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 1 / 46 页

  1. CVPR 20263D sans 3D Scans Scalable Pre-training from Video-Generated Point Clouds
  2. CVPR 20263D-Aware Implicit Motion Control for View-Adaptive Human Video Generation
  3. CVPR 20264D-RGPT Toward Region-level 4D Understanding via Perceptual Distillation
  4. CVPR 2026A Bit is All You Need Efficient Video Capture via
  5. CVPR 2026A Causal Marriage between VLM and IRM from Understanding to
  6. CVPR 2026Accelerating Autoregressive Video Diffusion via History-Guided Cache and Residual Correction
  7. CVPR 2026Accelerating Diffusion-based Video Editing via Heterogeneous Caching Beyond Full Computing
  8. CVPR 2026Accelerating Streaming Video Large Language Models via Hierarchical Token Compression
  9. CVPR 2026AdaCluster Adaptive Query-Key Clustering for Sparse Attention in Video Generation
  10. CVPR 2026Adapting Lightweight Image-based Counting Models for Video Crowd Counting
  11. CVPR 2026Adaptive Video Distillation Mitigating Oversaturation and Temporal Collapse in Few-Step
  12. CVPR 2026AdapTok Learning Adaptive and Temporally Causal Video Tokenization in a
  13. CVPR 2026AdaSpark Adaptive Sparsity for Efficient Long-Video Understanding
  14. CVPR 2026AE2VID Event-based Video Reconstruction via Aperture Modulation
  15. CVPR 2026Affordance-First Decomposition for Continual Learning in Video-Language Understanding
  16. CVPR 2026Agentic Video Summarization via Self-Reflecting Multimodal Understanding
  17. CVPR 2026Alert-CLIP Abnormality-aware Latent-Enhanced Representation Tuning of CLIP for Video Anomaly
  18. CVPR 2026An Empirical Study on How Video-LLMs Answer Video Questions
  19. CVPR 2026AniMimic Imitating 3D Animation from Video Priors
  20. CVPR 2026Attend Before Attention Efficient and Scalable Video Understanding via Autoregressive
  21. CVPR 2026Attention Surgery An Efficient Recipe to Linearize Your Video Diffusion
  22. CVPR 2026AutoCut End-to-end advertisement video editing based on multimodal discretization and
  23. CVPR 2026AVATAR Reinforcement Learning to See Hear and Reason Over Video
  24. CVPR 2026Back to the Feature Explaining Video Classifiers with Video Counterfactual
  25. CVPR 2026Beyond Caption-Based Queries in Video Moment Retrieval
  26. CVPR 2026Beyond Global Similarity Multi-Conditional Retrieval for Fine-Grained Cross-Modal Understanding
  27. CVPR 2026Beyond Single Images A Comprehensive Benchmark for Album-Level Vision-Language Understanding
  28. CVPR 2026Beyond Single-View Sufficiency CVBench for Cross-View Human Understanding
  29. CVPR 2026Blink Dynamic Visual Token Resolution for Enhanced Multimodal Understanding
  30. CVPR 2026Bootstrapping Video Semantic Segmentation Model via Distillation-assisted Test-Time Adaptation
  31. CVPR 2026Breaking Multimodal LLM Safety via Video-Driven Prompting
  32. CVPR 2026Bridging Facial Understanding and Animation via Language Models
  33. CVPR 2026Building a Precise Video Language with Human-AI Oversight
  34. CVPR 2026BulletTime Decoupled Control of Time and Camera Pose for Video
  35. CVPR 2026CamDirector Towards Long-Term Coherent Video Trajectory Editing
  36. CVPR 2026CaST-Bench Benchmarking Causal Chain-Grounded Spatio-Temporal Reasoning for Video Question Answering
  37. CVPR 2026Causality in Video Diffusers is Separable from Denoising
  38. CVPR 2026Chain-of-Frames Advancing Video Understanding in Multimodal LLMs via Frame-Aware Reasoning
  39. CVPR 2026CineScene Implicit 3D as Effective Scene Representation for Cinematic Video
  40. CVPR 2026Clinically-Grounded Counterfactual Reasoning for Medical Video Diagnosis
  41. CVPR 2026Cluster-Wise Spatio-Temporal Masking for Efficient Video-Language Pretraining
  42. CVPR 2026Complet4R Geometric Complete 4D Reconstruction
  43. CVPR 2026Compressed-Domain-Aware Online Video Super-Resolution
  44. CVPR 2026Condensed Test-Time Adaptation of VLMs for Action Recognition
  45. CVPR 2026Consistent Instance Field for Dynamic Scene Understanding
  46. CVPR 2026Content-Adaptive Hierarchical Hyperprior for Neural Video Coding
  47. CVPR 2026Content-Aware Dynamic Patchification for Efficient Video Diffusion
  48. CVPR 2026Cross-Subject EEG-to-Video Reconstruction and Beyond
  49. CVPR 2026Curvature-Aware Captioning Leveraging Geodesic Attention for 3D Scene Understanding
  50. CVPR 2026CURVE A Benchmark for Cultural and Multilingual Long Video Reasoning

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