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 39 / 46 页

  1. NeurIPS 2024SILENCE: Protecting privacy in offloaded speech understanding on resource-constrained devices
  2. NeurIPS 2024Slot State Space Models
  3. NeurIPS 2024Slot-VLM: Object-Event Slots for Video-Language Modeling
  4. NeurIPS 2024SlowFocus: Enhancing Fine-grained Temporal Understanding in Video LLM
  5. NeurIPS 2024Splatter a Video: Video Gaussian Representation for Versatile Processing
  6. NeurIPS 2024Streaming Detection of Queried Event Start
  7. NeurIPS 2024Streaming Long Video Understanding with Large Language Models
  8. NeurIPS 2024SyncVIS: Synchronized Video Instance Segmentation
  9. NeurIPS 2024Talking Heads: Understanding Inter-Layer Communication in Transformer Language Models
  10. NeurIPS 2024TAPVid-3D: A Benchmark for Tracking Any Point in 3D
  11. NeurIPS 2024The Importance of Online Data: Understanding Preference Fine-tuning via Coverage
  12. NeurIPS 2024TopoFR: A Closer Look at Topology Alignment on Face Recognition
  13. NeurIPS 2024Towards a Theoretical Understanding of the 'Reversal Curse' via Training Dynamics
  14. NeurIPS 2024Towards Understanding Evolving Patterns in Sequential Data
  15. NeurIPS 2024Towards Understanding Extrapolation: a Causal Lens
  16. NeurIPS 2024Towards Understanding How Transformers Learn In-context Through a Representation Learning Lens
  17. NeurIPS 2024TrackIME: Enhanced Video Point Tracking via Instance Motion Estimation
  18. NeurIPS 2024Understanding and Improving Adversarial Collaborative Filtering for Robust Recommendation
  19. NeurIPS 2024Understanding and Minimising Outlier Features in Transformer Training
  20. NeurIPS 2024Understanding Bias in Large-Scale Visual Datasets
  21. NeurIPS 2024Understanding Emergent Abilities of Language Models from the Loss Perspective
  22. NeurIPS 2024Understanding Generalizability of Diffusion Models Requires Rethinking the Hidden Gaussian Structure
  23. NeurIPS 2024Understanding Hallucinations in Diffusion Models through Mode Interpolation
  24. NeurIPS 2024Understanding Representation of Deep Equilibrium Models from Neural Collapse Perspective
  25. NeurIPS 2024Understanding Scaling Laws with Statistical and Approximation Theory for Transformer Neural Networks on Intrinsically Low-dimensional Data
  26. NeurIPS 2024Understanding the Differences in Foundation Models: Attention, State Space Models, and Recurrent Neural Networks
  27. NeurIPS 2024Understanding the Expressive Power and Mechanisms of Transformer for Sequence Modeling
  28. NeurIPS 2024Understanding the Expressivity and Trainability of Fourier Neural Operator: A Mean-Field Perspective
  29. NeurIPS 2024Understanding the Gains from Repeated Self-Distillation
  30. NeurIPS 2024Understanding the Role of Equivariance in Self-supervised Learning
  31. NeurIPS 2024Understanding the Transferability of Representations via Task-Relatedness
  32. NeurIPS 2024Understanding Transformers via N-Gram Statistics
  33. NeurIPS 2024Understanding Visual Feature Reliance through the Lens of Complexity
  34. NeurIPS 2024VERIFIED: A Video Corpus Moment Retrieval Benchmark for Fine-Grained Video Understanding
  35. NeurIPS 2024VFIMamba: Video Frame Interpolation with State Space Models
  36. NeurIPS 2024Video Diffusion Models are Training-free Motion Interpreter and Controller
  37. NeurIPS 2024Video Token Merging for Long Video Understanding
  38. NeurIPS 2024VideoLLM-MoD: Efficient Video-Language Streaming with Mixture-of-Depths Vision Computation
  39. NeurIPS 2024VidProM: A Million-scale Real Prompt-Gallery Dataset for Text-to-Video Diffusion Models
  40. NeurIPS 2024Vript: A Video Is Worth Thousands of Words
  41. NeurIPS 2024Warped Diffusion: Solving Video Inverse Problems with Image Diffusion Models
  42. NeurIPS 2024When LLMs Meet Cunning Texts: A Fallacy Understanding Benchmark for Large Language Models
  43. CVPR 20231000 FPS HDR Video With a Spike-RGB Hybrid Camera
  44. CVPR 20233D Video Loops From Asynchronous Input
  45. CVPR 20233D Video Object Detection With Learnable Object-Centric Global Optimization
  46. CVPR 2023A Dynamic Multi-Scale Voxel Flow Network for Video Prediction
  47. CVPR 2023A Generalized Framework for Video Instance Segmentation
  48. CVPR 2023A Large-Scale Robustness Analysis of Video Action Recognition Models
  49. CVPR 2023A Simple Baseline for Video Restoration With Grouped Spatial-Temporal Shift
  50. CVPR 2023A Unified Pyramid Recurrent Network for Video Frame Interpolation

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