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 17 / 46 页

  1. NeurIPS 2026Understanding the Convergence of Direct Training of SNNs with Surrogate Gradients
  2. NeurIPS 2026Understanding the Curse of Unrolling
  3. NeurIPS 2026Understanding the Effects of Hyper-Connections on Self-Attention Dynamics: A Bifurcation Analysis
  4. NeurIPS 2026Understanding the Interplay between Memorization and Learning in Large Language Models
  5. NeurIPS 2026Understanding the Out-of-Distribution Generalization of Chain-of-Thought Reasoning in LLMs
  6. NeurIPS 2026Uni-Synergy: Bridging Understanding and Generation for Personalized Reasoning
  7. NeurIPS 2026UniCon3R: Unified Contact-aware 4D Human-Scene Reconstruction from Monocular Video
  8. NeurIPS 2026Unified Generative-Predictive Modeling for 4D Scene Understanding
  9. NeurIPS 2026UTOPI: Efficient Egocentric Long-Video Understanding in AR via User-Guided Token Pre-Compression
  10. NeurIPS 2026V1-Inspired Dynamic Vision System: A Bio-Plausible Video Embedding Framework with Decoupled Shape–Color Pathways and Long-Range Spatiotemporal Perception
  11. NeurIPS 2026VI-Bench: Benchmarking Prompt Inversion from AIGC Videos
  12. NeurIPS 2026Video Stitching from Multiple Moving Cameras
  13. NeurIPS 2026Video-FLAIR: Not Whether to Reason, But How
  14. NeurIPS 2026VideoSailor: Navigating Video Deep Research via Trajectory-to-Policy Flywheel
  15. NeurIPS 2026VideoSleuth: A Narrative-Centric Agentic System with Video-Audio Native MLLM for Long-Form Video Understanding
  16. NeurIPS 2026VidHalluDoctor: Learning Video Differences to Mitigate Hallucinations in Vision-Language Models
  17. NeurIPS 2026ViDiC: Video Difference Captioning
  18. NeurIPS 2026ViMU: Benchmarking Video Metaphorical Understanding
  19. NeurIPS 2026Virtual Task Prompting for Multi-Task Scene Understanding
  20. NeurIPS 2026VISD: Enhancing Video Reasoning via Structured Self-Distillation
  21. NeurIPS 2026Vision Correlators: Correlation-Driven Visual Understanding with Hypergraphs
  22. NeurIPS 2026ViTeX-Bench: Benchmarking High-Fidelity Video Scene Text Editing
  23. NeurIPS 2026What Remains in Sight? Autoregressive Video Decoding as Representation-Guided Context Rewriting
  24. NeurIPS 2026What Should a Streaming Video Model Remember?
  25. NeurIPS 2026What the Geometry of Good Models Tells Us
  26. NeurIPS 2026When Medical VLMs Stop Understanding: MedTEC-Bench for Probing Semantic Specificity
  27. NeurIPS 2026When Safety Becomes An Outlier: Understanding the Retention of LLM Safety Behaviors
  28. NeurIPS 2026Where Do We (Not) Need Temporal Context in Low-Resource Video Task Adaptation?
  29. NeurIPS 2026Which Way Did It Move? Diagnosing and Overcoming Directional Motion Blindness in Video LLMs
  30. NeurIPS 2026Why Heavy-Tailed Weights Predict Model Quality
  31. NeurIPS 2026WorldPrism: 3D Consistency for Video World Models via Bidirectional Cross-Space Verification
  32. NeurIPS 2026WorldReasonBench: Human-Aligned Stress Testing of Video Generators as Future World-State Predictors
  33. CVPR 20254D-Fly: Fast 4D Reconstruction from a Single Monocular Video
  34. CVPR 20254DGC: Rate-Aware 4D Gaussian Compression for Efficient Streamable Free-Viewpoint Video
  35. CVPR 20254Real-Video: Learning Generalizable Photo-Realistic 4D Video Diffusion
  36. CVPR 2025A Simple yet Effective Layout Token in Large Language Models for Document Understanding
  37. CVPR 2025AC3D: Analyzing and Improving 3D Camera Control in Video Diffusion Transformers
  38. CVPR 2025Action Detail Matters: Refining Video Recognition with Local Action Queries
  39. CVPR 2025AdaCM^2: On Understanding Extremely Long-Term Video with Adaptive Cross-Modality Memory Reduction
  40. CVPR 2025Adapting Pre-trained 3D Models for Point Cloud Video Understanding via Cross-frame Spatio-temporal Perception
  41. CVPR 2025Adaptive Keyframe Sampling for Long Video Understanding
  42. CVPR 2025AG-VPReID: A Challenging Large-Scale Benchmark for Aerial-Ground Video-based Person Re-Identification
  43. CVPR 2025Align-A-Video: Deterministic Reward Tuning of Image Diffusion Models for Consistent Video Editing
  44. CVPR 2025AniGrad: Anisotropic Gradient-Adaptive Sampling for 3D Reconstruction From Monocular Video
  45. CVPR 2025Anomize: Better Open Vocabulary Video Anomaly Detection
  46. CVPR 2025AnyMoLe: Any Character Motion In-betweening Leveraging Video Diffusion Models
  47. CVPR 2025Apollo: An Exploration of Video Understanding in Large Multimodal Models
  48. CVPR 2025AR-Diffusion: Asynchronous Video Generation with Auto-Regressive Diffusion
  49. CVPR 2025ARKit LabelMaker: A New Scale for Indoor 3D Scene Understanding
  50. CVPR 2025Articulated Kinematics Distillation from Video Diffusion Models

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