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 113 篇，第 2 / 3 页

51. NeurIPS 2024Micro-Bench: A Microscopy Benchmark for Vision-Language Understanding
52. NeurIPS 2024MMBench-Video: A Long-Form Multi-Shot Benchmark for Holistic Video Understanding
53. NeurIPS 2024MoTE: Reconciling Generalization with Specialization for Visual-Language to Video Knowledge Transfer
54. NeurIPS 2024Motion Graph Unleashed: A Novel Approach to Video Prediction
55. NeurIPS 2024Moving Off-the-Grid: Scene-Grounded Video Representations
56. NeurIPS 2024Multiview Scene Graph
57. NeurIPS 2024NeuroClips: Towards High-fidelity and Smooth fMRI-to-Video Reconstruction
58. NeurIPS 2024NVRC: Neural Video Representation Compression
59. NeurIPS 2024Octopus: A Multi-modal LLM with Parallel Recognition and Sequential Understanding
60. NeurIPS 2024OMG-LLaVA: Bridging Image-level, Object-level, Pixel-level Reasoning and Understanding
61. NeurIPS 2024On Learning Multi-Modal Forgery Representation for Diffusion Generated Video Detection
62. NeurIPS 2024OnlineTAS: An Online Baseline for Temporal Action Segmentation
63. NeurIPS 2024OW-VISCapTor: Abstractors for Open-World Video Instance Segmentation and Captioning
64. NeurIPS 2024Precipitation Downscaling with Spatiotemporal Video Diffusion
65. NeurIPS 2024Procedure-Aware Surgical Video-language Pretraining with Hierarchical Knowledge Augmentation
66. NeurIPS 2024ReVideo: Remake a Video with Motion and Content Control
67. NeurIPS 2024Revisiting, Benchmarking and Understanding Unsupervised Graph Domain Adaptation
68. NeurIPS 2024ReXTime: A Benchmark Suite for Reasoning-Across-Time in Videos
69. NeurIPS 2024SeeClear: Semantic Distillation Enhances Pixel Condensation for Video Super-Resolution
70. NeurIPS 2024ShareGPT4Video: Improving Video Understanding and Generation with Better Captions
71. NeurIPS 2024Sharpness-Aware Minimization Activates the Interactive Teaching's Understanding and Optimization
72. NeurIPS 2024SILENCE: Protecting privacy in offloaded speech understanding on resource-constrained devices
73. NeurIPS 2024Slot State Space Models
74. NeurIPS 2024Slot-VLM: Object-Event Slots for Video-Language Modeling
75. NeurIPS 2024SlowFocus: Enhancing Fine-grained Temporal Understanding in Video LLM
76. NeurIPS 2024Splatter a Video: Video Gaussian Representation for Versatile Processing
77. NeurIPS 2024Streaming Detection of Queried Event Start
78. NeurIPS 2024Streaming Long Video Understanding with Large Language Models
79. NeurIPS 2024SyncVIS: Synchronized Video Instance Segmentation
80. NeurIPS 2024Talking Heads: Understanding Inter-Layer Communication in Transformer Language Models
81. NeurIPS 2024TAPVid-3D: A Benchmark for Tracking Any Point in 3D
82. NeurIPS 2024The Importance of Online Data: Understanding Preference Fine-tuning via Coverage
83. NeurIPS 2024TopoFR: A Closer Look at Topology Alignment on Face Recognition
84. NeurIPS 2024Towards a Theoretical Understanding of the 'Reversal Curse' via Training Dynamics
85. NeurIPS 2024Towards Understanding Evolving Patterns in Sequential Data
86. NeurIPS 2024Towards Understanding Extrapolation: a Causal Lens
87. NeurIPS 2024Towards Understanding How Transformers Learn In-context Through a Representation Learning Lens
88. NeurIPS 2024TrackIME: Enhanced Video Point Tracking via Instance Motion Estimation
89. NeurIPS 2024Understanding and Improving Adversarial Collaborative Filtering for Robust Recommendation
90. NeurIPS 2024Understanding and Minimising Outlier Features in Transformer Training
91. NeurIPS 2024Understanding Bias in Large-Scale Visual Datasets
92. NeurIPS 2024Understanding Emergent Abilities of Language Models from the Loss Perspective
93. NeurIPS 2024Understanding Generalizability of Diffusion Models Requires Rethinking the Hidden Gaussian Structure
94. NeurIPS 2024Understanding Hallucinations in Diffusion Models through Mode Interpolation
95. NeurIPS 2024Understanding Representation of Deep Equilibrium Models from Neural Collapse Perspective
96. NeurIPS 2024Understanding Scaling Laws with Statistical and Approximation Theory for Transformer Neural Networks on Intrinsically Low-dimensional Data
97. NeurIPS 2024Understanding the Differences in Foundation Models: Attention, State Space Models, and Recurrent Neural Networks
98. NeurIPS 2024Understanding the Expressive Power and Mechanisms of Transformer for Sequence Modeling
99. NeurIPS 2024Understanding the Expressivity and Trainability of Fourier Neural Operator: A Mean-Field Perspective
100. NeurIPS 2024Understanding the Gains from Repeated Self-Distillation

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。