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 38 / 46 页

  1. NeurIPS 2024Expressive Gaussian Human Avatars from Monocular RGB Video
  2. NeurIPS 2024Extending Video Masked Autoencoders to 128 frames
  3. NeurIPS 2024Fast and Memory-Efficient Video Diffusion Using Streamlined Inference
  4. NeurIPS 2024FineCLIP: Self-distilled Region-based CLIP for Better Fine-grained Understanding
  5. NeurIPS 2024Flow Snapshot Neurons in Action: Deep Neural Networks Generalize to Biological Motion Perception
  6. NeurIPS 2024Fourier Amplitude and Correlation Loss: Beyond Using L2 Loss for Skillful Precipitation Nowcasting
  7. NeurIPS 2024Frozen-DETR: Enhancing DETR with Image Understanding from Frozen Foundation Models
  8. NeurIPS 2024FUSU: A Multi-temporal-source Land Use Change Segmentation Dataset for Fine-grained Urban Semantic Understanding
  9. NeurIPS 2024Generalizable Implicit Motion Modeling for Video Frame Interpolation
  10. NeurIPS 2024Generalized Tensor Decomposition for Understanding Multi-Output Regression under Combinatorial Shifts
  11. NeurIPS 2024GenRec: Unifying Video Generation and Recognition with Diffusion Models
  12. NeurIPS 2024Harmony4D: A Video Dataset for In-The-Wild Close Human Interactions
  13. NeurIPS 2024HAWK: Learning to Understand Open-World Video Anomalies
  14. NeurIPS 2024HENASY: Learning to Assemble Scene-Entities for Interpretable Egocentric Video-Language Model
  15. NeurIPS 2024HourVideo: 1-Hour Video-Language Understanding
  16. NeurIPS 2024Human-level shape inferences: A benchmark for evaluating the 3D understanding of vision models
  17. NeurIPS 2024Identifying and Solving Conditional Image Leakage in Image-to-Video Diffusion Model
  18. NeurIPS 2024II-Bench: An Image Implication Understanding Benchmark for Multimodal Large Language Models
  19. NeurIPS 2024IKEA Manuals at Work: 4D Grounding of Assembly Instructions on Internet Videos
  20. NeurIPS 2024Intruding with Words: Towards Understanding Graph Injection Attacks at the Text Level
  21. NeurIPS 2024Is Behavior Cloning All You Need? Understanding Horizon in Imitation Learning
  22. NeurIPS 2024JourneyBench: A Challenging One-Stop Vision-Language Understanding Benchmark of Generated Images
  23. NeurIPS 2024LAVIB: A Large-scale Video Interpolation Benchmark
  24. NeurIPS 2024Learnability Matters: Active Learning for Video Captioning
  25. NeurIPS 2024Learning an Actionable Discrete Diffusion Policy via Large-Scale Actionless Video Pre-Training
  26. NeurIPS 2024Learning Truncated Causal History Model for Video Restoration
  27. NeurIPS 2024LongVideoBench: A Benchmark for Long-context Interleaved Video-Language Understanding
  28. NeurIPS 2024MambaSCI: Efficient Mamba-UNet for Quad-Bayer Patterned Video Snapshot Compressive Imaging
  29. NeurIPS 2024MambaTree: Tree Topology is All You Need in State Space Model
  30. NeurIPS 2024Micro-Bench: A Microscopy Benchmark for Vision-Language Understanding
  31. NeurIPS 2024MMBench-Video: A Long-Form Multi-Shot Benchmark for Holistic Video Understanding
  32. NeurIPS 2024MoTE: Reconciling Generalization with Specialization for Visual-Language to Video Knowledge Transfer
  33. NeurIPS 2024Motion Graph Unleashed: A Novel Approach to Video Prediction
  34. NeurIPS 2024Moving Off-the-Grid: Scene-Grounded Video Representations
  35. NeurIPS 2024Multiview Scene Graph
  36. NeurIPS 2024NeuroClips: Towards High-fidelity and Smooth fMRI-to-Video Reconstruction
  37. NeurIPS 2024NVRC: Neural Video Representation Compression
  38. NeurIPS 2024Octopus: A Multi-modal LLM with Parallel Recognition and Sequential Understanding
  39. NeurIPS 2024OMG-LLaVA: Bridging Image-level, Object-level, Pixel-level Reasoning and Understanding
  40. NeurIPS 2024On Learning Multi-Modal Forgery Representation for Diffusion Generated Video Detection
  41. NeurIPS 2024OnlineTAS: An Online Baseline for Temporal Action Segmentation
  42. NeurIPS 2024OW-VISCapTor: Abstractors for Open-World Video Instance Segmentation and Captioning
  43. NeurIPS 2024Precipitation Downscaling with Spatiotemporal Video Diffusion
  44. NeurIPS 2024Procedure-Aware Surgical Video-language Pretraining with Hierarchical Knowledge Augmentation
  45. NeurIPS 2024ReVideo: Remake a Video with Motion and Content Control
  46. NeurIPS 2024Revisiting, Benchmarking and Understanding Unsupervised Graph Domain Adaptation
  47. NeurIPS 2024ReXTime: A Benchmark Suite for Reasoning-Across-Time in Videos
  48. NeurIPS 2024SeeClear: Semantic Distillation Enhances Pixel Condensation for Video Super-Resolution
  49. NeurIPS 2024ShareGPT4Video: Improving Video Understanding and Generation with Better Captions
  50. NeurIPS 2024Sharpness-Aware Minimization Activates the Interactive Teaching's Understanding and Optimization

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