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 9 / 14 页

  1. ICML 2025Calibrating Video Watch-time Predictions with Credible Prototype Alignment
  2. ICML 2025Compositional Condition Question Answering in Tabular Understanding
  3. ICML 2025Compositional Scene Understanding through Inverse Generative Modeling
  4. ICML 2025Explanatory Instructions: Towards Unified Vision Tasks Understanding and Zero-shot Generalization
  5. ICML 2025HaploVL: A Single-Transformer Baseline for Multi-Modal Understanding
  6. ICML 2025Imitation Learning from a Single Temporally Misaligned Video
  7. ICML 2025Improving LLM Video Understanding with 16 Frames Per Second
  8. ICML 2025Learning Event Completeness for Weakly Supervised Video Anomaly Detection
  9. ICML 2025LongVU: Spatiotemporal Adaptive Compression for Long Video-Language Understanding
  10. ICML 2025Massive Values in Self-Attention Modules are the Key to Contextual Knowledge Understanding
  11. ICML 2025MedXpertQA: Benchmarking Expert-Level Medical Reasoning and Understanding
  12. ICML 2025MODA: MOdular Duplex Attention for Multimodal Perception, Cognition, and Emotion Understanding
  13. ICML 2025Modularized Self-Reflected Video Reasoner for Multimodal LLM with Application to Video Question Answering
  14. ICML 2025MoMa: Modulating Mamba for Adapting Image Foundation Models to Video Recognition
  15. ICML 2025On Understanding Attention-Based In-Context Learning for Categorical Data
  16. ICML 2025PlaySlot: Learning Inverse Latent Dynamics for Controllable Object-Centric Video Prediction and Planning
  17. ICML 2025Position: Deep Learning is Not So Mysterious or Different
  18. ICML 2025Position: We Can’t Understand AI Using our Existing Vocabulary
  19. ICML 2025Potemkin Understanding in Large Language Models
  20. ICML 2025RIFLEx: A Free Lunch for Length Extrapolation in Video Diffusion Transformers
  21. ICML 2025Scaling Video-Language Models to 10K Frames via Hierarchical Differential Distillation
  22. ICML 2025SpargeAttention: Accurate and Training-free Sparse Attention Accelerating Any Model Inference
  23. ICML 2025Sparse Video-Gen: Accelerating Video Diffusion Transformers with Spatial-Temporal Sparsity
  24. ICML 2025SpikeVideoFormer: An Efficient Spike-Driven Video Transformer with Hamming Attention and $\mathcal{O}(T)$ Complexity
  25. ICML 2025Time to Spike? Understanding the Representational Power of Spiking Neural Networks in Discrete Time
  26. ICML 2025Towards Theoretical Understanding of Sequential Decision Making with Preference Feedback
  27. ICML 2025Towards Understanding Catastrophic Forgetting in Two-layer Convolutional Neural Networks
  28. ICML 2025Towards Understanding Gradient Dynamics of the Sliced-Wasserstein Distance via Critical Point Analysis
  29. ICML 2025Towards Understanding Parametric Generalized Category Discovery on Graphs
  30. ICML 2025Train for the Worst, Plan for the Best: Understanding Token Ordering in Masked Diffusions
  31. ICML 2025TUMTraf VideoQA: Dataset and Benchmark for Unified Spatio-Temporal Video Understanding in Traffic Scenes
  32. ICML 2025Understanding and Improving Length Generalization in Recurrent Models
  33. ICML 2025Understanding and Mitigating Memorization in Diffusion Models for Tabular Data
  34. ICML 2025Understanding and Mitigating Memorization in Generative Models via Sharpness of Probability Landscapes
  35. ICML 2025Understanding and Mitigating Miscalibration in Prompt Tuning for Vision-Language Models
  36. ICML 2025Understanding Chain-of-Thought in LLMs through Information Theory
  37. ICML 2025Understanding Fixed Predictions via Confined Regions
  38. ICML 2025Understanding Generalization in Quantum Machine Learning with Margins
  39. ICML 2025Understanding High-Dimensional Bayesian Optimization
  40. ICML 2025Understanding Input Selectivity in Mamba: Impact on Approximation Power, Memorization, and Associative Recall Capacity
  41. ICML 2025Understanding Mode Connectivity via Parameter Space Symmetry
  42. ICML 2025Understanding Model Reprogramming for CLIP via Decoupling Visual Prompts
  43. ICML 2025Understanding Multimodal LLMs Under Distribution Shifts: An Information-Theoretic Approach
  44. ICML 2025Understanding Nonlinear Implicit Bias via Region Counts in Input Space
  45. ICML 2025Understanding Sharpness Dynamics in NN Training with a Minimalist Example: The Effects of Dataset Difficulty, Depth, Stochasticity, and More
  46. ICML 2025Understanding the difficulties of posterior predictive estimation
  47. ICML 2025Understanding the Emergence of Multimodal Representation Alignment
  48. ICML 2025Understanding the Forgetting of (Replay-based) Continual Learning via Feature Learning: Angle Matters
  49. ICML 2025Understanding the Kronecker Matrix-Vector Complexity of Linear Algebra
  50. ICML 2025Understanding the Limits of Deep Tabular Methods with Temporal Shift

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