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 13 / 46 页

  1. ICML 2026VideoTemp-o3: Harmonizing Temporal Grounding and Video Understanding in Agentic Thinking-with-Videos
  2. ICML 2026VidLaDA: Bidirectional Diffusion Large Language Models for Efficient Video Understanding
  3. ICML 2026Words Towards Explainability: Caption Label-Free Learning via Dual Loop Agentic Time Series Captioning
  4. NeurIPS 20263DSPA: A 3D Semantic Point Autoencoder for Evaluating Video Realism
  5. NeurIPS 2026A Local Geometric Analysis of Maximal Coding Rate Reduction via Error Bounds
  6. NeurIPS 2026A Matter of Interest: Understanding Interestingness Judgments of Math Problems in Humans and Language Models
  7. NeurIPS 2026A Principled Optimal Transport Framework for Frame Selection in Long Video Understanding
  8. NeurIPS 2026A Training-Free Video Moment Retrieval Framework via Selection from Multiple Visual Prompts
  9. NeurIPS 2026A Unified Image and Video Encoder for Multimodal LLMs
  10. NeurIPS 2026Accelerating Video Inverse Problem Solvers with Autoregressive Diffusion Models
  11. NeurIPS 2026ActO: Extracting Action Representations from MLLM Embeddings for Video World Models
  12. NeurIPS 2026AdaCodec: A Predictive Visual Code for Video MLLMs
  13. NeurIPS 2026AdaState: Self-Evolving Anchors for Streaming Video Generation
  14. NeurIPS 2026Addressable Memory for Video World Models
  15. NeurIPS 2026AdShot: Benchmarking Multimodal Large Language Models for Video Advertisement Clipping
  16. NeurIPS 2026AEON: Unifying Video and 3D World Models
  17. NeurIPS 2026AgenticVBench: Can AI Agents Complete Real-World Video Production Tasks?
  18. NeurIPS 2026Aligning Forest and Trees in Images & Long Captions for Visually Grounded Understanding
  19. NeurIPS 2026AmbiguousWorld: Benchmarking and Resolving Ambiguous Instructions in Video World Models
  20. NeurIPS 2026Apple-$\pi$: Benchmarking Thinking with Video Towards Law-Grounded Physical Intelligence
  21. NeurIPS 2026AR-Edit: Training-Free Streaming Video Editing without Inversion
  22. NeurIPS 2026Articulation in Prime: Primitive-Based Articulated Object Understanding from a Single Casual Video
  23. NeurIPS 2026ASAP: Attention Sink Anchored Pruning
  24. NeurIPS 2026AsymHP: Load-Balanced Sparse Attention for Video Diffusion Transformers
  25. NeurIPS 2026Attend Locally, Remember Linearly: Linear Attention as Cross-Frame Memory for Autoregressive Video Diffusion
  26. NeurIPS 2026Automated Kernel Discovery Towards Understanding High-dimensional Bayesian Optimization
  27. NeurIPS 2026AVENUE: Audio-Video Editing Understanding and Evaluation
  28. NeurIPS 2026AVOC: Enhancing Hour-Level Audio-Video Understanding in Omni-Modal LLMs via Retrieval-Inspired Token Compression
  29. NeurIPS 2026BasicLT: Basic-Level Abstraction and Selective Differentiation for Long-Tailed Recognition
  30. NeurIPS 2026BEAST3D: animal behavioral analysis and neural encoding from multi-view video via Gaussian splatting
  31. NeurIPS 2026Behavior Pack Optimization for Video MLLM Post-Training
  32. NeurIPS 2026Behavioral Geometric Supervision Aligns Video Foundation Models with Human Social Perception
  33. NeurIPS 2026Benchmarking Fine-Grained Spatio-Temporal Awareness in Embodied Brain Models
  34. NeurIPS 2026Bernini: Latent Semantic Planning for Video Diffusion
  35. NeurIPS 2026Beyond Flat Frames: Hierarchical Graph Reasoning for Long Video Understanding
  36. NeurIPS 2026Beyond Oversquashing: Understanding Signal Propagation in GNNs Via Observables
  37. NeurIPS 2026Beyond Single Expert: Harmonizing Diverse Visual Priors in MLLMs for Spatial Understanding
  38. NeurIPS 2026Bidirectional Sparse Attention for Faster Video Diffusion Training
  39. NeurIPS 2026Breaking the Second Barrier: Sub-Second Timestamped Omni-Modal Captioning
  40. NeurIPS 2026Breaking the Uniformity Trap: Scaling Video Diffusion Model via SplitMoE
  41. NeurIPS 2026Bridging Modalities, Spanning Time: Structured Memory for Ultra-Long Agentic Video Reasoning
  42. NeurIPS 2026CAIRN: Cross-Room 3D Scene Understanding with Topology-Aware Large Multimodal Models
  43. NeurIPS 2026CARVE: Counterfactual Video Editing for Auditing and Hardening Video Detectors
  44. NeurIPS 2026CoANeRV: Coordinate-Aware Token-Space Neural Video Representation
  45. NeurIPS 2026ColorConceptBench: A Benchmark for Probabilistic Color-Concept Understanding in Text-to-Image Models
  46. NeurIPS 2026Computational Depth Predicts Quantization Sensitivity in Multimodal Models
  47. NeurIPS 2026Conditional Multi-Event Temporal Grounding in Long-Form Video
  48. NeurIPS 2026Controllable Multi-label Video Safety Detection via Adaptive Tversky Policy Optimization
  49. NeurIPS 2026CoPE-VideoLM: Leveraging Codec Primitives For Efficient Video Language Modelling
  50. NeurIPS 2026CoRDS: Coreset-Based Representative and Diverse Selection for Streaming Video Understanding

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