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 334 篇，第 2 / 7 页

  1. ICLR 2026IWR-Bench: Can LVLMs reconstruct interactive webpage from a user interaction video?
  2. ICLR 2026Jailbreaking on Text-to-Video Models via Scene Splitting Strategy
  3. ICLR 2026Let's Split Up: Zero-Shot Classifier Edits for Fine-Grained Video Understanding
  4. ICLR 2026LH-DECEPTION: Simulating and Understanding LLM Deceptive Behaviors in Long-Horizon Interactions
  5. ICLR 2026LightCtrl: Training-free Controllable Video Relighting
  6. ICLR 2026Linear Mechanisms for Spatiotemporal Reasoning in Vision Language Models
  7. ICLR 2026LLaVAction: evaluating and training multi-modal large language models for action understanding
  8. ICLR 2026Lost in Tokenization: Context as the Key to Unlocking Biomolecular Understanding in Scientific LLMs
  9. ICLR 2026Map the Flow: Revealing Hidden Pathways of Information in VideoLLMs
  10. ICLR 2026MARC: Memory-Augmented RL Token Compression for Efficient Video Understanding
  11. ICLR 2026Measure Twice, Cut Once: A Semantic-Oriented Approach to Video Temporal Localization with Video LLMs
  12. ICLR 2026Memento: Toward an All-Day Proactive Assistant for Ultra-Long Streaming Video
  13. ICLR 2026Midway Network: Learning Representations for Recognition and Motion from Latent Dynamics
  14. ICLR 2026MMDuet2: Enhancing Proactive Interaction of Video MLLMs with Multi-Turn Reinforcement Learning
  15. ICLR 2026MoAlign: Motion-Centric Representation Alignment for Video Diffusion Models
  16. ICLR 2026Model Already Knows the Best Noise: Bayesian Active Noise Selection via Attention in Video Diffusion Model
  17. ICLR 2026Monocular Normal Estimation via Shading Sequence Estimation
  18. ICLR 2026MotionSight: Boosting Fine-Grained Motion Understanding in Multimodal LLMs
  19. ICLR 2026NeRV-Diffusion: Diffuse Implicit Neural Representation for Video Synthesis
  20. ICLR 2026Neuron-Level Analysis of Cultural Understanding in Large Language Models
  21. ICLR 2026OmniSTVG: Toward Spatio-Temporal Omni-Object Video Grounding
  22. ICLR 2026OmniVinci: Enhancing Architecture and Data for Omni-Modal Understanding LLM
  23. ICLR 2026On the Limits of Sparse Autoencoders: A Theoretical Framework and Reweighted Remedy
  24. ICLR 2026On the Spectral Differences Between NTK and CNTK and Their Implications for Point Cloud Recognition
  25. ICLR 2026Only Brains Align with Brains: Cross-Region Patterns Expose Limits of Normative Models
  26. ICLR 2026Orak: A Foundational Benchmark for Training and Evaluating LLM Agents on Diverse Video Games
  27. ICLR 2026ParallelBench: Understanding the Trade-offs of Parallel Decoding in Diffusion LLMs
  28. ICLR 2026Plug, Play, and Fortify: A Low-Cost Module for Robust Multimodal Image Understanding Models
  29. ICLR 2026Post-Training Quantization for Video Matting
  30. ICLR 2026PPLLaVA: Varied Video Sequence Understanding With Prompt Guidance
  31. ICLR 2026Privacy Beyond Pixels: Latent Anonymization for Privacy-Preserving Video Understanding
  32. ICLR 2026Procedural Mistake Detection via Action Effect Modeling
  33. ICLR 2026Progressive Online Video Understanding with Evidence-Aligned Timing and Transparent Decisions
  34. ICLR 2026Prune-then-Quantize or Quantize-then-Prune? Understanding the Impact of Compression Order in Joint Model Compression
  35. ICLR 2026QueryStream: Advancing Streaming Video Understanding with Query-Aware Pruning and Proactive Response
  36. ICLR 2026Reading Images Like Texts: Sequential Image Understanding in Vision-Language Models
  37. ICLR 2026RelayFormer: A Unified Local-Global Attention Framework for Scalable Image and Video Manipulation Localization
  38. ICLR 2026Rethinking JEPA: Compute‑Efficient Video Self-Supervised Learning with Frozen Teachers
  39. ICLR 2026RIVER: Real-time Video Interaction Benchmark
  40. ICLR 2026ScaleLong: A Multi-Timescale Benchmark for Long Video Understanding
  41. ICLR 2026Seeing What’s Not There: Negation Understanding Needs More Than Training
  42. ICLR 2026SPIKE-RL: Video-LLMs meet Bayesian Surprise
  43. ICLR 2026ST-SimDiff: Balancing Spatiotemporal Similarity and Difference for Efficient Video Understanding with MLLMs
  44. ICLR 2026StochasTok: Improving Fine-Grained Subword Understanding in LLMs
  45. ICLR 2026StPR: Spatiotemporal Preservation and Routing for Exemplar-Free Video Class-Incremental Learning
  46. ICLR 2026Streaming Drag-Oriented Interactive Video Manipulation: Drag Anything, Anytime!
  47. ICLR 2026StreamingVLM: Real-Time Understanding for Infinite Video Streams
  48. ICLR 2026SURGE: Surprise-Guided Token Reduction for Efficient Video Understanding with VLMs
  49. ICLR 2026The Human Brain as a Dynamic Mixture of Expert Models in Video Understanding
  50. ICLR 2026Threading Keyframe with Narratives: MLLMs as Strong Long Video Comprehenders

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