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 95 篇，第 2 / 2 页

51. ICLR 2025Real-Time Video Generation with Pyramid Attention Broadcast
52. ICLR 2025SafeWatch: An Efficient Safety-Policy Following Video Guardrail Model with Transparent Explanations
53. ICLR 2025Scalable Benchmarking and Robust Learning for Noise-Free Ego-Motion and 3D Reconstruction from Noisy Video
54. ICLR 2025See It from My Perspective: How Language Affects Cultural Bias in Image Understanding
55. ICLR 2025Shot2Story: A New Benchmark for Comprehensive Understanding of Multi-shot Videos
56. ICLR 2025Solving Video Inverse Problems Using Image Diffusion Models
57. ICLR 2025Streaming Video Question-Answering with In-context Video KV-Cache Retrieval
58. ICLR 2025Streaming Video Understanding and Multi-round Interaction with Memory-enhanced Knowledge
59. ICLR 2025StringLLM: Understanding the String Processing Capability of Large Language Models
60. ICLR 2025SVBench: A Benchmark with Temporal Multi-Turn Dialogues for Streaming Video Understanding
61. ICLR 2025SVG: 3D Stereoscopic Video Generation via Denoising Frame Matrix
62. ICLR 2025TAU-106K: A New Dataset for Comprehensive Understanding of Traffic Accident
63. ICLR 2025Teaching Human Behavior Improves Content Understanding Abilities Of VLMs
64. ICLR 2025TimeSuite: Improving MLLMs for Long Video Understanding via Grounded Tuning
65. ICLR 2025Topological Blindspots: Understanding and Extending Topological Deep Learning Through the Lens of Expressivity
66. ICLR 2025Toward Understanding In-context vs. In-weight Learning
67. ICLR 2025Towards a Theoretical Understanding of Synthetic Data in LLM Post-Training: A Reverse-Bottleneck Perspective
68. ICLR 2025Towards a Unified and Verified Understanding of Group-Operation Networks
69. ICLR 2025Towards Understanding the Robustness of Diffusion-Based Purification: A Stochastic Perspective
70. ICLR 2025Towards Understanding the Universality of Transformers for Next-Token Prediction
71. ICLR 2025Towards Understanding Why FixMatch Generalizes Better Than Supervised Learning
72. ICLR 2025Towards Understanding Why Label Smoothing Degrades Selective Classification and How to Fix It
73. ICLR 2025TRACE: Temporal Grounding Video LLM via Causal Event Modeling
74. ICLR 2025Understanding and Enhancing the Transferability of Jailbreaking Attacks
75. ICLR 2025Understanding and Mitigating Bottlenecks of State Space Models through the Lens of Recency and Over-smoothing
76. ICLR 2025Understanding and Mitigating Hallucination in Large Vision-Language Models via Modular Attribution and Intervention
77. ICLR 2025Understanding Constraint Inference in Safety-Critical Inverse Reinforcement Learning
78. ICLR 2025Understanding Factual Recall in Transformers via Associative Memories
79. ICLR 2025Understanding Long Videos with Multimodal Language Models
80. ICLR 2025Understanding Matrix Function Normalizations in Covariance Pooling through the Lens of Riemannian Geometry
81. ICLR 2025Understanding Optimization in Deep Learning with Central Flows
82. ICLR 2025Understanding the Generalization of In-Context Learning in Transformers: An Empirical Study
83. ICLR 2025Understanding the Stability-based Generalization of Personalized Federated Learning
84. ICLR 2025Understanding Virtual Nodes: Oversquashing and Node Heterogeneity
85. ICLR 2025Understanding Warmup-Stable-Decay Learning Rates: A River Valley Loss Landscape View
86. ICLR 2025Unhackable Temporal Reward for Scalable Video MLLMs
87. ICLR 2025ViBiDSampler: Enhancing Video Interpolation Using Bidirectional Diffusion Sampler
88. ICLR 2025Video In-context Learning: Autoregressive Transformers are Zero-Shot Video Imitators
89. ICLR 2025Video-STaR: Self-Training Enables Video Instruction Tuning with Any Supervision
90. ICLR 2025VideoGrain: Modulating Space-Time Attention for Multi-Grained Video Editing
91. ICLR 2025VideoWebArena: Evaluating Long Context Multimodal Agents with Video Understanding Web Tasks
92. ICLR 2025Watch Less, Do More: Implicit Skill Discovery for Video-Conditioned Policy
93. ICLR 2025Weakly Supervised Video Scene Graph Generation via Natural Language Supervision
94. ICLR 2025What Secrets Do Your Manifolds Hold? Understanding the Local Geometry of Generative Models
95. ICLR 2025World Model on Million-Length Video And Language With Blockwise RingAttention

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。