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 28 / 46 页

  1. NeurIPS 2025InfiniPot-V: Memory-Constrained KV Cache Compression for Streaming Video Understanding
  2. NeurIPS 2025INST-IT: Boosting Instance Understanding via Explicit Visual Prompt Instruction Tuning
  3. NeurIPS 2025Instant4D: 4D Gaussian Splatting in Minutes
  4. NeurIPS 2025JavisGPT: A Unified Multi-modal LLM for Sounding-Video Comprehension and Generation
  5. NeurIPS 2025LaViDa: A Large Diffusion Model for Vision-Language Understanding
  6. NeurIPS 2025Learning Skill-Attributes for Transferable Assessment in Video
  7. NeurIPS 2025Less Is More, but Where? Dynamic Token Compression via LLM-Guided Keyframe Prior
  8. NeurIPS 2025LiveStar: Live Streaming Assistant for Real-World Online Video Understanding
  9. NeurIPS 2025Logic-in-Frames: Dynamic Keyframe Search via Visual Semantic-Logical Verification for Long Video Understanding
  10. NeurIPS 2025LongVPO: From Anchored Cues to Self-Reasoning for Long-Form Video Preference Optimization
  11. NeurIPS 2025LuxDiT: Lighting Estimation with Video Diffusion Transformer
  12. NeurIPS 2025Martian World Model: Controllable Video Synthesis with Physically Accurate 3D Reconstructions
  13. NeurIPS 2025Mitigating Semantic Collapse in Partially Relevant Video Retrieval
  14. NeurIPS 2025MLLMs Need 3D-Aware Representation Supervision for Scene Understanding
  15. NeurIPS 2025MME-VideoOCR: Evaluating OCR-Based Capabilities of Multimodal LLMs in Video Scenarios
  16. NeurIPS 2025Mol-LLaMA: Towards General Understanding of Molecules in Large Molecular Language Model
  17. NeurIPS 2025MomentSeeker: A Task-Oriented Benchmark For Long-Video Moment Retrieval
  18. NeurIPS 2025MoniTor: Exploiting Large Language Models with Instruction for Online Video Anomaly Detection
  19. NeurIPS 2025Motion Matters: Compact Gaussian Streaming for Free-Viewpoint Video Reconstruction
  20. NeurIPS 2025Motion4D: Learning 3D-Consistent Motion and Semantics for 4D Scene Understanding
  21. NeurIPS 2025MR. Video: MapReduce as an Effective Principle for Long Video Understanding
  22. NeurIPS 2025Multi-Kernel Correlation-Attention Vision Transformer for Enhanced Contextual Understanding and Multi-Scale Integration
  23. NeurIPS 2025MVU-Eval: Towards Multi-Video Understanding Evaluation for Multimodal LLMs
  24. NeurIPS 2025NAUTILUS: A Large Multimodal Model for Underwater Scene Understanding
  25. NeurIPS 2025NEED: Cross-Subject and Cross-Task Generalization for Video and Image Reconstruction from EEG Signals
  26. NeurIPS 2025Neural B-frame Video Compression with Bi-directional Reference Harmonization
  27. NeurIPS 2025OctoNet: A Large-Scale Multi-Modal Dataset for Human Activity Understanding Grounded in Motion-Captured 3D Pose Labels
  28. NeurIPS 2025On the Hardness of Approximating Distributions with Tractable Probabilistic Models
  29. NeurIPS 2025One Token per Highly Selective Frame: Towards Extreme Compression for Long Video Understanding
  30. NeurIPS 2025One-Step Diffusion for Detail-Rich and Temporally Consistent Video Super-Resolution
  31. NeurIPS 2025OnlineSplatter: Pose-Free Online 3D Reconstruction for Free-Moving Objects
  32. NeurIPS 2025OpenMMEgo: Enhancing Egocentric Understanding for LMMs with Open Weights and Data
  33. NeurIPS 2025Orient Anything V2: Unifying Orientation and Rotation Understanding
  34. NeurIPS 2025PC-Net: Weakly Supervised Compositional Moment Retrieval via Proposal-Centric Network
  35. NeurIPS 2025Perceive Anything: Recognize, Explain, Caption, and Segment Anything in Images and Videos
  36. NeurIPS 2025PerceptionLM: Open-Access Data and Models for Detailed Visual Understanding
  37. NeurIPS 2025PlayerOne: Egocentric World Simulator
  38. NeurIPS 2025PMQ-VE: Progressive Multi-Frame Quantization for Video Enhancement
  39. NeurIPS 2025PolyVivid: Vivid Multi-Subject Video Generation with Cross-Modal Interaction and Enhancement
  40. NeurIPS 2025Positional Fragility in LLMs: How Offset Effects Reshape Our Understanding of Memorization Risks
  41. NeurIPS 2025Prior Forgetting and In-Context Overfitting
  42. NeurIPS 2025Prompt-guided Disentangled Representation for Action Recognition
  43. NeurIPS 2025PUO-Bench: A Panel Understanding and Operation Benchmark with A Privacy-Preserving Framework
  44. NeurIPS 2025Puzzles: Unbounded Video-Depth Augmentation for Scalable End-to-End 3D Reconstruction
  45. NeurIPS 2025Reading Recognition in the Wild
  46. NeurIPS 2025Rebalancing Contrastive Alignment with Bottlenecked Semantic Increments in Text-Video Retrieval
  47. NeurIPS 2025Recurrent Attention-based Token Selection for Efficient Streaming Video-LLMs
  48. NeurIPS 2025RePO: Understanding Preference Learning Through ReLU-Based Optimization
  49. NeurIPS 2025RepoMaster: Autonomous Exploration and Understanding of GitHub Repositories for Complex Task Solving
  50. NeurIPS 2025Restage4D: Reanimating Deformable 3D Reconstruction from a Single Video

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