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 279 篇，第 3 / 6 页

  1. ICML 2026V-LynX: Token Interface Alignment for Video+X LLMs
  2. ICML 2026Veda: Scalable Video Diffusion via Distilled Sparse Attention
  3. ICML 2026Video-Based Optimal Transport for Feedback-Efficient Offline Preference-Based Reinforcement Learning
  4. ICML 2026Video-BCI: Bayesian Cognitive Integration of Self-Prior Hypotheses for Video Understanding
  5. ICML 2026Video-in-the-Loop: Span-Grounded Long Video QA with Interleaved Reasoning
  6. ICML 2026Video-MTR: Reinforced Multi-Turn Reasoning for Long Video Understanding
  7. ICML 2026VideoFlexTok: Flexible-Length Coarse-to-Fine Video Tokenization
  8. ICML 2026VideoKR: Towards Knowledge- and Reasoning-Intensive Video Understanding
  9. ICML 2026VideoLoom: A Video Large Language Model for Joint Spatial-Temporal Understanding
  10. ICML 2026VideoMAETok: Boosting Video Diffusion Models via Masked Autoencoders as Tokenizers
  11. ICML 2026VideoSEAL: Mitigating Evidence Misalignment in Agentic Long Video Understanding by Decoupling Answer Authority
  12. ICML 2026VideoTemp-o3: Harmonizing Temporal Grounding and Video Understanding in Agentic Thinking-with-Videos
  13. ICML 2026VidLaDA: Bidirectional Diffusion Large Language Models for Efficient Video Understanding
  14. ICML 2026Words Towards Explainability: Caption Label-Free Learning via Dual Loop Agentic Time Series Captioning
  15. ICML 2025$\infty$-Video: A Training-Free Approach to Long Video Understanding via Continuous-Time Memory Consolidation
  16. ICML 2025$\mathcal{V}ista\mathcal{DPO}$: Video Hierarchical Spatial-Temporal Direct Preference Optimization for Large Video Models
  17. ICML 2025A Closer Look at Transformers for Time Series Forecasting: Understanding Why They Work and Where They Struggle
  18. ICML 2025Action Dubber: Timing Audible Actions via Inflectional Flow
  19. ICML 2025AffectGPT: A New Dataset, Model, and Benchmark for Emotion Understanding with Multimodal Large Language Models
  20. ICML 2025AsymRnR: Video Diffusion Transformers Acceleration with Asymmetric Reduction and Restoration
  21. ICML 2025BDC-CLIP: Brownian Distance Covariance for Adapting CLIP to Action Recognition
  22. ICML 2025Calibrating Video Watch-time Predictions with Credible Prototype Alignment
  23. ICML 2025Compositional Condition Question Answering in Tabular Understanding
  24. ICML 2025Compositional Scene Understanding through Inverse Generative Modeling
  25. ICML 2025Explanatory Instructions: Towards Unified Vision Tasks Understanding and Zero-shot Generalization
  26. ICML 2025HaploVL: A Single-Transformer Baseline for Multi-Modal Understanding
  27. ICML 2025Imitation Learning from a Single Temporally Misaligned Video
  28. ICML 2025Improving LLM Video Understanding with 16 Frames Per Second
  29. ICML 2025Learning Event Completeness for Weakly Supervised Video Anomaly Detection
  30. ICML 2025LongVU: Spatiotemporal Adaptive Compression for Long Video-Language Understanding
  31. ICML 2025Massive Values in Self-Attention Modules are the Key to Contextual Knowledge Understanding
  32. ICML 2025MedXpertQA: Benchmarking Expert-Level Medical Reasoning and Understanding
  33. ICML 2025MODA: MOdular Duplex Attention for Multimodal Perception, Cognition, and Emotion Understanding
  34. ICML 2025Modularized Self-Reflected Video Reasoner for Multimodal LLM with Application to Video Question Answering
  35. ICML 2025MoMa: Modulating Mamba for Adapting Image Foundation Models to Video Recognition
  36. ICML 2025On Understanding Attention-Based In-Context Learning for Categorical Data
  37. ICML 2025PlaySlot: Learning Inverse Latent Dynamics for Controllable Object-Centric Video Prediction and Planning
  38. ICML 2025Position: Deep Learning is Not So Mysterious or Different
  39. ICML 2025Position: We Can’t Understand AI Using our Existing Vocabulary
  40. ICML 2025Potemkin Understanding in Large Language Models
  41. ICML 2025RIFLEx: A Free Lunch for Length Extrapolation in Video Diffusion Transformers
  42. ICML 2025Scaling Video-Language Models to 10K Frames via Hierarchical Differential Distillation
  43. ICML 2025SpargeAttention: Accurate and Training-free Sparse Attention Accelerating Any Model Inference
  44. ICML 2025Sparse Video-Gen: Accelerating Video Diffusion Transformers with Spatial-Temporal Sparsity
  45. ICML 2025SpikeVideoFormer: An Efficient Spike-Driven Video Transformer with Hamming Attention and $\mathcal{O}(T)$ Complexity
  46. ICML 2025Time to Spike? Understanding the Representational Power of Spiking Neural Networks in Discrete Time
  47. ICML 2025Towards Theoretical Understanding of Sequential Decision Making with Preference Feedback
  48. ICML 2025Towards Understanding Catastrophic Forgetting in Two-layer Convolutional Neural Networks
  49. ICML 2025Towards Understanding Gradient Dynamics of the Sliced-Wasserstein Distance via Critical Point Analysis
  50. ICML 2025Towards Understanding Parametric Generalized Category Discovery on Graphs

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