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 431 篇，第 1 / 9 页

1. CVPR 2024360+x: A Panoptic Multi-modal Scene Understanding Dataset
2. CVPR 20243D Face Tracking from 2D Video through Iterative Dense UV to Image Flow
3. CVPR 20243D Multi-frame Fusion for Video Stabilization
4. CVPR 20243DInAction: Understanding Human Actions in 3D Point Clouds
5. CVPR 2024A Backpack Full of Skills: Egocentric Video Understanding with Diverse Task Perspectives
6. CVPR 2024A Simple Recipe for Contrastively Pre-training Video-First Encoders Beyond 16 Frames
7. CVPR 2024A Unified Framework for Human-centric Point Cloud Video Understanding
8. CVPR 2024A Video is Worth 256 Bases: Spatial-Temporal Expectation-Maximization Inversion for Zero-Shot Video Editing
9. CVPR 2024Abductive Ego-View Accident Video Understanding for Safe Driving Perception
10. CVPR 2024Action Scene Graphs for Long-Form Understanding of Egocentric Videos
11. CVPR 2024Align Before Adapt: Leveraging Entity-to-Region Alignments for Generalizable Video Action Recognition
12. CVPR 2024Animate Anyone: Consistent and Controllable Image-to-Video Synthesis for Character Animation
13. CVPR 2024AutoAD III: The Prequel - Back to the Pixels
14. CVPR 2024AVID: Any-Length Video Inpainting with Diffusion Model
15. CVPR 2024Binarized Low-light Raw Video Enhancement
16. CVPR 2024Blur-aware Spatio-temporal Sparse Transformer for Video Deblurring
17. CVPR 2024Bootstrapping Chest CT Image Understanding by Distilling Knowledge from X-ray Expert Models
18. CVPR 2024Breathing Life Into Sketches Using Text-to-Video Priors
19. CVPR 2024Bridging the Gap: A Unified Video Comprehension Framework for Moment Retrieval and Highlight Detection
20. CVPR 2024BT-Adapter: Video Conversation is Feasible Without Video Instruction Tuning
21. CVPR 2024C3: High-Performance and Low-Complexity Neural Compression from a Single Image or Video
22. CVPR 2024CAMEL: CAusal Motion Enhancement Tailored for Lifting Text-driven Video Editing
23. CVPR 2024Can I Trust Your Answer? Visually Grounded Video Question Answering
24. CVPR 2024Can't Make an Omelette Without Breaking Some Eggs: Plausible Action Anticipation Using Large Video-Language Models
25. CVPR 2024CCEdit: Creative and Controllable Video Editing via Diffusion Models
26. CVPR 2024Chat-UniVi: Unified Visual Representation Empowers Large Language Models with Image and Video Understanding
27. CVPR 2024CoDeF: Content Deformation Fields for Temporally Consistent Video Processing
28. CVPR 2024COLMAP-Free 3D Gaussian Splatting
29. CVPR 2024Combining Frame and GOP Embeddings for Neural Video Representation
30. CVPR 2024Composed Video Retrieval via Enriched Context and Discriminative Embeddings
31. CVPR 2024Compositional Video Understanding with Spatiotemporal Structure-based Transformers
32. CVPR 2024Context-Guided Spatio-Temporal Video Grounding
33. CVPR 2024Contrasting Intra-Modal and Ranking Cross-Modal Hard Negatives to Enhance Visio-Linguistic Compositional Understanding
34. CVPR 2024CPGA: Coding Priors-Guided Aggregation Network for Compressed Video Quality Enhancement
35. CVPR 2024Cross-view and Cross-pose Completion for 3D Human Understanding
36. CVPR 2024CSTA: CNN-based Spatiotemporal Attention for Video Summarization
37. CVPR 2024Dancing with Still Images: Video Distillation via Static-Dynamic Disentanglement
38. CVPR 2024Decoupling Static and Hierarchical Motion Perception for Referring Video Segmentation
39. CVPR 2024Deep Video Inverse Tone Mapping Based on Temporal Clues
40. CVPR 2024DIBS: Enhancing Dense Video Captioning with Unlabeled Videos via Pseudo Boundary Enrichment and Online Refinement
41. CVPR 2024DiVAS: Video and Audio Synchronization with Dynamic Frame Rates
42. CVPR 2024DriveWorld: 4D Pre-trained Scene Understanding via World Models for Autonomous Driving
43. CVPR 2024DS-NeRV: Implicit Neural Video Representation with Decomposed Static and Dynamic Codes
44. CVPR 2024DyBluRF: Dynamic Neural Radiance Fields from Blurry Monocular Video
45. CVPR 2024DynVideo-E: Harnessing Dynamic NeRF for Large-Scale Motion- and View-Change Human-Centric Video Editing
46. CVPR 2024Dysen-VDM: Empowering Dynamics-aware Text-to-Video Diffusion with LLMs
47. CVPR 2024Effective Video Mirror Detection with Inconsistent Motion Cues
48. CVPR 2024Ego-Exo4D: Understanding Skilled Human Activity from First- and Third-Person Perspectives
49. CVPR 2024End-to-End Spatio-Temporal Action Localisation with Video Transformers
50. CVPR 2024Endow SAM with Keen Eyes: Temporal-spatial Prompt Learning for Video Camouflaged Object Detection

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。