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 114 篇，第 1 / 3 页

1. ICML 20263DPoV: Improving 3D understanding via Patch Ordering on Videos
2. ICML 20264DPC$^2$hat: Towards Dynamic Point Cloud Understanding with Failure-Aware Bootstrapping
3. ICML 2026A Fine-Grained Understanding of Uniform Convergence for Halfspaces
4. ICML 2026A Single Layer to Explain Them All: Understanding Massive Values in Large Language Models
5. ICML 2026ActiveScope: Actively Seeking and Correcting Perception for MLLMs
6. ICML 2026AnyMod-LLVE: Low-Light Video Enhancement with Modality-Agnostic Inference
7. ICML 2026Benchmarking and Enhancing VLM for Compressed Image Understanding
8. ICML 2026CE$^4$L: Continual Ego, Exo, and Ego-Exo Learning
9. ICML 2026Chain-of-Glimpse: Search-Guided Progressive Object-Grounded Reasoning for Video Understanding
10. ICML 2026CombinationTS: A Modular Framework for Understanding Time-Series Forecasting Models
11. ICML 2026CURVE: Learning Causality-Inspired Invariant Representations for Robust Scene Understanding via Uncertainty-Guided Regularization
12. ICML 2026Decouple and Cache: KV Cache Construction for Streaming Video Understanding
13. ICML 2026Deep Forcing: Training-Free Long Video Generation with Deep Sink and Participative Compression
14. ICML 2026DOUBT: Decoupled Object-level Understanding and Bridging via vMF-based Trustworthiness for Hallucination Detection in MLLMs
15. ICML 2026DRFusion: Drift-Resilient Temporally Consistent Infrared–Visible Video Fusion
16. ICML 2026EAKV: An Entropy-Driven Adaptive KV Compression Framework for Long Video Understanding
17. ICML 2026EchoAttention: Exploiting Token-Pair Redundancy and Frame-Block Similarity for Efficient Video Generation
18. ICML 2026EgoTactile: Learning Grasp Pressure for Everyday Objects from Egocentric Video
19. ICML 2026Eigenvectors of Experts are Training-free Non-collapsing Routers
20. ICML 2026Explainable Forensics of Manipulated Segments in Untrimmed Long Videos
21. ICML 2026Flex-Forcing: Towards a Unified Autoregressive and Bidirectional Video Diffusion Model
22. ICML 2026FlowNar: Scalable Streaming Narration for Long-Form Videos
23. ICML 2026Foreground-Aware Token Routing Vision Transformer for Real-Time Satellite Video Tracking
24. ICML 2026FrameOracle: Learning What to See and How Much to See in Videos
25. ICML 2026From Content to Knowledge: Lightning Fast Long-Video Understanding with Neural Knowledge Representations
26. ICML 2026From Denoising to De-Channeling: Integrating Physical Channel Priors into Diffusion Models for Radio Signal Understanding
27. ICML 2026GemDepth: Geometry-Embedded Features for 3D-Consistent Video Depth
28. ICML 2026Gradient Descent as a Perceptron Algorithm: Understanding Dynamics and Implicit Acceleration
29. ICML 2026IDRBench: Understanding the Capability of Large Language Models on Interdisciplinary Research
30. ICML 2026ImmersePro: End-to-End Stereo Video Synthesis Via Implicit Disparity Learning
31. ICML 2026Is One Layer Enough? Understanding Inference Dynamics in Tabular Foundation Models
32. ICML 2026Keep It in Mind: User Centric Continual Spatial Intelligence Reasoning in Egocentric Video Streams
33. ICML 2026Learning Flexible Generalization in Video Quality Assessment by Bringing Device and Viewing Condition Distributions
34. ICML 2026Learning Latent Action World Models in the Wild
35. ICML 2026Learning to Decode Against Compositional Hallucination in Video Multimodal Large Language Models
36. ICML 2026Learning to Watch: Active Video Anomaly Understanding via Interleaved Policy Optimization
37. ICML 2026Light Forcing: Accelerating Autoregressive Video Diffusion via Sparse Attention
38. ICML 2026LIVEditor-14B: Lightning Unified Video Editing via In-Context Sparse Attention
39. ICML 2026LMM4-IC4K: A Large Multimodal Model Powered Integrated Circuit Footprint Geometry Understanding
40. ICML 2026LSGQuant: Layer-Sensitivity Guided Quantization for One-Step Diffusion Real-World Video Super-Resolution
41. ICML 2026MACD: Model-Aware Contrastive Decoding via Counterfactual Data for Video-LLMs
42. ICML 2026MetaphorVU: Towards Metaphorical Video Understanding
43. ICML 2026Mitigating Surgical Data Imbalance with Dual-Prediction Video Diffusion Model
44. ICML 2026More Edits, More Stable: Understanding the Lifelong Normalization in Sequential Model Editing
45. ICML 2026MUSE: Resolving Manifold Misalignment in Visual Tokenization via Topological Orthogonality
46. ICML 2026Orthogonal Hierarchical Decomposition for Structure-Aware Table Understanding with Large Language Models
47. ICML 2026PanoWorld-X: Generating Explorable Panoramic Worlds via Sphere-Aware Video Diffusion
48. ICML 2026Per-example Gradients: a New Frontier for Understanding and Improving Optimizers
49. ICML 2026Physics from Video: Identifiability of Time-Invariant Second-Order ODEs under Minimal Trajectory Conditions
50. ICML 2026Positive Distribution Shift as a Framework for Understanding Tractable Learning

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。