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 27 / 46 页

  1. NeurIPS 2025Autoregressive Adversarial Post-Training for Real-Time Interactive Video Generation
  2. NeurIPS 2025Bisecle: Binding and Separation in Continual Learning for Video Language Understanding
  3. NeurIPS 2025Brain-Informed Fine-Tuning for Improved Multilingual Understanding in Language Models
  4. NeurIPS 2025CamSAM2: Segment Anything Accurately in Camouflaged Videos
  5. NeurIPS 2025CausalVTG: Towards Robust Video Temporal Grounding via Causal Inference
  6. NeurIPS 2025Chirality in Action: Time-Aware Video Representation Learning by Latent Straightening
  7. NeurIPS 2025CineTechBench: A Benchmark for Cinematographic Technique Understanding and Generation
  8. NeurIPS 2025ConViS-Bench: Estimating Video Similarity Through Semantic Concepts
  9. NeurIPS 2025CoralVQA: A Large-Scale Visual Question Answering Dataset for Coral Reef Image Understanding
  10. NeurIPS 2025CroPe: Cross-Modal Semantic Compensation Adaptation for All Adverse Scene Understanding
  11. NeurIPS 2025DanmakuTPPBench: A Multi-modal Benchmark for Temporal Point Process Modeling and Understanding
  12. NeurIPS 2025Deep Video Discovery: Agentic Search with Tool Use for Long-form Video Understanding
  13. NeurIPS 2025DeepVideo-R1: Video Reinforcement Fine-Tuning via Difficulty-aware Regressive GRPO
  14. NeurIPS 2025Disentangled Concepts Speak Louder Than Words: Explainable Video Action Recognition
  15. NeurIPS 2025DOVE: Efficient One-Step Diffusion Model for Real-World Video Super-Resolution
  16. NeurIPS 2025Dynamic Shadow Unveils Invisible Semantics for Video Outpainting
  17. NeurIPS 2025Dynamic View Synthesis as an Inverse Problem
  18. NeurIPS 2025DynamicVL: Benchmarking Multimodal Large Language Models for Dynamic City Understanding
  19. NeurIPS 2025EgoExoBench: A Benchmark for First- and Third-person View Video Understanding in MLLMs
  20. NeurIPS 2025EgoExOR: An Ego-Exo-Centric Operating Room Dataset for Surgical Activity Understanding
  21. NeurIPS 2025EgoThinker: Unveiling Egocentric Reasoning with Spatio-Temporal CoT
  22. NeurIPS 2025Emergent Temporal Correspondences from Video Diffusion Transformers
  23. NeurIPS 2025Enhancing Temporal Understanding in Video-LLMs through Stacked Temporal Attention in Vision Encoders
  24. NeurIPS 2025EPFL-Smart-Kitchen: An Ego-Exo Multi-Modal Dataset for Challenging Action and Motion Understanding in Video-Language Models
  25. NeurIPS 2025Event-Guided Consistent Video Enhancement with Modality-Adaptive Diffusion Pipeline
  26. NeurIPS 2025ExAct: A Video-Language Benchmark for Expert Action Analysis
  27. NeurIPS 2025Eyes Wide Open: Ego Proactive Video-LLM for Streaming Video
  28. NeurIPS 2025Face-Human-Bench: A Comprehensive Benchmark of Face and Human Understanding for Multi-modal Assistants
  29. NeurIPS 2025FailureSensorIQ: A Multi-Choice QA Dataset for Understanding Sensor Relationships and Failure Modes
  30. NeurIPS 2025Faster Video Diffusion with Trainable Sparse Attention
  31. NeurIPS 2025FastVID: Dynamic Density Pruning for Fast Video Large Language Models
  32. NeurIPS 2025FAVOR-Bench: A Comprehensive Benchmark for Fine-Grained Video Motion Understanding
  33. NeurIPS 2025FlexSelect: Flexible Token Selection for Efficient Long Video Understanding
  34. NeurIPS 2025Frame Context Packing and Drift Prevention in Next-Frame-Prediction Video Diffusion Models
  35. NeurIPS 2025FrameShield: Adversarially Robust Video Anomaly Detection
  36. NeurIPS 2025Gaze-VLM: Bridging Gaze and VLMs through Attention Regularization for Egocentric Understanding
  37. NeurIPS 2025GEM: Empowering MLLM for Grounded ECG Understanding with Time Series and Images
  38. NeurIPS 2025Generalization or Hallucination? Understanding Out-of-Context Reasoning in Transformers
  39. NeurIPS 2025Generalizing Single-Frame Supervision to Event-Level Understanding for Video Anomaly Detection
  40. NeurIPS 2025HEIR: Learning Graph-Based Motion Hierarchies
  41. NeurIPS 2025HermesFlow: Seamlessly Closing the Gap in Multimodal Understanding and Generation
  42. NeurIPS 2025Holistic Order Prediction in Natural Scenes
  43. NeurIPS 2025HoliTom: Holistic Token Merging for Fast Video Large Language Models
  44. NeurIPS 2025HoloScene: Simulation‑Ready Interactive 3D Worlds from a Single Video
  45. NeurIPS 2025HopaDIFF: Holistic-Partial Aware Fourier Conditioned Diffusion for Referring Human Action Segmentation in Multi-Person Scenarios
  46. NeurIPS 2025iFinder: Structured Zero-Shot Vision-Based LLM Grounding for Dash-Cam Video Reasoning
  47. NeurIPS 2025Imagine360: Immersive 360 Video Generation from Perspective Anchor
  48. NeurIPS 2025Improve Temporal Reasoning in Multimodal Large Language Models via Video Contrastive Decoding
  49. NeurIPS 2025Improving Perturbation-based Explanations by Understanding the Role of Uncertainty Calibration
  50. NeurIPS 2025In the Eye of MLLM: Benchmarking Egocentric Video Intent Understanding with Gaze-Guided Prompting

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