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 2,261 篇，第 30 / 46 页

  1. NeurIPS 2025Understanding Adam Requires Better Rotation Dependent Assumptions
  2. NeurIPS 2025Understanding and Enhancing Mask-Based Pretraining towards Universal Representations
  3. NeurIPS 2025Understanding and Enhancing Message Passing on Heterophilic Graphs via Compatibility Matrix
  4. NeurIPS 2025Understanding and Improving Adversarial Robustness of Neural Probabilistic Circuits
  5. NeurIPS 2025Understanding and Improving Fast Adversarial Training against $l_0$ Bounded Perturbations
  6. NeurIPS 2025Understanding and Mitigating Numerical Sources of Nondeterminism in LLM Inference
  7. NeurIPS 2025Understanding and Rectifying Safety Perception Distortion in VLMs
  8. NeurIPS 2025Understanding Bias Terms in Neural Representations
  9. NeurIPS 2025Understanding challenges to the interpretation of disaggregated evaluations of algorithmic fairness
  10. NeurIPS 2025Understanding Contrastive Learning via Gaussian Mixture Models
  11. NeurIPS 2025Understanding Data Influence in Reinforcement Finetuning
  12. NeurIPS 2025Understanding Differential Transformer Unchains Pretrained Self-Attentions
  13. NeurIPS 2025Understanding Generalization in Physics Informed Models through Affine Variety Dimensions
  14. NeurIPS 2025Understanding LLM Behaviors via Compression: Data Generation, Knowledge Acquisition and Scaling Laws
  15. NeurIPS 2025Understanding outer learning rates in Local SGD
  16. NeurIPS 2025Understanding Parametric and Contextual Knowledge Reconciliation within Large Language Models
  17. NeurIPS 2025Understanding Prompt Tuning and In-Context Learning via Meta-Learning
  18. NeurIPS 2025Understanding Representation Dynamics of Diffusion Models via Low-Dimensional Modeling
  19. NeurIPS 2025Understanding Softmax Attention Layers:\\ Exact Mean-Field Analysis on a Toy Problem
  20. NeurIPS 2025Understanding the Evolution of the Neural Tangent Kernel at the Edge of Stability
  21. NeurIPS 2025Understanding the Gain from Data Filtering in Multimodal Contrastive Learning
  22. NeurIPS 2025Understanding the Generalization of Stochastic Gradient Adam in Learning Neural Networks
  23. NeurIPS 2025Understanding while Exploring: Semantics-driven Active Mapping
  24. NeurIPS 2025UniCTokens: Boosting Personalized Understanding and Generation via Unified Concept Tokens
  25. NeurIPS 2025UniRelight: Learning Joint Decomposition and Synthesis for Video Relighting
  26. NeurIPS 2025UniTok: a Unified Tokenizer for Visual Generation and Understanding
  27. NeurIPS 2025Universal Video Temporal Grounding with Generative Multi-modal Large Language Models
  28. NeurIPS 2025Universal Visuo-Tactile Video Understanding for Embodied Interaction
  29. NeurIPS 2025UniViT: Unifying Image and Video Understanding in One Vision Encoder
  30. NeurIPS 2025Unleashing Hour-Scale Video Training for Long Video-Language Understanding
  31. NeurIPS 2025URLs Help, Topics Guide: Understanding Metadata Utility in LLM Training
  32. NeurIPS 2025UVE: Are MLLMs Unified Evaluators for AI-Generated Videos?
  33. NeurIPS 2025VADB: A Large-Scale Video Aesthetic Database with Professional and Multi-Dimensional Annotations
  34. NeurIPS 2025VADTree: Explainable Training-Free Video Anomaly Detection via Hierarchical Granularity-Aware Tree
  35. NeurIPS 2025VaporTok: RL-Driven Adaptive Video Tokenizer with Prior & Task Awareness
  36. NeurIPS 2025VFRTok: Variable Frame Rates Video Tokenizer with Duration-Proportional Information Assumption
  37. NeurIPS 2025Vgent: Graph-based Retrieval-Reasoning-Augmented Generation For Long Video Understanding
  38. NeurIPS 2025Vid-SME: Membership Inference Attacks against Large Video Understanding Models
  39. NeurIPS 2025ViDAR: Video Diffusion-Aware 4D Reconstruction From Monocular Inputs
  40. NeurIPS 2025VidEmo: Affective-Tree Reasoning for Emotion-Centric Video Foundation Models
  41. NeurIPS 2025Video Diffusion Models Excel at Tracking Similar-Looking Objects Without Supervision
  42. NeurIPS 2025Video-RAG: Visually-aligned Retrieval-Augmented Long Video Comprehension
  43. NeurIPS 2025VideoGameQA-Bench: Evaluating Vision-Language Models for Video Game Quality Assurance
  44. NeurIPS 2025VideoLucy: Deep Memory Backtracking for Long Video Understanding
  45. NeurIPS 2025VideoMAR: Autoregressive Video Generation with Continuous Tokens
  46. NeurIPS 2025VideoTitans: Scalable Video Prediction with Integrated Short- and Long-term Memory
  47. NeurIPS 2025VideoVLA: Video Generators Can Be Generalizable Robot Manipulators
  48. NeurIPS 2025Visual Sync: Multi‑Camera Synchronization via Cross‑View Object Motion
  49. NeurIPS 2025Visual Thoughts: A Unified Perspective of Understanding Multimodal Chain-of-Thought
  50. NeurIPS 2025VITRIX-CLIPIN: Enhancing Fine-Grained Visual Understanding in CLIP via Instruction-Editing Data and Long Captions

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