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 1,037 篇，第 15 / 21 页
- CVPR 2024From Isolated Islands to Pangea: Unifying Semantic Space for Human Action Understanding
- CVPR 2024FutureHuman3D: Forecasting Complex Long-Term 3D Human Behavior from Video Observations
- CVPR 2024GaussianAvatar: Towards Realistic Human Avatar Modeling from a Single Video via Animatable 3D Gaussians
- CVPR 2024GlitchBench: Can Large Multimodal Models Detect Video Game Glitches?
- CVPR 2024GoMAvatar: Efficient Animatable Human Modeling from Monocular Video Using Gaussians-on-Mesh
- CVPR 2024GP-NeRF: Generalized Perception NeRF for Context-Aware 3D Scene Understanding
- CVPR 2024GPT4Point: A Unified Framework for Point-Language Understanding and Generation
- CVPR 2024Grounded Question-Answering in Long Egocentric Videos
- CVPR 2024GroupContrast: Semantic-aware Self-supervised Representation Learning for 3D Understanding
- CVPR 2024GSNeRF: Generalizable Semantic Neural Radiance Fields with Enhanced 3D Scene Understanding
- CVPR 2024Harnessing Large Language Models for Training-free Video Anomaly Detection
- CVPR 2024Harnessing Meta-Learning for Improving Full-Frame Video Stabilization
- CVPR 2024HDRFlow: Real-Time HDR Video Reconstruction with Large Motions
- CVPR 2024HIG: Hierarchical Interlacement Graph Approach to Scene Graph Generation in Video Understanding
- CVPR 2024HOLD: Category-agnostic 3D Reconstruction of Interacting Hands and Objects from Video
- CVPR 2024Holistic Autonomous Driving Understanding by Bird's-Eye-View Injected Multi-Modal Large Models
- CVPR 2024Holistic Features are almost Sufficient for Text-to-Video Retrieval
- CVPR 2024HUGS: Holistic Urban 3D Scene Understanding via Gaussian Splatting
- CVPR 2024HumMUSS: Human Motion Understanding using State Space Models
- CVPR 2024Implicit Motion Function
- CVPR 2024Infer from What You Have Seen Before: Temporally-dependent Classifier for Semi-supervised Video Segmentation
- CVPR 2024Insect-Foundation: A Foundation Model and Large-scale 1M Dataset for Visual Insect Understanding
- CVPR 2024InstructVideo: Instructing Video Diffusion Models with Human Feedback
- CVPR 2024IQ-VFI: Implicit Quadratic Motion Estimation for Video Frame Interpolation
- CVPR 2024Just Add ?! Pose Induced Video Transformers for Understanding Activities of Daily Living
- CVPR 2024Koala: Key Frame-Conditioned Long Video-LLM
- CVPR 2024KVQ: Kwai Video Quality Assessment for Short-form Videos
- CVPR 2024Language Embedded 3D Gaussians for Open-Vocabulary Scene Understanding
- CVPR 2024Language Model Guided Interpretable Video Action Reasoning
- CVPR 2024Language-aware Visual Semantic Distillation for Video Question Answering
- CVPR 2024LayoutFormer: Hierarchical Text Detection Towards Scene Text Understanding
- CVPR 2024Learned Scanpaths Aid Blind Panoramic Video Quality Assessment
- CVPR 2024Learning from One Continuous Video Stream
- CVPR 2024Learning Spatial Adaptation and Temporal Coherence in Diffusion Models for Video Super-Resolution
- CVPR 2024Learning to Predict Activity Progress by Self-Supervised Video Alignment
- CVPR 2024Learning to Select Views for Efficient Multi-View Understanding
- CVPR 2024Leveraging Frame Affinity for sRGB-to-RAW Video De-rendering
- CVPR 2024LL3DA: Visual Interactive Instruction Tuning for Omni-3D Understanding Reasoning and Planning
- CVPR 2024MA-LMM: Memory-Augmented Large Multimodal Model for Long-Term Video Understanding
- CVPR 2024MemSAM: Taming Segment Anything Model for Echocardiography Video Segmentation
- CVPR 2024MMMU: A Massive Multi-discipline Multimodal Understanding and Reasoning Benchmark for Expert AGI
- CVPR 2024Modular Blind Video Quality Assessment
- CVPR 2024MonoHair: High-Fidelity Hair Modeling from a Monocular Video
- CVPR 2024MoReVQA: Exploring Modular Reasoning Models for Video Question Answering
- CVPR 2024MorpheuS: Neural Dynamic 360deg Surface Reconstruction from Monocular RGB-D Video
- CVPR 2024MotionEditor: Editing Video Motion via Content-Aware Diffusion
- CVPR 2024MovieChat: From Dense Token to Sparse Memory for Long Video Understanding
- CVPR 2024Multimodal Pathway: Improve Transformers with Irrelevant Data from Other Modalities
- CVPR 2024MultiPly: Reconstruction of Multiple People from Monocular Video in the Wild
- CVPR 2024MV-Adapter: Multimodal Video Transfer Learning for Video Text Retrieval
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。