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 18 / 21 页
- CVPR 2023A Unified Pyramid Recurrent Network for Video Frame Interpolation
- CVPR 2023Affordance Grounding From Demonstration Video To Target Image
- CVPR 2023Aligning Step-by-Step Instructional Diagrams to Video Demonstrations
- CVPR 2023All in One: Exploring Unified Video-Language Pre-Training
- CVPR 2023An Empirical Study of End-to-End Video-Language Transformers With Masked Visual Modeling
- CVPR 2023An In-Depth Exploration of Person Re-Identification and Gait Recognition in Cloth-Changing Conditions
- CVPR 2023Are Binary Annotations Sufficient? Video Moment Retrieval via Hierarchical Uncertainty-Based Active Learning
- CVPR 2023AssemblyHands: Towards Egocentric Activity Understanding via 3D Hand Pose Estimation
- CVPR 2023Bidirectional Cross-Modal Knowledge Exploration for Video Recognition With Pre-Trained Vision-Language Models
- CVPR 2023BiFormer: Learning Bilateral Motion Estimation via Bilateral Transformer for 4K Video Frame Interpolation
- CVPR 2023Blind Video Deflickering by Neural Filtering With a Flawed Atlas
- CVPR 2023Boosting Video Object Segmentation via Space-Time Correspondence Learning
- CVPR 2023Breaking the "Object" in Video Object Segmentation
- CVPR 2023Cap4Video: What Can Auxiliary Captions Do for Text-Video Retrieval?
- CVPR 2023CelebV-Text: A Large-Scale Facial Text-Video Dataset
- CVPR 2023CLIP2Scene: Towards Label-Efficient 3D Scene Understanding by CLIP
- CVPR 2023CLIPPING: Distilling CLIP-Based Models With a Student Base for Video-Language Retrieval
- CVPR 2023CLIPPO: Image-and-Language Understanding From Pixels Only
- CVPR 2023Clover: Towards a Unified Video-Language Alignment and Fusion Model
- CVPR 2023CNVid-3.5M: Build, Filter, and Pre-Train the Large-Scale Public Chinese Video-Text Dataset
- CVPR 2023Collaborative Static and Dynamic Vision-Language Streams for Spatio-Temporal Video Grounding
- CVPR 2023Command-Driven Articulated Object Understanding and Manipulation
- CVPR 2023Complexity-Guided Slimmable Decoder for Efficient Deep Video Compression
- CVPR 2023Compression-Aware Video Super-Resolution
- CVPR 2023Connecting Vision and Language With Video Localized Narratives
- CVPR 2023Consistent Direct Time-of-Flight Video Depth Super-Resolution
- CVPR 2023Context-Aware Relative Object Queries To Unify Video Instance and Panoptic Segmentation
- CVPR 2023Continuous Sign Language Recognition With Correlation Network
- CVPR 2023Deep Discriminative Spatial and Temporal Network for Efficient Video Deblurring
- CVPR 2023Deep Stereo Video Inpainting
- CVPR 2023DPE: Disentanglement of Pose and Expression for General Video Portrait Editing
- CVPR 2023Dual-Path Adaptation From Image to Video Transformers
- CVPR 2023Dynamic Aggregated Network for Gait Recognition
- CVPR 2023EfficientSCI: Densely Connected Network With Space-Time Factorization for Large-Scale Video Snapshot Compressive Imaging
- CVPR 2023Ego-Body Pose Estimation via Ego-Head Pose Estimation
- CVPR 2023Egocentric Video Task Translation
- CVPR 2023End-to-End Video Matting With Trimap Propagation
- CVPR 2023Enlarging Instance-Specific and Class-Specific Information for Open-Set Action Recognition
- CVPR 2023EVAL: Explainable Video Anomaly Localization
- CVPR 2023Event-Based Video Frame Interpolation With Cross-Modal Asymmetric Bidirectional Motion Fields
- CVPR 2023Exploiting Completeness and Uncertainty of Pseudo Labels for Weakly Supervised Video Anomaly Detection
- CVPR 2023Exploring Discontinuity for Video Frame Interpolation
- CVPR 2023Exploring Motion Ambiguity and Alignment for High-Quality Video Frame Interpolation
- CVPR 2023Extracting Motion and Appearance via Inter-Frame Attention for Efficient Video Frame Interpolation
- CVPR 2023Feature Aggregated Queries for Transformer-Based Video Object Detectors
- CVPR 2023Fine-Grained Audible Video Description
- CVPR 2023Fine-Tuned CLIP Models Are Efficient Video Learners
- CVPR 2023Frame Flexible Network
- CVPR 2023FREDOM: Fairness Domain Adaptation Approach to Semantic Scene Understanding
- CVPR 2023Generating Anomalies for Video Anomaly Detection With Prompt-Based Feature Mapping
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。