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 1 / 2 页

1. ICLR 2025$F^3Set$: Towards Analyzing Fast, Frequent, and Fine-grained Events from Videos
2. ICLR 2025A Formal Framework for Understanding Length Generalization in Transformers
3. ICLR 2025A Geometric Framework for Understanding Memorization in Generative Models
4. ICLR 2025Answer, Assemble, Ace: Understanding How LMs Answer Multiple Choice Questions
5. ICLR 2025AuroraCap: Efficient, Performant Video Detailed Captioning and a New Benchmark
6. ICLR 2025Autocorrelation Matters: Understanding the Role of Initialization Schemes for State Space Models
7. ICLR 2025CameraCtrl: Enabling Camera Control for Video Diffusion Models
8. ICLR 2025Can Video LLMs Refuse to Answer? Alignment for Answerability in Video Large Language Models
9. ICLR 2025CG-Bench: Clue-grounded Question Answering Benchmark for Long Video Understanding
10. ICLR 2025Compositional 4D Dynamic Scenes Understanding with Physics Priors for Video Question Answering
11. ICLR 2025Contextual Self-paced Learning for Weakly Supervised Spatio-Temporal Video Grounding
12. ICLR 2025DeepRTL: Bridging Verilog Understanding and Generation with a Unified Representation Model
13. ICLR 2025Dense Video Object Captioning from Disjoint Supervision
14. ICLR 2025Do Egocentric Video-Language Models Truly Understand Hand-Object Interactions?
15. ICLR 2025Duoduo CLIP: Efficient 3D Understanding with Multi-View Images
16. ICLR 2025Ferret-UI 2: Mastering Universal User Interface Understanding Across Platforms
17. ICLR 2025Frame-Voyager: Learning to Query Frames for Video Large Language Models
18. ICLR 2025FreqPrior: Improving Video Diffusion Models with Frequency Filtering Gaussian Noise
19. ICLR 2025Generalized Video Moment Retrieval
20. ICLR 2025GenEx: Generating an Explorable World
21. ICLR 2025Going Beyond Static: Understanding Shifts with Time-Series Attribution
22. ICLR 2025Grounding Video Models to Actions through Goal Conditioned Exploration
23. ICLR 2025GUI-World: A Video Benchmark and Dataset for Multimodal GUI-oriented Understanding
24. ICLR 2025Harnessing Webpage UIs for Text-Rich Visual Understanding
25. ICLR 2025I2VControl-Camera: Precise Video Camera Control with Adjustable Motion Strength
26. ICLR 2025IDA-VLM: Towards Movie Understanding via ID-Aware Large Vision-Language Model
27. ICLR 2025INCLUDE: Evaluating Multilingual Language Understanding with Regional Knowledge
28. ICLR 2025Is Your Video Language Model a Reliable Judge?
29. ICLR 2025Kronecker Mask and Interpretive Prompts are Language-Action Video Learners
30. ICLR 2025Language-Image Models with 3D Understanding
31. ICLR 2025LASER: A Neuro-Symbolic Framework for Learning Spatio-Temporal Scene Graphs with Weak Supervision
32. ICLR 2025Learning Fine-Grained Representations through Textual Token Disentanglement in Composed Video Retrieval
33. ICLR 2025Learning Video-Conditioned Policy on Unlabelled Data with Joint Embedding Predictive Transformer
34. ICLR 2025Let Your Features Tell The Differences: Understanding Graph Convolution By Feature Splitting
35. ICLR 2025Linear Mode Connectivity in Differentiable Tree Ensembles
36. ICLR 2025LongVILA: Scaling Long-Context Visual Language Models for Long Videos
37. ICLR 2025Looking Backward: Streaming Video-to-Video Translation with Feature Banks
38. ICLR 2025MMEgo: Towards Building Egocentric Multimodal LLMs for Video QA
39. ICLR 2025MMIU: Multimodal Multi-image Understanding for Evaluating Large Vision-Language Models
40. ICLR 2025MMWorld: Towards Multi-discipline Multi-faceted World Model Evaluation in Videos
41. ICLR 2025Modeling Fine-Grained Hand-Object Dynamics for Egocentric Video Representation Learning
42. ICLR 2025mPLUG-Owl3: Towards Long Image-Sequence Understanding in Multi-Modal Large Language Models
43. ICLR 2025MuirBench: A Comprehensive Benchmark for Robust Multi-image Understanding
44. ICLR 2025Needle In A Video Haystack: A Scalable Synthetic Evaluator for Video MLLMs
45. ICLR 2025NVS-Solver: Video Diffusion Model as Zero-Shot Novel View Synthesizer
46. ICLR 2025One Hundred Neural Networks and Brains Watching Videos: Lessons from Alignment
47. ICLR 2025Oryx MLLM: On-Demand Spatial-Temporal Understanding at Arbitrary Resolution
48. ICLR 2025PooDLe🐩: Pooled and dense self-supervised learning from naturalistic videos
49. ICLR 2025Proximal Mapping Loss: Understanding Loss Functions in Crowd Counting & Localization
50. ICLR 2025PvNeXt: Rethinking Network Design and Temporal Motion for Point Cloud Video Recognition

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。