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 341 篇，第 3 / 7 页

  1. CVPR 2026FlashVSR Towards Real-time Diffusion-Based Streaming Video Super Resolution
  2. CVPR 2026Flat-Pack Bench Evaluating Spatio-Temporal Understanding in Large Vision-Language Models through
  3. CVPR 2026FlexiVideo Variation-Aware Temporal Dynamics Modeling for Efficient Video Understanding
  4. CVPR 2026FlowDirector Training-Free Flow Steering for Precise Text-to-Video Editing
  5. CVPR 2026FlowMotion Training-Free Flow Guidance for Video Motion Transfer
  6. CVPR 2026FlowPortal Residual-Corrected Flow for Training-Free Video Relighting and Background Replacement
  7. CVPR 2026FluxMem Adaptive Hierarchical Memory for Streaming Video Understanding
  8. CVPR 2026fMRI-LM Towards a Universal Foundation Model for Language-Aligned fMRI Understanding
  9. CVPR 2026Focus Dont Prune Identifying Instruction-Relevant Regions for Information-Rich Image Understanding
  10. CVPR 2026Focus-to-Perceive Representation Learning A Cognition-Inspired Hierarchical Framework for Endoscopic Video
  11. CVPR 2026Forecasting 3D Scanpaths in Egocentric Video
  12. CVPR 2026FPS-Bench A Benchmark for High Frame-Rate Video Understanding
  13. CVPR 2026Frame2Freq Spectral Adapters for Fine-Grained Video Understanding
  14. CVPR 2026From Static to Dynamic Exploring Self-supervised Image-to-Video Representation Transfer Learning
  15. CVPR 2026From Where Things Are to What They Are For Benchmarking
  16. CVPR 2026GauMVC Generative Decoupled Gaussian Representation for Human-centric Multi-view Video Compression
  17. CVPR 2026Generalizable Video Quality Assessment via Weak-to-Strong Learning
  18. CVPR 2026Generative Neural Video Compression via Video Diffusion Prior
  19. CVPR 2026Generative Video Compression with One-Dimensional Latent Representation
  20. CVPR 2026Generative Video Motion Editing with 3D Point Tracks
  21. CVPR 2026GeoDiT A Diffusion-based Vision-Language Model for Geospatial Understanding
  22. CVPR 2026Geometry-Guided 3D Visual Token Pruning for Video-Language Models
  23. CVPR 2026GIFT Global Irreplaceability Frame Targeting for Efficient Video Understanding
  24. CVPR 2026Gloria Consistent Character Video Generation via Content Anchors
  25. CVPR 2026Goal-Driven Reward by Video Diffusion Models for Reinforcement Learning
  26. CVPR 2026GP-4DGS Probabilistic 4D Gaussian Splatting from Monocular Video via Variational
  27. CVPR 2026GUIDE A Benchmark for Understanding and Assisting Users in Open-Ended
  28. CVPR 2026Gyro-based Deep Video Deblurring
  29. CVPR 2026HandWorld Hand-Centric Unified Video Action Generation
  30. CVPR 2026HanDyVQA A Video QA Benchmark for Fine-Grained Hand-Object Interaction Dynamics
  31. CVPR 2026HERBench A Benchmark for Multi-Evidence Integration in Video Question Answering
  32. CVPR 2026HFR and HDR Video from Multi-Attenuated Spikes Using a Rapidly
  33. CVPR 2026HieraMamba Video Temporal Grounding via Hierarchical Anchor-Mamba Pooling
  34. CVPR 2026High Resolution Neural Video Coding with Bi-directional Confidence-Guided Reference Information
  35. CVPR 2026High-Fidelity Mobile Avatars with Pruned Local Blendshapes
  36. CVPR 2026HiSpatial Taming Hierarchical 3D Spatial Understanding in Vision-Language Models
  37. CVPR 2026How Much 3D Do Video Foundation Models Encode
  38. CVPR 2026HumanVBench Probing Human-Centric Video Understanding in MLLMs with Automatically Synthesized
  39. CVPR 2026Illumination-Consistent Human-Scene Reconstruction from Monocular Video
  40. CVPR 2026Im a Map Interpretable Motion-Attentive Maps Spatio-Temporally Localizing Concepts in
  41. CVPR 2026Image Guides Images Consistent Video Amodal Completion with Rectified In-Context
  42. CVPR 2026Imagine Before Concentration Diffusion-Guided Registers Enhance Partially Relevant Video Retrieval
  43. CVPR 2026Incentivizing Versatile Video Reasoning in MLLMs via Data-Efficient Reinforcement Learning
  44. CVPR 2026Inference-time Physics Alignment of Video Generative Models with Latent World
  45. CVPR 2026InstantViR Real-Time Video Inverse Problem Solver with Distilled Diffusion Prior
  46. CVPR 2026InstAP Instance-Aware Vision-Language Pre-Train for Spatial-Temporal Understanding
  47. CVPR 2026InternVideo-Next Towards World-Understanding Video Models
  48. CVPR 2026InterRVOS Interaction-Aware Referring Video Object Segmentation
  49. CVPR 2026Latent Diffusion Inversion Requires Understanding the Latent Space
  50. CVPR 2026LaVR Scene Latent Conditioned Generative Video Trajectory Re-Rendering using Large

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