communication Gives Maximal Speed-Ups
  48. NeurIPS 2026Understanding the Convergence of Direct Training of SNNs with Surrogate Gradients
  49. NeurIPS 2026Understanding the Curse of Unrolling
  50. NeurIPS 2026Understanding the Effects of Hyper-Connections on Self-Attention Dynamics: A Bifurcation Analysis

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