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 431 篇，第 7 / 9 页

  1. ICML 2024Understanding Finetuning for Factual Knowledge Extraction
  2. ICML 2024Understanding Forgetting in Continual Learning with Linear Regression
  3. ICML 2024Understanding Heterophily for Graph Neural Networks
  4. ICML 2024Understanding Inter-Concept Relationships in Concept-Based Models
  5. ICML 2024Understanding MLP-Mixer as a wide and sparse MLP
  6. ICML 2024Understanding Reasoning Ability of Language Models From the Perspective of Reasoning Paths Aggregation
  7. ICML 2024Understanding Server-Assisted Federated Learning in the Presence of Incomplete Client Participation
  8. ICML 2024Understanding Stochastic Natural Gradient Variational Inference
  9. ICML 2024Understanding the Effects of Iterative Prompting on Truthfulness
  10. ICML 2024Understanding the Impact of Introducing Constraints at Inference Time on Generalization Error
  11. ICML 2024Understanding the Learning Dynamics of Alignment with Human Feedback
  12. ICML 2024Understanding the Training Speedup from Sampling with Approximate Losses
  13. ICML 2024Understanding Unimodal Bias in Multimodal Deep Linear Networks
  14. ICML 2024Video-LaVIT: Unified Video-Language Pre-training with Decoupled Visual-Motional Tokenization
  15. ICML 2024Video-of-Thought: Step-by-Step Video Reasoning from Perception to Cognition
  16. ICML 2024VideoPrism: A Foundational Visual Encoder for Video Understanding
  17. ICML 2024Weisfeiler-Leman at the margin: When more expressivity matters
  18. ICML 2024Why Larger Language Models Do In-context Learning Differently?
  19. NeurIPS 2024$E^3$: Exploring Embodied Emotion Through A Large-Scale Egocentric Video Dataset
  20. NeurIPS 20243DCoMPaT200: Language Grounded Large-Scale 3D Vision Dataset for Compositional Recognition
  21. NeurIPS 2024A Theoretical Understanding of Self-Correction through In-context Alignment
  22. NeurIPS 2024ActionAtlas: A VideoQA Benchmark for Domain-specialized Action Recognition
  23. NeurIPS 2024Advancing Video Anomaly Detection: A Concise Review and a New Dataset
  24. NeurIPS 2024Animal-Bench: Benchmarking Multimodal Video Models for Animal-centric Video Understanding
  25. NeurIPS 2024Artemis: Towards Referential Understanding in Complex Videos
  26. NeurIPS 2024AverNet: All-in-one Video Restoration for Time-varying Unknown Degradations
  27. NeurIPS 2024Beyond Euclidean: Dual-Space Representation Learning for Weakly Supervised Video Violence Detection
  28. NeurIPS 2024bit2bit: 1-bit quanta video reconstruction via self-supervised photon prediction
  29. NeurIPS 2024CALVIN: Improved Contextual Video Captioning via Instruction Tuning
  30. NeurIPS 2024CaptainCook4D: A Dataset for Understanding Errors in Procedural Activities
  31. NeurIPS 2024CharXiv: Charting Gaps in Realistic Chart Understanding in Multimodal LLMs
  32. NeurIPS 2024Chat-Scene: Bridging 3D Scene and Large Language Models with Object Identifiers
  33. NeurIPS 2024Cross-video Identity Correlating for Person Re-identification Pre-training
  34. NeurIPS 2024CulturePark: Boosting Cross-cultural Understanding in Large Language Models
  35. NeurIPS 2024Differentiable Task Graph Learning: Procedural Activity Representation and Online Mistake Detection from Egocentric Videos
  36. NeurIPS 2024Don't Look Twice: Faster Video Transformers with Run-Length Tokenization
  37. NeurIPS 2024E.T. Bench: Towards Open-Ended Event-Level Video-Language Understanding
  38. NeurIPS 2024End-to-End Video Semantic Segmentation in Adverse Weather using Fusion Blocks and Temporal-Spatial Teacher-Student Learning
  39. NeurIPS 2024Estimating Ego-Body Pose from Doubly Sparse Egocentric Video Data
  40. NeurIPS 2024Expressive Gaussian Human Avatars from Monocular RGB Video
  41. NeurIPS 2024Extending Video Masked Autoencoders to 128 frames
  42. NeurIPS 2024Fast and Memory-Efficient Video Diffusion Using Streamlined Inference
  43. NeurIPS 2024FineCLIP: Self-distilled Region-based CLIP for Better Fine-grained Understanding
  44. NeurIPS 2024Flow Snapshot Neurons in Action: Deep Neural Networks Generalize to Biological Motion Perception
  45. NeurIPS 2024Fourier Amplitude and Correlation Loss: Beyond Using L2 Loss for Skillful Precipitation Nowcasting
  46. NeurIPS 2024Frozen-DETR: Enhancing DETR with Image Understanding from Frozen Foundation Models
  47. NeurIPS 2024FUSU: A Multi-temporal-source Land Use Change Segmentation Dataset for Fine-grained Urban Semantic Understanding
  48. NeurIPS 2024Generalizable Implicit Motion Modeling for Video Frame Interpolation
  49. NeurIPS 2024Generalized Tensor Decomposition for Understanding Multi-Output Regression under Combinatorial Shifts
  50. NeurIPS 2024GenRec: Unifying Video Generation and Recognition with Diffusion Models

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