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 12 / 46 页
- ICML 2026Seeing is Understanding: Unlocking Causal Attention into Modality-Mutual Attention for Multimodal LLMs
- ICML 2026Seeing Symbols, Missing Structure: A Real-World Handwritten Mathematical Expression Recognition Benchmark for Large Models
- ICML 2026SegPVSG: Panoptic Video Scene Graph Generation via Temporal Focusing and Generative Augmentation
- ICML 2026SemanticNVS: Improving Semantic Scene Understanding in Generative Novel View Synthesis
- ICML 2026SGMD: Score Gradient Matching Distillation for Few-Step Video Diffusion Distillation
- ICML 2026Smoothing Slot Attention Iterations and Recurrences
- ICML 2026SpaceVista: All-Scale Visual Spatial Reasoning from mm to km
- ICML 2026Spectral Reach: Understanding Neural Scaling as Progress into the Spectral Tail
- ICML 2026TapSampling: Inference-Time Sampling with a Task-Progress-Understanding Verifier for Robotic Manipulation
- ICML 2026Think in Cloud, Look at Edges: Semantic-Driven Query Decomposition for Efficient Video Reasoning
- ICML 2026TimeChat-Captioner: Scripting Multi-Scene Videos with Time-Aware and Structural Audio-Visual Captions
- ICML 2026Toward Safe Quantization-Aware Fine-tuning: Understanding and Mitigating Safety Alignment Degradation
- ICML 2026Toward Understanding Adversarial Distillation: Why Robust Teachers Fail
- ICML 2026Towards Theoretical Understanding of Transformer Test-Time Computing: Investigation on In-Context Linear Regression
- ICML 2026Towards Trustworthy Video Anomaly Understanding: A Class-Guided Chain-of-Evaluation Metric and An Anomaly-focused Meta-Benchmark
- ICML 2026Towards Understanding Adam Convergence on Highly Degenerate Polynomials
- ICML 2026Towards Understanding Massive Activations in Attention Sink Mechanism
- ICML 2026Towards Understanding Modality Interaction in Multimodal Language Models via Partial Information Decomposition
- ICML 2026Towards Understanding Steering Strength
- ICML 2026Trajectory-Stabilized Inference for Diffusion-Based Video Inpainting
- ICML 2026Two-Layer Linear Auto-Regressive Models Estimate Latent States
- ICML 2026Understanding Behavior Cloning with Action Quantization
- ICML 2026Understanding Catastrophic Forgetting In LoRA via Mean-Field Attention Dynamics
- ICML 2026Understanding Data Temporality Impact on Large Language Models Pre-training
- ICML 2026Understanding Dynamic Compute Allocation in Recurrent Transformers
- ICML 2026Understanding Dynamics of Adam in Zero-Sum Games: An ODE Approach
- ICML 2026Understanding Generalization and Forgetting in In-Context Continual Learning
- ICML 2026Understanding Generalization from Embedding Dimension and Distributional Convergence
- ICML 2026Understanding MARS: When Scaling Momentum Provably Helps
- ICML 2026Understanding Performance Collapse in Layer-Pruned Large Language Models via Decision Representation Transitions
- ICML 2026Understanding Private Learning From Feature Perspective
- ICML 2026Understanding SAM through Minimax Perspective
- ICML 2026Understanding Self-Supervised Learning via Latent Distribution Matching
- ICML 2026Understanding the Ability of LLMs to Handle Character-Level Perturbation
- ICML 2026Understanding the Gaps in Satisficing Bandits
- ICML 2026Understanding the Parameter Space Geometry of Transformers Encoding Boolean Functions
- ICML 2026Understanding Truncated Positional Encodings for Graph Neural Networks
- ICML 2026Unison: Benchmarking Unified Multimodal Models via Synergistic Understanding and Generation
- ICML 2026Universal Skeleton Understanding via Differentiable Rendering and MLLMs
- ICML 2026V-LynX: Token Interface Alignment for Video+X LLMs
- ICML 2026Veda: Scalable Video Diffusion via Distilled Sparse Attention
- ICML 2026Video-Based Optimal Transport for Feedback-Efficient Offline Preference-Based Reinforcement Learning
- ICML 2026Video-BCI: Bayesian Cognitive Integration of Self-Prior Hypotheses for Video Understanding
- ICML 2026Video-in-the-Loop: Span-Grounded Long Video QA with Interleaved Reasoning
- ICML 2026Video-MTR: Reinforced Multi-Turn Reasoning for Long Video Understanding
- ICML 2026VideoFlexTok: Flexible-Length Coarse-to-Fine Video Tokenization
- ICML 2026VideoKR: Towards Knowledge- and Reasoning-Intensive Video Understanding
- ICML 2026VideoLoom: A Video Large Language Model for Joint Spatial-Temporal Understanding
- ICML 2026VideoMAETok: Boosting Video Diffusion Models via Masked Autoencoders as Tokenizers
- ICML 2026VideoSEAL: Mitigating Evidence Misalignment in Agentic Long Video Understanding by Decoupling Answer Authority
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。