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 679 篇，第 7 / 14 页

  1. ICLR 2025A Geometric Framework for Understanding Memorization in Generative Models
  2. ICLR 2025Answer, Assemble, Ace: Understanding How LMs Answer Multiple Choice Questions
  3. ICLR 2025AuroraCap: Efficient, Performant Video Detailed Captioning and a New Benchmark
  4. ICLR 2025Autocorrelation Matters: Understanding the Role of Initialization Schemes for State Space Models
  5. ICLR 2025CameraCtrl: Enabling Camera Control for Video Diffusion Models
  6. ICLR 2025Can Video LLMs Refuse to Answer? Alignment for Answerability in Video Large Language Models
  7. ICLR 2025CG-Bench: Clue-grounded Question Answering Benchmark for Long Video Understanding
  8. ICLR 2025Compositional 4D Dynamic Scenes Understanding with Physics Priors for Video Question Answering
  9. ICLR 2025Contextual Self-paced Learning for Weakly Supervised Spatio-Temporal Video Grounding
  10. ICLR 2025DeepRTL: Bridging Verilog Understanding and Generation with a Unified Representation Model
  11. ICLR 2025Dense Video Object Captioning from Disjoint Supervision
  12. ICLR 2025Do Egocentric Video-Language Models Truly Understand Hand-Object Interactions?
  13. ICLR 2025Duoduo CLIP: Efficient 3D Understanding with Multi-View Images
  14. ICLR 2025Ferret-UI 2: Mastering Universal User Interface Understanding Across Platforms
  15. ICLR 2025Frame-Voyager: Learning to Query Frames for Video Large Language Models
  16. ICLR 2025FreqPrior: Improving Video Diffusion Models with Frequency Filtering Gaussian Noise
  17. ICLR 2025Generalized Video Moment Retrieval
  18. ICLR 2025GenEx: Generating an Explorable World
  19. ICLR 2025Going Beyond Static: Understanding Shifts with Time-Series Attribution
  20. ICLR 2025Grounding Video Models to Actions through Goal Conditioned Exploration
  21. ICLR 2025GUI-World: A Video Benchmark and Dataset for Multimodal GUI-oriented Understanding
  22. ICLR 2025Harnessing Webpage UIs for Text-Rich Visual Understanding
  23. ICLR 2025I2VControl-Camera: Precise Video Camera Control with Adjustable Motion Strength
  24. ICLR 2025IDA-VLM: Towards Movie Understanding via ID-Aware Large Vision-Language Model
  25. ICLR 2025INCLUDE: Evaluating Multilingual Language Understanding with Regional Knowledge
  26. ICLR 2025Is Your Video Language Model a Reliable Judge?
  27. ICLR 2025Kronecker Mask and Interpretive Prompts are Language-Action Video Learners
  28. ICLR 2025Language-Image Models with 3D Understanding
  29. ICLR 2025LASER: A Neuro-Symbolic Framework for Learning Spatio-Temporal Scene Graphs with Weak Supervision
  30. ICLR 2025Learning Fine-Grained Representations through Textual Token Disentanglement in Composed Video Retrieval
  31. ICLR 2025Learning Video-Conditioned Policy on Unlabelled Data with Joint Embedding Predictive Transformer
  32. ICLR 2025Let Your Features Tell The Differences: Understanding Graph Convolution By Feature Splitting
  33. ICLR 2025Linear Mode Connectivity in Differentiable Tree Ensembles
  34. ICLR 2025LongVILA: Scaling Long-Context Visual Language Models for Long Videos
  35. ICLR 2025Looking Backward: Streaming Video-to-Video Translation with Feature Banks
  36. ICLR 2025MMEgo: Towards Building Egocentric Multimodal LLMs for Video QA
  37. ICLR 2025MMIU: Multimodal Multi-image Understanding for Evaluating Large Vision-Language Models
  38. ICLR 2025MMWorld: Towards Multi-discipline Multi-faceted World Model Evaluation in Videos
  39. ICLR 2025Modeling Fine-Grained Hand-Object Dynamics for Egocentric Video Representation Learning
  40. ICLR 2025mPLUG-Owl3: Towards Long Image-Sequence Understanding in Multi-Modal Large Language Models
  41. ICLR 2025MuirBench: A Comprehensive Benchmark for Robust Multi-image Understanding
  42. ICLR 2025Needle In A Video Haystack: A Scalable Synthetic Evaluator for Video MLLMs
  43. ICLR 2025NVS-Solver: Video Diffusion Model as Zero-Shot Novel View Synthesizer
  44. ICLR 2025One Hundred Neural Networks and Brains Watching Videos: Lessons from Alignment
  45. ICLR 2025Oryx MLLM: On-Demand Spatial-Temporal Understanding at Arbitrary Resolution
  46. ICLR 2025PooDLe🐩: Pooled and dense self-supervised learning from naturalistic videos
  47. ICLR 2025Proximal Mapping Loss: Understanding Loss Functions in Crowd Counting & Localization
  48. ICLR 2025PvNeXt: Rethinking Network Design and Temporal Motion for Point Cloud Video Recognition
  49. ICLR 2025Real-Time Video Generation with Pyramid Attention Broadcast
  50. ICLR 2025SafeWatch: An Efficient Safety-Policy Following Video Guardrail Model with Transparent Explanations

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