视频理解论文趋势 2023–2026
视频识别与理解
统计范围：NeurIPS、ICLR、ICML、CVPR 四个会议，2023–2026 年，共 2,261 篇被归入该主题的论文。
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。
各会议论文数
按年份和会议统计
| 年份 | NeurIPS | ICLR | ICML | CVPR | 合计 |
|---|---|---|---|---|---|
| 2023 | 47 | 44 | 34 | 194 | 319 |
| 2024 | 113 | 47 | 67 | 204 | 431 |
| 2025 | 222 | 95 | 64 | 298 | 679 |
| 2026 | 229 | 148 | 114 | 341 | 832 |
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 2,261 篇，第 23 / 46 页
- CVPR 2025ViCaS: A Dataset for Combining Holistic and Pixel-level Video Understanding using Captions with Grounded Segmentation
- CVPR 2025Vid2Avatar-Pro: Authentic Avatar from Videos in the Wild via Universal Prior
- CVPR 2025VidComposition: Can MLLMs Analyze Compositions in Compiled Videos?
- CVPR 2025Video Depth Anything: Consistent Depth Estimation for Super-Long Videos
- CVPR 2025Video Depth without Video Models
- CVPR 2025Video Language Model Pretraining with Spatio-temporal Masking
- CVPR 2025Video Motion Transfer with Diffusion Transformers
- CVPR 2025Video Summarization with Large Language Models
- CVPR 2025Video-3D LLM: Learning Position-Aware Video Representation for 3D Scene Understanding
- CVPR 2025Video-Bench: Human-Aligned Video Generation Benchmark
- CVPR 2025Video-MME: The First-Ever Comprehensive Evaluation Benchmark of Multi-modal LLMs in Video Analysis
- CVPR 2025Video-Panda: Parameter-efficient Alignment for Encoder-free Video-Language Models
- CVPR 2025Video-XL: Extra-Long Vision Language Model for Hour-Scale Video Understanding
- CVPR 2025VideoEspresso: A Large-Scale Chain-of-Thought Dataset for Fine-Grained Video Reasoning via Core Frame Selection
- CVPR 2025VideoGigaGAN: Towards Detail-rich Video Super-Resolution
- CVPR 2025VideoGuide: Improving Video Diffusion Models without Training Through a Teacher's Guide
- CVPR 2025VideoICL: Confidence-based Iterative In-context Learning for Out-of-Distribution Video Understanding
- CVPR 2025VideoMage: Multi-Subject and Motion Customization of Text-to-Video Diffusion Models
- CVPR 2025VideoRefer Suite: Advancing Spatial-Temporal Object Understanding with Video LLM
- CVPR 2025VideoScene: Distilling Video Diffusion Model to Generate 3D Scenes in One Step
- CVPR 2025VideoSPatS: Video SPatiotemporal Splines for Disentangled Occlusion, Appearance and Motion Modeling and Editing
- CVPR 2025VideoTree: Adaptive Tree-based Video Representation for LLM Reasoning on Long Videos
- CVPR 2025VidHalluc: Evaluating Temporal Hallucinations in Multimodal Large Language Models for Video Understanding
- CVPR 2025VidSeg: Training-free Video Semantic Segmentation based on Diffusion Models
- CVPR 2025VidTwin: Video VAE with Decoupled Structure and Dynamics
- CVPR 2025VISTA: Enhancing Long-Duration and High-Resolution Video Understanding by Video Spatiotemporal Augmentation
- CVPR 2025VITED: Video Temporal Evidence Distillation
- CVPR 2025VLog: Video-Language Models by Generative Retrieval of Narration Vocabulary
- CVPR 2025VSNet: Focusing on the Linguistic Characteristics of Sign Language
- CVPR 2025WF-VAE: Enhancing Video VAE by Wavelet-Driven Energy Flow for Latent Video Diffusion Model
- ICLR 2025$F^3Set$: Towards Analyzing Fast, Frequent, and Fine-grained Events from Videos
- ICLR 2025A Formal Framework for Understanding Length Generalization in Transformers
- ICLR 2025A Geometric Framework for Understanding Memorization in Generative Models
- ICLR 2025Answer, Assemble, Ace: Understanding How LMs Answer Multiple Choice Questions
- ICLR 2025AuroraCap: Efficient, Performant Video Detailed Captioning and a New Benchmark
- ICLR 2025Autocorrelation Matters: Understanding the Role of Initialization Schemes for State Space Models
- ICLR 2025CameraCtrl: Enabling Camera Control for Video Diffusion Models
- ICLR 2025Can Video LLMs Refuse to Answer? Alignment for Answerability in Video Large Language Models
- ICLR 2025CG-Bench: Clue-grounded Question Answering Benchmark for Long Video Understanding
- ICLR 2025Compositional 4D Dynamic Scenes Understanding with Physics Priors for Video Question Answering
- ICLR 2025Contextual Self-paced Learning for Weakly Supervised Spatio-Temporal Video Grounding
- ICLR 2025DeepRTL: Bridging Verilog Understanding and Generation with a Unified Representation Model
- ICLR 2025Dense Video Object Captioning from Disjoint Supervision
- ICLR 2025Do Egocentric Video-Language Models Truly Understand Hand-Object Interactions?
- ICLR 2025Duoduo CLIP: Efficient 3D Understanding with Multi-View Images
- ICLR 2025Ferret-UI 2: Mastering Universal User Interface Understanding Across Platforms
- ICLR 2025Frame-Voyager: Learning to Query Frames for Video Large Language Models
- ICLR 2025FreqPrior: Improving Video Diffusion Models with Frequency Filtering Gaussian Noise
- ICLR 2025Generalized Video Moment Retrieval
- ICLR 2025GenEx: Generating an Explorable World
在 Claude、Cursor 里直接问这个趋势
接上 Paperlist MCP 后，写综述、挑方向或准备投稿时，不用离开对话框就能拿到这页的数字：每年各会议的论文数、增长倍数、涨得最快的子方向和代表论文，AI 会按你的问题整理。
可以直接复制这句话问 AI
用 paperlist 查视频理解在 CVPR 2023–2026 的论文趋势，哪一年涨得最快？
AI 会调用的工具：get_topic_stats {"topic": "video-understanding"}
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。