视频理解论文趋势 2023–2026

主要结论

• 视频理解论文从 2023 年的 319 篇增长到 2026 年的 832 篇，三年间扩大到约 2.6 倍。
• CVPR 是发视频理解论文最多的会议，2023–2026 年共 1,037 篇，占四个会议总量的 46%。
• 交叉方向里涨得最快的是扩散模型：同时属于两个主题的论文从 2023 年的 8 篇增至 2026 年的 116 篇。
• 在「计算机视觉」的 5 个主题里，它的 2026 年论文数排第 3；同组增长最快的图像生成是 2.2 倍，视频理解是 2.6 倍。

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

• NeurIPS 2026Articulation in Prime: Primitive-Based Articulated Object Understanding from a Single Casual Video
• ICML 2026A Single Layer to Explain Them All: Understanding Massive Values in Large Language Models
• ICLR 2026Action-Guided Attention for Video Action Anticipation
• CVPR 20264D-RGPT Toward Region-level 4D Understanding via Perceptual Distillation
• NeurIPS 20254DGCPro: Efficient Hierarchical 4D Gaussian Compression for Progressive Volumetric Video Streaming
• ICML 2025$\infty$-Video: A Training-Free Approach to Long Video Understanding via Continuous-Time Memory Consolidation
• ICLR 2025Answer, Assemble, Ace: Understanding How LMs Answer Multiple Choice Questions
• CVPR 20254D-Fly: Fast 4D Reconstruction from a Single Monocular Video
• NeurIPS 2024$E^3$: Exploring Embodied Emotion Through A Large-Scale Egocentric Video Dataset
• ICML 2024Enhancing Sufficient Dimension Reduction via Hellinger Correlation
• ICLR 2024Don't Judge by the Look: Towards Motion Coherent Video Representation
• CVPR 2024Dancing with Still Images: Video Distillation via Static-Dynamic Disentanglement
• NeurIPS 2023A Multi-modal Global Instance Tracking Benchmark (MGIT): Better Locating Target in Complex Spatio-temporal and Causal Relationship
• ICML 2023Dissecting the Effects of SGD Noise in Distinct Regimes of Deep Learning
• ICLR 2023A Theoretical Understanding of Shallow Vision Transformers: Learning, Generalization, and Sample Complexity
• CVPR 20231000 FPS HDR Video With a Spike-RGB Hybrid Camera
• NeurIPS 2026AsymHP: Load-Balanced Sparse Attention for Video Diffusion Transformers
• ICML 2026AnyMod-LLVE: Low-Light Video Enhancement with Modality-Agnostic Inference
• ICLR 2026Emotions Where Art Thou: Understanding and Characterizing the Emotional Latent Space of Large Language Models
• CVPR 2026Accelerating Streaming Video Large Language Models via Hierarchical Token Compression

全部视频理解论文

共 64 篇，第 1 / 2 页

1. ICML 2025$\infty$-Video: A Training-Free Approach to Long Video Understanding via Continuous-Time Memory Consolidation
2. ICML 2025$\mathcal{V}ista\mathcal{DPO}$: Video Hierarchical Spatial-Temporal Direct Preference Optimization for Large Video Models
3. ICML 2025A Closer Look at Transformers for Time Series Forecasting: Understanding Why They Work and Where They Struggle
4. ICML 2025Action Dubber: Timing Audible Actions via Inflectional Flow
5. ICML 2025AffectGPT: A New Dataset, Model, and Benchmark for Emotion Understanding with Multimodal Large Language Models
6. ICML 2025AsymRnR: Video Diffusion Transformers Acceleration with Asymmetric Reduction and Restoration
7. ICML 2025BDC-CLIP: Brownian Distance Covariance for Adapting CLIP to Action Recognition
8. ICML 2025Calibrating Video Watch-time Predictions with Credible Prototype Alignment
9. ICML 2025Compositional Condition Question Answering in Tabular Understanding
10. ICML 2025Compositional Scene Understanding through Inverse Generative Modeling
11. ICML 2025Explanatory Instructions: Towards Unified Vision Tasks Understanding and Zero-shot Generalization
12. ICML 2025HaploVL: A Single-Transformer Baseline for Multi-Modal Understanding
13. ICML 2025Imitation Learning from a Single Temporally Misaligned Video
14. ICML 2025Improving LLM Video Understanding with 16 Frames Per Second
15. ICML 2025Learning Event Completeness for Weakly Supervised Video Anomaly Detection
16. ICML 2025LongVU: Spatiotemporal Adaptive Compression for Long Video-Language Understanding
17. ICML 2025Massive Values in Self-Attention Modules are the Key to Contextual Knowledge Understanding
18. ICML 2025MedXpertQA: Benchmarking Expert-Level Medical Reasoning and Understanding
19. ICML 2025MODA: MOdular Duplex Attention for Multimodal Perception, Cognition, and Emotion Understanding
20. ICML 2025Modularized Self-Reflected Video Reasoner for Multimodal LLM with Application to Video Question Answering
21. ICML 2025MoMa: Modulating Mamba for Adapting Image Foundation Models to Video Recognition
22. ICML 2025On Understanding Attention-Based In-Context Learning for Categorical Data
23. ICML 2025PlaySlot: Learning Inverse Latent Dynamics for Controllable Object-Centric Video Prediction and Planning
24. ICML 2025Position: Deep Learning is Not So Mysterious or Different
25. ICML 2025Position: We Can’t Understand AI Using our Existing Vocabulary
26. ICML 2025Potemkin Understanding in Large Language Models
27. ICML 2025RIFLEx: A Free Lunch for Length Extrapolation in Video Diffusion Transformers
28. ICML 2025Scaling Video-Language Models to 10K Frames via Hierarchical Differential Distillation
29. ICML 2025SpargeAttention: Accurate and Training-free Sparse Attention Accelerating Any Model Inference
30. ICML 2025Sparse Video-Gen: Accelerating Video Diffusion Transformers with Spatial-Temporal Sparsity
31. ICML 2025SpikeVideoFormer: An Efficient Spike-Driven Video Transformer with Hamming Attention and $\mathcal{O}(T)$ Complexity
32. ICML 2025Time to Spike? Understanding the Representational Power of Spiking Neural Networks in Discrete Time
33. ICML 2025Towards Theoretical Understanding of Sequential Decision Making with Preference Feedback
34. ICML 2025Towards Understanding Catastrophic Forgetting in Two-layer Convolutional Neural Networks
35. ICML 2025Towards Understanding Gradient Dynamics of the Sliced-Wasserstein Distance via Critical Point Analysis
36. ICML 2025Towards Understanding Parametric Generalized Category Discovery on Graphs
37. ICML 2025Train for the Worst, Plan for the Best: Understanding Token Ordering in Masked Diffusions
38. ICML 2025TUMTraf VideoQA: Dataset and Benchmark for Unified Spatio-Temporal Video Understanding in Traffic Scenes
39. ICML 2025Understanding and Improving Length Generalization in Recurrent Models
40. ICML 2025Understanding and Mitigating Memorization in Diffusion Models for Tabular Data
41. ICML 2025Understanding and Mitigating Memorization in Generative Models via Sharpness of Probability Landscapes
42. ICML 2025Understanding and Mitigating Miscalibration in Prompt Tuning for Vision-Language Models
43. ICML 2025Understanding Chain-of-Thought in LLMs through Information Theory
44. ICML 2025Understanding Fixed Predictions via Confined Regions
45. ICML 2025Understanding Generalization in Quantum Machine Learning with Margins
46. ICML 2025Understanding High-Dimensional Bayesian Optimization
47. ICML 2025Understanding Input Selectivity in Mamba: Impact on Approximation Power, Memorization, and Associative Recall Capacity
48. ICML 2025Understanding Mode Connectivity via Parameter Space Symmetry
49. ICML 2025Understanding Model Reprogramming for CLIP via Decoupling Visual Prompts
50. ICML 2025Understanding Multimodal LLMs Under Distribution Shifts: An Information-Theoretic Approach

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。