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 12 / 14 页

  1. NeurIPS 2025Orient Anything V2: Unifying Orientation and Rotation Understanding
  2. NeurIPS 2025PC-Net: Weakly Supervised Compositional Moment Retrieval via Proposal-Centric Network
  3. NeurIPS 2025Perceive Anything: Recognize, Explain, Caption, and Segment Anything in Images and Videos
  4. NeurIPS 2025PerceptionLM: Open-Access Data and Models for Detailed Visual Understanding
  5. NeurIPS 2025PlayerOne: Egocentric World Simulator
  6. NeurIPS 2025PMQ-VE: Progressive Multi-Frame Quantization for Video Enhancement
  7. NeurIPS 2025PolyVivid: Vivid Multi-Subject Video Generation with Cross-Modal Interaction and Enhancement
  8. NeurIPS 2025Positional Fragility in LLMs: How Offset Effects Reshape Our Understanding of Memorization Risks
  9. NeurIPS 2025Prior Forgetting and In-Context Overfitting
  10. NeurIPS 2025Prompt-guided Disentangled Representation for Action Recognition
  11. NeurIPS 2025PUO-Bench: A Panel Understanding and Operation Benchmark with A Privacy-Preserving Framework
  12. NeurIPS 2025Puzzles: Unbounded Video-Depth Augmentation for Scalable End-to-End 3D Reconstruction
  13. NeurIPS 2025Reading Recognition in the Wild
  14. NeurIPS 2025Rebalancing Contrastive Alignment with Bottlenecked Semantic Increments in Text-Video Retrieval
  15. NeurIPS 2025Recurrent Attention-based Token Selection for Efficient Streaming Video-LLMs
  16. NeurIPS 2025RePO: Understanding Preference Learning Through ReLU-Based Optimization
  17. NeurIPS 2025RepoMaster: Autonomous Exploration and Understanding of GitHub Repositories for Complex Task Solving
  18. NeurIPS 2025Restage4D: Reanimating Deformable 3D Reconstruction from a Single Video
  19. NeurIPS 2025Return of ChebNet: Understanding and Improving an Overlooked GNN on Long Range Tasks
  20. NeurIPS 2025Robust Egocentric Referring Video Object Segmentation via Dual-Modal Causal Intervention
  21. NeurIPS 2025ROVER: Recursive Reasoning Over Videos with Vision-Language Models for Embodied Tasks
  22. NeurIPS 2025RTV-Bench: Benchmarking MLLM Continuous Perception, Understanding and Reasoning through Real-Time Video
  23. NeurIPS 2025SAGE: A Unified Framework for Generalizable Object State Recognition with State-Action Graph Embedding
  24. NeurIPS 2025SAMA: Towards Multi-Turn Referential Grounded Video Chat with Large Language Models
  25. NeurIPS 2025SD-VLM: Spatial Measuring and Understanding with Depth-Encoded Vision-Language Models
  26. NeurIPS 2025See&Trek: Training-Free Spatial Prompting for Multimodal Large Language Model
  27. NeurIPS 2025Seeing the Arrow of Time in Large Multimodal Models
  28. NeurIPS 2025Seeing What Matters: Generalizable AI-generated Video Detection with Forensic-Oriented Augmentation
  29. NeurIPS 2025Self-alignment of Large Video Language Models with Refined Regularized Preference Optimization
  30. NeurIPS 2025Self-supervised Learning of Echocardiographic Video Representations via Online Cluster Distillation
  31. NeurIPS 2025Self-Supervised Learning of Motion Concepts by Optimizing Counterfactuals
  32. NeurIPS 2025ShapeLLM-Omni: A Native Multimodal LLM for 3D Generation and Understanding
  33. NeurIPS 2025ShotBench: Expert-Level Cinematic Understanding in Vision-Language Models
  34. NeurIPS 2025SIU3R: Simultaneous Scene Understanding and 3D Reconstruction Beyond Feature Alignment
  35. NeurIPS 2025Smooth Regularization for Efficient Video Recognition
  36. NeurIPS 2025Spatial-MLLM: Boosting MLLM Capabilities in Visual-based Spatial Intelligence
  37. NeurIPS 2025SpikingVTG: A Spiking Detection Transformer for Video Temporal Grounding
  38. NeurIPS 2025Spiral: Semantic-Aware Progressive LiDAR Scene Generation and Understanding
  39. NeurIPS 2025Stable Part Diffusion 4D: Multi-View RGB and Kinematic Parts Video Generation
  40. NeurIPS 2025State Space Prompting via Gathering and Spreading Spatio-Temporal Information for Video Understanding
  41. NeurIPS 2025Stitch and Tell: A Structured Data Augmentation Method for Spatial Understanding
  42. NeurIPS 2025Storyboard-guided Alignment for Fine-grained Video Action Recognition
  43. NeurIPS 2025StreamBridge: Turning Your Offline Video Large Language Model into a Proactive Streaming Assistant
  44. NeurIPS 2025StreamForest: Efficient Online Video Understanding with Persistent Event Memory
  45. NeurIPS 2025TaiwanVQA: Benchmarking and Enhancing Cultural Understanding in Vision-Language Models
  46. NeurIPS 2025Talk2Event: Grounded Understanding of Dynamic Scenes from Event Cameras
  47. NeurIPS 2025TAPVid-360: Tracking Any Point in 360 from Narrow Field of View Video
  48. NeurIPS 2025Temporal Chain of Thought: Long-Video Understanding by Thinking in Frames
  49. NeurIPS 2025Temporal In‑Context Fine‑Tuning for Versatile Control of Video Diffusion Models
  50. NeurIPS 2025The Graphon Limit Hypothesis: Understanding Neural Network Pruning via Infinite Width Analysis

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