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 8 / 14 页

  1. ICLR 2025Scalable Benchmarking and Robust Learning for Noise-Free Ego-Motion and 3D Reconstruction from Noisy Video
  2. ICLR 2025See It from My Perspective: How Language Affects Cultural Bias in Image Understanding
  3. ICLR 2025Shot2Story: A New Benchmark for Comprehensive Understanding of Multi-shot Videos
  4. ICLR 2025Solving Video Inverse Problems Using Image Diffusion Models
  5. ICLR 2025Streaming Video Question-Answering with In-context Video KV-Cache Retrieval
  6. ICLR 2025Streaming Video Understanding and Multi-round Interaction with Memory-enhanced Knowledge
  7. ICLR 2025StringLLM: Understanding the String Processing Capability of Large Language Models
  8. ICLR 2025SVBench: A Benchmark with Temporal Multi-Turn Dialogues for Streaming Video Understanding
  9. ICLR 2025SVG: 3D Stereoscopic Video Generation via Denoising Frame Matrix
  10. ICLR 2025TAU-106K: A New Dataset for Comprehensive Understanding of Traffic Accident
  11. ICLR 2025Teaching Human Behavior Improves Content Understanding Abilities Of VLMs
  12. ICLR 2025TimeSuite: Improving MLLMs for Long Video Understanding via Grounded Tuning
  13. ICLR 2025Topological Blindspots: Understanding and Extending Topological Deep Learning Through the Lens of Expressivity
  14. ICLR 2025Toward Understanding In-context vs. In-weight Learning
  15. ICLR 2025Towards a Theoretical Understanding of Synthetic Data in LLM Post-Training: A Reverse-Bottleneck Perspective
  16. ICLR 2025Towards a Unified and Verified Understanding of Group-Operation Networks
  17. ICLR 2025Towards Understanding the Robustness of Diffusion-Based Purification: A Stochastic Perspective
  18. ICLR 2025Towards Understanding the Universality of Transformers for Next-Token Prediction
  19. ICLR 2025Towards Understanding Why FixMatch Generalizes Better Than Supervised Learning
  20. ICLR 2025Towards Understanding Why Label Smoothing Degrades Selective Classification and How to Fix It
  21. ICLR 2025TRACE: Temporal Grounding Video LLM via Causal Event Modeling
  22. ICLR 2025Understanding and Enhancing the Transferability of Jailbreaking Attacks
  23. ICLR 2025Understanding and Mitigating Bottlenecks of State Space Models through the Lens of Recency and Over-smoothing
  24. ICLR 2025Understanding and Mitigating Hallucination in Large Vision-Language Models via Modular Attribution and Intervention
  25. ICLR 2025Understanding Constraint Inference in Safety-Critical Inverse Reinforcement Learning
  26. ICLR 2025Understanding Factual Recall in Transformers via Associative Memories
  27. ICLR 2025Understanding Long Videos with Multimodal Language Models
  28. ICLR 2025Understanding Matrix Function Normalizations in Covariance Pooling through the Lens of Riemannian Geometry
  29. ICLR 2025Understanding Optimization in Deep Learning with Central Flows
  30. ICLR 2025Understanding the Generalization of In-Context Learning in Transformers: An Empirical Study
  31. ICLR 2025Understanding the Stability-based Generalization of Personalized Federated Learning
  32. ICLR 2025Understanding Virtual Nodes: Oversquashing and Node Heterogeneity
  33. ICLR 2025Understanding Warmup-Stable-Decay Learning Rates: A River Valley Loss Landscape View
  34. ICLR 2025Unhackable Temporal Reward for Scalable Video MLLMs
  35. ICLR 2025ViBiDSampler: Enhancing Video Interpolation Using Bidirectional Diffusion Sampler
  36. ICLR 2025Video In-context Learning: Autoregressive Transformers are Zero-Shot Video Imitators
  37. ICLR 2025Video-STaR: Self-Training Enables Video Instruction Tuning with Any Supervision
  38. ICLR 2025VideoGrain: Modulating Space-Time Attention for Multi-Grained Video Editing
  39. ICLR 2025VideoWebArena: Evaluating Long Context Multimodal Agents with Video Understanding Web Tasks
  40. ICLR 2025Watch Less, Do More: Implicit Skill Discovery for Video-Conditioned Policy
  41. ICLR 2025Weakly Supervised Video Scene Graph Generation via Natural Language Supervision
  42. ICLR 2025What Secrets Do Your Manifolds Hold? Understanding the Local Geometry of Generative Models
  43. ICLR 2025World Model on Million-Length Video And Language With Blockwise RingAttention
  44. ICML 2025$\infty$-Video: A Training-Free Approach to Long Video Understanding via Continuous-Time Memory Consolidation
  45. ICML 2025$\mathcal{V}ista\mathcal{DPO}$: Video Hierarchical Spatial-Temporal Direct Preference Optimization for Large Video Models
  46. ICML 2025A Closer Look at Transformers for Time Series Forecasting: Understanding Why They Work and Where They Struggle
  47. ICML 2025Action Dubber: Timing Audible Actions via Inflectional Flow
  48. ICML 2025AffectGPT: A New Dataset, Model, and Benchmark for Emotion Understanding with Multimodal Large Language Models
  49. ICML 2025AsymRnR: Video Diffusion Transformers Acceleration with Asymmetric Reduction and Restoration
  50. ICML 2025BDC-CLIP: Brownian Distance Covariance for Adapting CLIP to Action Recognition

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