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 319 篇，第 5 / 7 页

  1. ICLR 2023Discovering Informative and Robust Positives for Video Domain Adaptation
  2. ICLR 2023Does Deep Learning Learn to Abstract? A Systematic Probing Framework
  3. ICLR 2023Exploring Temporally Dynamic Data Augmentation for Video Recognition
  4. ICLR 2023First Steps Toward Understanding the Extrapolation of Nonlinear Models to Unseen Domains
  5. ICLR 2023GAIN: On the Generalization of Instructional Action Understanding
  6. ICLR 2023ImageNet-X: Understanding Model Mistakes with Factor of Variation Annotations
  7. ICLR 2023Is Attention All That NeRF Needs?
  8. ICLR 2023MaskViT: Masked Visual Pre-Training for Video Prediction
  9. ICLR 2023Maximizing Spatio-Temporal Entropy of Deep 3D CNNs for Efficient Video Recognition
  10. ICLR 2023MIMT: Masked Image Modeling Transformer for Video Compression
  11. ICLR 2023MultiViz: Towards Visualizing and Understanding Multimodal Models
  12. ICLR 2023SQA3D: Situated Question Answering in 3D Scenes
  13. ICLR 2023Temporal Coherent Test Time Optimization for Robust Video Classification
  14. ICLR 2023The Curious Case of Benign Memorization
  15. ICLR 2023The Modality Focusing Hypothesis: Towards Understanding Crossmodal Knowledge Distillation
  16. ICLR 2023Towards a Unified Theoretical Understanding of Non-contrastive Learning via Rank Differential Mechanism
  17. ICLR 2023Towards Smooth Video Composition
  18. ICLR 2023Towards Understanding and Mitigating Dimensional Collapse in Heterogeneous Federated Learning
  19. ICLR 2023Towards Understanding Ensemble, Knowledge Distillation and Self-Distillation in Deep Learning
  20. ICLR 2023Towards Understanding GD with Hard and Conjugate Pseudo-labels for Test-Time Adaptation
  21. ICLR 2023Towards Understanding Why Mask Reconstruction Pretraining Helps in Downstream Tasks
  22. ICLR 2023Understanding and Adopting Rational Behavior by Bellman Score Estimation
  23. ICLR 2023Understanding DDPM Latent Codes Through Optimal Transport
  24. ICLR 2023Understanding Edge-of-Stability Training Dynamics with a Minimalist Example
  25. ICLR 2023Understanding Embodied Reference with Touch-Line Transformer
  26. ICLR 2023Understanding Influence Functions and Datamodels via Harmonic Analysis
  27. ICLR 2023Understanding Neural Coding on Latent Manifolds by Sharing Features and Dividing Ensembles
  28. ICLR 2023Understanding new tasks through the lens of training data via exponential tilting
  29. ICLR 2023Understanding the Covariance Structure of Convolutional Filters
  30. ICLR 2023Understanding the Generalization of Adam in Learning Neural Networks with Proper Regularization
  31. ICLR 2023Understanding The Robustness of Self-supervised Learning Through Topic Modeling
  32. ICLR 2023Understanding the Role of Nonlinearity in Training Dynamics of Contrastive Learning
  33. ICLR 2023Understanding Train-Validation Split in Meta-Learning with Neural Networks
  34. ICLR 2023Understanding weight-magnitude hyperparameters in training binary networks
  35. ICLR 2023Understanding Why Generalized Reweighting Does Not Improve Over ERM
  36. ICLR 2023UNICORN: A Unified Backdoor Trigger Inversion Framework
  37. ICLR 2023Voint Cloud: Multi-View Point Cloud Representation for 3D Understanding
  38. ICLR 2023Your Contrastive Learning Is Secretly Doing Stochastic Neighbor Embedding
  39. ICML 2023A Category-theoretical Meta-analysis of Definitions of Disentanglement
  40. ICML 2023Differentially Private Sharpness-Aware Training
  41. ICML 2023Dissecting the Effects of SGD Noise in Distinct Regimes of Deep Learning
  42. ICML 2023Does Sparsity Help in Learning Misspecified Linear Bandits?
  43. ICML 2023How Do Transformers Learn Topic Structure: Towards a Mechanistic Understanding
  44. ICML 2023Is Overfitting Necessary for Implicit Video Representation?
  45. ICML 2023Learning Control by Iterative Inversion
  46. ICML 2023Long-Term Rhythmic Video Soundtracker
  47. ICML 2023MonoFlow: Rethinking Divergence GANs via the Perspective of Wasserstein Gradient Flows
  48. ICML 2023Open-VCLIP: Transforming CLIP to an Open-vocabulary Video Model via Interpolated Weight Optimization
  49. ICML 2023Pix2Struct: Screenshot Parsing as Pretraining for Visual Language Understanding
  50. ICML 2023Quantifying the Variability Collapse of Neural Networks

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