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 148 篇，第 1 / 3 页

1. ICLR 2026<SO$G_k$>: One LLM Token for Explicit Graph Structural Understanding
2. ICLR 2026A Training-Free Framework for Long Video Understanding via Video-Query-Options Similarity
3. ICLR 2026A.I.R.: Enabling Adaptive, Iterative, and Reasoning-based Frame Selection For Video Question Answering
4. ICLR 2026Action-Guided Attention for Video Action Anticipation
5. ICLR 2026Advancing Complex Video Object Segmentation via Progressive Concept Construction
6. ICLR 2026AFD-INSTRUCTION: A Comprehensive Antibody Instruction Dataset with Functional Annotations for LLM-Based Understanding and Design
7. ICLR 2026AlphaFlow: Understanding and Improving MeanFlow Models
8. ICLR 2026BAH Dataset for Ambivalence/Hesitancy Recognition in Videos for Behavioural Change
9. ICLR 2026BANZ-FS: BANZSL Fingerspelling Dataset
10. ICLR 2026Barriers for Learning in an Evolving World: Mathematical Understanding of Loss of Plasticity
11. ICLR 2026Beyond Static Vision: Scene Dynamic Field Unlocks Intuitive Physics Understanding in Multi-modal Large Language Models
12. ICLR 2026Boosting Medical Visual Understanding From Multi-Granular Language Learning
13. ICLR 2026BWCache: Accelerating Video Diffusion Transformers through Block-Wise Caching
14. ICLR 2026CaReBench: A Fine-grained Benchmark for Video Captioning and Retrieval
15. ICLR 2026Concept-TRAK: Understanding how diffusion models learn concepts through concept attribution
16. ICLR 2026Context Tokens are Anchors: Understanding the Repetition Curse in Diffusion MLLMs from an Information Flow Perspective
17. ICLR 2026Controllable Video Generation with Provable Disentanglement
18. ICLR 2026Cosmos Policy: Fine-Tuning Video Models for Visuomotor Control and Planning
19. ICLR 2026DanceTogether: Generating Interactive Multi-Person Video without Identity Drifting
20. ICLR 2026Decomposed Attention Fusion in MLLMs for Training-free Video Reasoning Segmentation
21. ICLR 2026Deforming Videos to Masks: Flow Matching for Referring Video Segmentation
22. ICLR 2026Divid: Disentangled Spatial-Temporal Modeling within LLMs for Temporally Grounded Video Understanding
23. ICLR 2026Dynamic Reflections: Probing Video Representations with Text Alignment
24. ICLR 2026EasyCreator: Empowering 4D Creation through Video Inpainting
25. ICLR 2026EchoMotion: Unified Human Video and Motion Generation via Dual-Modality Diffusion Transformer
26. ICLR 2026EgoDex: Learning Dexterous Manipulation from Large-Scale Egocentric Video
27. ICLR 2026EmotionHallucer: Evaluating Emotion Hallucinations in Multimodal Large Language Models
28. ICLR 2026Emotions Where Art Thou: Understanding and Characterizing the Emotional Latent Space of Large Language Models
29. ICLR 2026Enhancing Visual Token Representations for Video Large Language Models via Training-free Spatial-Temporal Pooling and Gridding
30. ICLR 2026Evaluating Intuitive Physics Understanding in Video Diffusion Models via Likelihood Preference
31. ICLR 2026Exploring the Potential of Encoder-free Architectures in 3D LMMs
32. ICLR 2026ExpVid: A Benchmark for Experiment Video Understanding & Reasoning
33. ICLR 2026FastVMT: Eliminating Redundancy in Video Motion Transfer
34. ICLR 2026FlashVID: Efficient Video Large Language Models via Training-free Tree-based Spatiotemporal Token Merging
35. ICLR 2026FLoC: Facility Location-Based Efficient Visual Token Compression for Long Video Understanding
36. ICLR 2026FlowNIB: An Information Bottleneck Analysis of Bidirectional vs. Unidirectional Language Models
37. ICLR 2026FOCUS: Efficient Keyframe Selection for Long Video Understanding
38. ICLR 2026Frame Guidance: Training-Free Guidance for Frame-Level Control in Video Diffusion Model
39. ICLR 2026FreeViS: Training-free Video Stylization with Inconsistent References
40. ICLR 2026From Collapse to Control: Understanding and Extending Context Length in Emerging Hybrid Models via Universal Position Interpolation
41. ICLR 2026GenCompositor: Generative Video Compositing with Diffusion Transformer
42. ICLR 2026Geometry-aware 4D Video Generation for Robot Manipulation
43. ICLR 2026Gistify: Codebase-Level Understanding via Runtime Execution
44. ICLR 2026HFSTI-Net: Hierarchical Frequency-spatial-temporal Interactions for Video Polyp Segmentation
45. ICLR 2026HiTeA: Hierarchical Temporal Alignment for Training-Free Long-Video Temporal Grounding
46. ICLR 2026IF-VidCap: Can Video Caption Models Follow Instructions?
47. ICLR 2026Improving Autoregressive Video Modeling with History Understanding
48. ICLR 2026InclusiveVidPose: Bridging the Pose Estimation Gap for Individuals with Limb Deficiencies in Video-Based Motion
49. ICLR 2026InfoTok: Adaptive Discrete Video Tokenizer via Information-Theoretic Compression
50. ICLR 2026Invert4TVG: A Temporal Video Grounding Framework with Inversion Tasks Preserving Action Understanding Ability

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。