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 9 / 13 页

  1. NeurIPS 2025Understanding Data Influence in Reinforcement Finetuning
  2. NeurIPS 2025Understanding Differential Transformer Unchains Pretrained Self-Attentions
  3. NeurIPS 2025Understanding Generalization in Physics Informed Models through Affine Variety Dimensions
  4. NeurIPS 2025Understanding LLM Behaviors via Compression: Data Generation, Knowledge Acquisition and Scaling Laws
  5. NeurIPS 2025Understanding outer learning rates in Local SGD
  6. NeurIPS 2025Understanding Parametric and Contextual Knowledge Reconciliation within Large Language Models
  7. NeurIPS 2025Understanding Prompt Tuning and In-Context Learning via Meta-Learning
  8. NeurIPS 2025Understanding Representation Dynamics of Diffusion Models via Low-Dimensional Modeling
  9. NeurIPS 2025Understanding Softmax Attention Layers:\\ Exact Mean-Field Analysis on a Toy Problem
  10. NeurIPS 2025Understanding the Evolution of the Neural Tangent Kernel at the Edge of Stability
  11. NeurIPS 2025Understanding the Gain from Data Filtering in Multimodal Contrastive Learning
  12. NeurIPS 2025Understanding the Generalization of Stochastic Gradient Adam in Learning Neural Networks
  13. NeurIPS 2025Understanding while Exploring: Semantics-driven Active Mapping
  14. NeurIPS 2025UniCTokens: Boosting Personalized Understanding and Generation via Unified Concept Tokens
  15. NeurIPS 2025UniRelight: Learning Joint Decomposition and Synthesis for Video Relighting
  16. NeurIPS 2025UniTok: a Unified Tokenizer for Visual Generation and Understanding
  17. NeurIPS 2025Universal Video Temporal Grounding with Generative Multi-modal Large Language Models
  18. NeurIPS 2025Universal Visuo-Tactile Video Understanding for Embodied Interaction
  19. NeurIPS 2025UniViT: Unifying Image and Video Understanding in One Vision Encoder
  20. NeurIPS 2025Unleashing Hour-Scale Video Training for Long Video-Language Understanding
  21. NeurIPS 2025URLs Help, Topics Guide: Understanding Metadata Utility in LLM Training
  22. NeurIPS 2025UVE: Are MLLMs Unified Evaluators for AI-Generated Videos?
  23. NeurIPS 2025VADB: A Large-Scale Video Aesthetic Database with Professional and Multi-Dimensional Annotations
  24. NeurIPS 2025VADTree: Explainable Training-Free Video Anomaly Detection via Hierarchical Granularity-Aware Tree
  25. NeurIPS 2025VaporTok: RL-Driven Adaptive Video Tokenizer with Prior & Task Awareness
  26. NeurIPS 2025VFRTok: Variable Frame Rates Video Tokenizer with Duration-Proportional Information Assumption
  27. NeurIPS 2025Vgent: Graph-based Retrieval-Reasoning-Augmented Generation For Long Video Understanding
  28. NeurIPS 2025Vid-SME: Membership Inference Attacks against Large Video Understanding Models
  29. NeurIPS 2025ViDAR: Video Diffusion-Aware 4D Reconstruction From Monocular Inputs
  30. NeurIPS 2025VidEmo: Affective-Tree Reasoning for Emotion-Centric Video Foundation Models
  31. NeurIPS 2025Video Diffusion Models Excel at Tracking Similar-Looking Objects Without Supervision
  32. NeurIPS 2025Video-RAG: Visually-aligned Retrieval-Augmented Long Video Comprehension
  33. NeurIPS 2025VideoGameQA-Bench: Evaluating Vision-Language Models for Video Game Quality Assurance
  34. NeurIPS 2025VideoLucy: Deep Memory Backtracking for Long Video Understanding
  35. NeurIPS 2025VideoMAR: Autoregressive Video Generation with Continuous Tokens
  36. NeurIPS 2025VideoTitans: Scalable Video Prediction with Integrated Short- and Long-term Memory
  37. NeurIPS 2025VideoVLA: Video Generators Can Be Generalizable Robot Manipulators
  38. NeurIPS 2025Visual Sync: Multi‑Camera Synchronization via Cross‑View Object Motion
  39. NeurIPS 2025Visual Thoughts: A Unified Perspective of Understanding Multimodal Chain-of-Thought
  40. NeurIPS 2025VITRIX-CLIPIN: Enhancing Fine-Grained Visual Understanding in CLIP via Instruction-Editing Data and Long Captions
  41. NeurIPS 2025VividFace: A Robost and High-Fidelity Video Face Swapping Framework
  42. NeurIPS 2025VQToken: Neural Discrete Token Representation Learning for Extreme Token Reduction in Video Large Language Models
  43. NeurIPS 2025Web-Scale Collection of Video Data for 4D Animal Reconstruction
  44. NeurIPS 2025What are you sinking? A geometric approach on attention sink
  45. NeurIPS 2025What Do Latent Action Models Actually Learn?
  46. NeurIPS 2025What Happens During the Loss Plateau? Understanding Abrupt Learning in Transformers
  47. NeurIPS 2025What We Miss Matters: Learning from the Overlooked in Point Cloud Transformers
  48. NeurIPS 2025When Semantics Mislead Vision: Mitigating Large Multimodal Models Hallucinations in Scene Text Spotting and Understanding
  49. NeurIPS 2025When Thinking Drifts: Evidential Grounding for Robust Video Reasoning
  50. NeurIPS 2025ZeroPatcher: Training-free Sampler for Video Inpainting and Editing

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