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 15 / 46 页

  1. NeurIPS 2026Learning Motion-Appearance Coupling Priors for Solving Video Inverse Problems
  2. NeurIPS 2026LifeStream: Token Life-Cycle Modeling for Training-Free Online Video Understanding
  3. NeurIPS 2026LogicDirector: Enforcing Temporal Composition in Text-to-Video Generation
  4. NeurIPS 2026LongSCOP: Semantically Consistent Long Video Outpainting
  5. NeurIPS 2026LookWhen? Fast Video Recognition by Learning When, Where, and What to Compute
  6. NeurIPS 2026MedHorizon: Towards Long-context Medical Video Understanding in the Wild
  7. NeurIPS 2026MEMEVO: A Memory-Evolved Video Agent for Long Video Understanding
  8. NeurIPS 2026MemoryFusion: Cross-Temporal Memory Learning for Multimodal Video Fusion
  9. NeurIPS 2026MixForensics: Blend Before You Encode for Generalizable AI-Generated Video Detection
  10. NeurIPS 2026MobileWan: Closing the Quality Gap for Mobile Video Diffusion
  11. NeurIPS 2026MonarchRT: Efficient Attention for Real-Time Video Generation
  12. NeurIPS 2026MSR-3D: Multi-Mode Semantic Representation for Open-Vocabulary 3D Scene Understanding
  13. NeurIPS 2026Muon Does Not Converge on Convex Lipschitz Functions
  14. NeurIPS 2026My Video Stays Mine: Temporally Consistent Universal Adversarial Perturbations against Video Customization
  15. NeurIPS 2026NIKA: Efficient Neural Video Representation via Structured Latent Diversity
  16. NeurIPS 2026Not All Layers Are Equal in Image-to-Video Transfer
  17. NeurIPS 2026OLA-Place: Cross-Modal Place Recognition without Global Descriptors
  18. NeurIPS 2026ONE-SHOT: Compositional Human-Environment Video Synthesis via Spatial-Decoupled Motion Injection and Hybrid Context Integration
  19. NeurIPS 2026OneCanvas: 3D Scene Understanding via Panoramic Reprojection
  20. NeurIPS 2026OpenCoF: Learning to Reason Through Video Generation
  21. NeurIPS 2026PanoWorld: Geometry-Consistent Panoramic Video World Modeling
  22. NeurIPS 2026ParaVT: Taming the Tool Prior Paradox for Parallel Tool Use in Agentic Video Reinforcement Learning
  23. NeurIPS 2026PathView-Bench: Can Multimodal Large Language Models Achieve Fine-grained Multiscale Understanding of Pathology Images?
  24. NeurIPS 2026PickMoment: Continuous-Time Single-Image-to-Video via Learning Deblurring and Blur-to-Video
  25. NeurIPS 2026PISCO: Precise Video Instance Insertion with Sparse Control
  26. NeurIPS 2026PIVOT: A Unified Agentic Framework for Streaming Long-Video Understanding
  27. NeurIPS 2026PoseBridge: Bridging the Skeletonization Gap for Zero-Shot Skeleton-Based Action Recognition
  28. NeurIPS 2026Principia: Relational Physics Tests for Video Models
  29. NeurIPS 2026PRISM: Rethinking Atmospheric Scattering Reconstruction as a Unified Understanding and Restoration Model for Real-world Dehazing
  30. NeurIPS 2026ProxyPose: 6-DoF Pose Tracking via Video-to-Video Translation
  31. NeurIPS 2026PuppetGait: Generalizing Gait Recognition via 3D Body-Aligned LVM Features
  32. NeurIPS 2026Q-ARVD: Quantizing Autoregressive Video Diffusion Models
  33. NeurIPS 2026Q-Focus: Let the Question Guide What to See in Long Videos
  34. NeurIPS 2026Rate-Constrained Edge Metadata for Sender–Receiver Generative Video Super-Resolution
  35. NeurIPS 2026RAVEN-Bench: A Paired EO-IR Video QA Benchmark for Aerial Multimodal Understanding
  36. NeurIPS 2026Reading Positional Coupling in Transformers with Diffusion Scores
  37. NeurIPS 2026Recreating Video Arenas via Automated Preference Scoring
  38. NeurIPS 2026Reject, Resample, Repeat: Understanding Parallel Reasoning in Language Model Inference
  39. NeurIPS 2026RelGS: Relation-Aware Gaussian Splatting for Open-Vocabulary 3D Scene Understanding
  40. NeurIPS 2026Rethinking Entropy Allocation in LLM-based ASR: Understanding the Dynamics between Speech Encoders and Large Language Models
  41. NeurIPS 2026Rethinking Long-Video Efficiency: A Joint Allocation Perspective on Frames, Pixels, and Front-End Latency
  42. NeurIPS 2026Rethinking the Readout: Unlocking Video Backbones for AI-Generated Video Detection
  43. NeurIPS 2026RigPAPR: Rig-Based Animation of Static Neural Point Clouds from a Single-View Video
  44. NeurIPS 2026SceneScaffold: Active Scene-State Construction for Unified 3D Scene Understanding
  45. NeurIPS 2026SCG-HF: Semantic Consistency Grouping for Hierarchical Fusion in Video Emotion Recognition
  46. NeurIPS 2026Seed-Your-Motion: Householder Orthogonal Noise for Motion-Controllable Video Diffusion Models
  47. NeurIPS 2026Seeing Through the Chain: Understanding and Mitigating Hallucinations in Multimodal Large Reasoning Models
  48. NeurIPS 2026SEEK-VAU: Towards Evidence-Faithful Video Anomaly Understanding via Agentic Search
  49. NeurIPS 2026Shifting the Gradient: Understanding How Defensive Training Methods Protect Language Model Integrity
  50. NeurIPS 2026SierpinskiCam: Camera-Controlled Video Retaking with Sierpinski Triangle Pattern Cues

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