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 222 篇，第 3 / 5 页

  1. NeurIPS 2025Positional Fragility in LLMs: How Offset Effects Reshape Our Understanding of Memorization Risks
  2. NeurIPS 2025Prior Forgetting and In-Context Overfitting
  3. NeurIPS 2025Prompt-guided Disentangled Representation for Action Recognition
  4. NeurIPS 2025PUO-Bench: A Panel Understanding and Operation Benchmark with A Privacy-Preserving Framework
  5. NeurIPS 2025Puzzles: Unbounded Video-Depth Augmentation for Scalable End-to-End 3D Reconstruction
  6. NeurIPS 2025Reading Recognition in the Wild
  7. NeurIPS 2025Rebalancing Contrastive Alignment with Bottlenecked Semantic Increments in Text-Video Retrieval
  8. NeurIPS 2025Recurrent Attention-based Token Selection for Efficient Streaming Video-LLMs
  9. NeurIPS 2025RePO: Understanding Preference Learning Through ReLU-Based Optimization
  10. NeurIPS 2025RepoMaster: Autonomous Exploration and Understanding of GitHub Repositories for Complex Task Solving
  11. NeurIPS 2025Restage4D: Reanimating Deformable 3D Reconstruction from a Single Video
  12. NeurIPS 2025Return of ChebNet: Understanding and Improving an Overlooked GNN on Long Range Tasks
  13. NeurIPS 2025Robust Egocentric Referring Video Object Segmentation via Dual-Modal Causal Intervention
  14. NeurIPS 2025ROVER: Recursive Reasoning Over Videos with Vision-Language Models for Embodied Tasks
  15. NeurIPS 2025RTV-Bench: Benchmarking MLLM Continuous Perception, Understanding and Reasoning through Real-Time Video
  16. NeurIPS 2025SAGE: A Unified Framework for Generalizable Object State Recognition with State-Action Graph Embedding
  17. NeurIPS 2025SAMA: Towards Multi-Turn Referential Grounded Video Chat with Large Language Models
  18. NeurIPS 2025SD-VLM: Spatial Measuring and Understanding with Depth-Encoded Vision-Language Models
  19. NeurIPS 2025See&Trek: Training-Free Spatial Prompting for Multimodal Large Language Model
  20. NeurIPS 2025Seeing the Arrow of Time in Large Multimodal Models
  21. NeurIPS 2025Seeing What Matters: Generalizable AI-generated Video Detection with Forensic-Oriented Augmentation
  22. NeurIPS 2025Self-alignment of Large Video Language Models with Refined Regularized Preference Optimization
  23. NeurIPS 2025Self-supervised Learning of Echocardiographic Video Representations via Online Cluster Distillation
  24. NeurIPS 2025Self-Supervised Learning of Motion Concepts by Optimizing Counterfactuals
  25. NeurIPS 2025ShapeLLM-Omni: A Native Multimodal LLM for 3D Generation and Understanding
  26. NeurIPS 2025ShotBench: Expert-Level Cinematic Understanding in Vision-Language Models
  27. NeurIPS 2025SIU3R: Simultaneous Scene Understanding and 3D Reconstruction Beyond Feature Alignment
  28. NeurIPS 2025Smooth Regularization for Efficient Video Recognition
  29. NeurIPS 2025Spatial-MLLM: Boosting MLLM Capabilities in Visual-based Spatial Intelligence
  30. NeurIPS 2025SpikingVTG: A Spiking Detection Transformer for Video Temporal Grounding
  31. NeurIPS 2025Spiral: Semantic-Aware Progressive LiDAR Scene Generation and Understanding
  32. NeurIPS 2025Stable Part Diffusion 4D: Multi-View RGB and Kinematic Parts Video Generation
  33. NeurIPS 2025State Space Prompting via Gathering and Spreading Spatio-Temporal Information for Video Understanding
  34. NeurIPS 2025Stitch and Tell: A Structured Data Augmentation Method for Spatial Understanding
  35. NeurIPS 2025Storyboard-guided Alignment for Fine-grained Video Action Recognition
  36. NeurIPS 2025StreamBridge: Turning Your Offline Video Large Language Model into a Proactive Streaming Assistant
  37. NeurIPS 2025StreamForest: Efficient Online Video Understanding with Persistent Event Memory
  38. NeurIPS 2025TaiwanVQA: Benchmarking and Enhancing Cultural Understanding in Vision-Language Models
  39. NeurIPS 2025Talk2Event: Grounded Understanding of Dynamic Scenes from Event Cameras
  40. NeurIPS 2025TAPVid-360: Tracking Any Point in 360 from Narrow Field of View Video
  41. NeurIPS 2025Temporal Chain of Thought: Long-Video Understanding by Thinking in Frames
  42. NeurIPS 2025Temporal In‑Context Fine‑Tuning for Versatile Control of Video Diffusion Models
  43. NeurIPS 2025The Graphon Limit Hypothesis: Understanding Neural Network Pruning via Infinite Width Analysis
  44. NeurIPS 2025The Illusion of Thinking: Understanding the Strengths and Limitations of Reasoning Models via the Lens of Problem Complexity
  45. NeurIPS 2025The Underappreciated Power of Vision Models for Graph Structural Understanding
  46. NeurIPS 2025Through the River: Understanding the Benefit of Schedule-Free Methods for Language Model Training
  47. NeurIPS 2025To Distill or Decide? Understanding the Algorithmic Trade-off in Partially Observable RL
  48. NeurIPS 2025Topology of Reasoning: Understanding Large Reasoning Models through Reasoning Graph Properties
  49. NeurIPS 2025Toward a Unified Geometry Understanding : Riemannian Diffusion Framework for Graph Generation and Prediction
  50. NeurIPS 2025Towards a Geometric Understanding of Tensor Learning via the t-Product

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