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 611 篇，第 2 / 13 页

  1. NeurIPS 2026Diagnosing and Correcting Bias in MLLM for Long Video Understanding
  2. NeurIPS 2026Diffusion-DRF: Free, Rich, and Differentiable Reward for Video Diffusion Fine-Tuning
  3. NeurIPS 2026Disen-Forcing: Disentangling Semantic Anchoring from Motion for Autoregressive Video Diffusion
  4. NeurIPS 2026Disentangling Where and When: Factored Spatio-Temporal Explanations for Video Action Recognition
  5. NeurIPS 2026DopplerWild: A Doppler Dataset and Benchmark for Human Kinematic Understanding in the Wild
  6. NeurIPS 2026DriveStreamBench: Evaluating User-Conditioned Watch-and-Notify in Streaming Driving Video
  7. NeurIPS 2026Dynamic Video Generation: Shaping Video Generation Across Time and Space
  8. NeurIPS 2026DynaTokens: Teaching Dynamics to Camera-Controlled Video Models at Test Time
  9. NeurIPS 2026EgoBabyVLM: Benchmarking cross-modal learning from naturalistic egocentric video data
  10. NeurIPS 2026Elephant in the Fridge: Constant-Memory Frame Packing for Long Video Understanding
  11. NeurIPS 2026ELSA3D: Elastic Semantic Anchoring for Unified 3D Understanding and Generation
  12. NeurIPS 2026EmbodiedObject: All-in-One Object Understanding with SLAT
  13. NeurIPS 2026Emergent Semantic Role Understanding in Language Models
  14. NeurIPS 2026EndoSCOP-V: A Multi-Turn Video Understanding Evaluation Framework for Multimodal Models in Endoscopy Reporting and Clinical Reasoning
  15. NeurIPS 2026Epistemic Pairwise Maximin Share
  16. NeurIPS 2026Evaluating Multimodal Narrative Understanding of Popular Hollywood Films
  17. NeurIPS 2026EventLens: Event-Structure Reinforcement Learning for Video Understanding
  18. NeurIPS 2026Exposing and Mitigating Temporal Attack in Deepfake Video Detection
  19. NeurIPS 2026FacEDiT: Talking Head Video Editing via Facial Motion Infilling
  20. NeurIPS 2026FakeParts: a New Family of AI-Generated Video Forgeries
  21. NeurIPS 2026FashionChameleon: Towards Real-Time and Interactive Human-Garment Video Customization
  22. NeurIPS 2026FlashRelight: Portrait Video Relighting with Dynamic Lighting
  23. NeurIPS 2026FlowTrack: Controlling Edit-Signal Execution in Inversion-Free Flow Video Editing
  24. NeurIPS 2026FrameRouter: Frame Budget Routing for Long-Video Understanding on Video-MME-v2 and Beyond
  25. NeurIPS 2026FrameScout: Scouting Query-Relevant Frames for Long Video Understanding
  26. NeurIPS 2026FrameSelect: A Unified Library for Video Frame Selection and Evaluation
  27. NeurIPS 2026From Failure Taxonomy to Intervention: A Diagnostic Methodology for Industry-Scale AVLM in Video and Live-Streaming Platform Moderation
  28. NeurIPS 2026From Finding to Linking: Benchmarking and Advancing Cross-Long-Video Reasoning for Multimodal LLMs
  29. NeurIPS 2026From Label Priors to Task Evidence: Long-Video Frame Selection via Bayesian GRPO
  30. NeurIPS 2026fxBench: Evaluating and Understanding Formula Suggestions in Spreadsheets
  31. NeurIPS 2026Gaussian Splatting-based Volumetric Video Compression with Sparse 4D Anchors
  32. NeurIPS 2026Generation-for-Understanding with Structured Action Scripts for Embodied Multimodal Learning
  33. NeurIPS 2026GeoG2U-Bench: When Does Generation Help Understanding in Ultra-High-Resolution Remote Sensing?
  34. NeurIPS 2026Going Down Memory Lane: Scaling Tokens for Video Stream Understanding with Dynamic KV-Cache Memory
  35. NeurIPS 2026GridProbe: Posterior-Probing for Adaptive Test-Time Compute in Long-Video VLMs
  36. NeurIPS 2026Guided Data Generation for Understanding Model Behavior
  37. NeurIPS 2026Hierarchical Adaptive Frame Sampling For Video Understanding
  38. NeurIPS 2026HIMMEL: Hierarchical Interleaved Multi-stream Motion Encoding for Long Video Understanding
  39. NeurIPS 2026Holo4D: Holistic 4D Reconstruction as Geometric Control for Video Diffusion
  40. NeurIPS 2026How to Train a Surgeon? Benchmarking Generalist Agents in Surgical Scene Understanding
  41. NeurIPS 2026HyrCap: Hybrid Rank-Calibration of Action Proposals for Temporal Event Understanding
  42. NeurIPS 2026InfiniteVL: A Systematic Approach to Highly-Efficient, Ultra-Long Multimodal Understanding
  43. NeurIPS 2026InstructVVT: Instruction-Driven Video Virtual Try-On without Auxiliary Spatial Priors
  44. NeurIPS 2026Iris: Empowering Video MLLMs with High-Frequency Pose Priors via Spatiotemporal Binding
  45. NeurIPS 2026kVNN: Learnable Volterra Network Kernels
  46. NeurIPS 2026Latent Motion Alignment for Video Diffusion
  47. NeurIPS 2026Latent Video Prediction for World Modeling: An Evaluation Uncovering Intriguing Favorable Evidence
  48. NeurIPS 2026Learning Motion-Appearance Coupling Priors for Solving Video Inverse Problems
  49. NeurIPS 2026LifeStream: Token Life-Cycle Modeling for Training-Free Online Video Understanding
  50. NeurIPS 2026LogicDirector: Enforcing Temporal Composition in Text-to-Video Generation

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