Video: research map
Video understanding, action recognition and video generation.
5,006 accepted papers at ICML, NeurIPS, ICLR, CVPR and AAAI (2016–2026), in 4 topics. Within all five venues, its share grew from 3.9% in 2023–24 to 5.5% in 2025–26 (1,032 → 2,518 papers at ICML, NeurIPS, CVPR and AAAI, the venues with data for all four years).
Explore Video in the interactive map
Topics
- Video segmentation and tracking · 1,736 papers
Self-supervised video representation learning, Video restoration with temporal priors, Sign language and physiological video analysis - Video generation · 1,407 papers
Efficient video diffusion models, Compositional text-to-video diffusion, Trajectory-guided motion control - Video-language understanding · 1,146 papers
Event and anomaly reasoning in video, Video LLMs with fine-grained understanding, Long video understanding - Action recognition · 717 papers
Disentangled action recognition, Spatiotemporal CNNs for action recognition, Contrastive video representation learning
Most cited papers in Video
- Quo Vadis, Action Recognition? A New Model and the Kinetics Dataset (CVPR 2017 · 9,707 citations)
- A Closer Look at Spatiotemporal Convolutions for Action Recognition (CVPR 2018 · 3,632 citations)
- BDD100K: A Diverse Driving Dataset for Heterogeneous Multitask Learning (CVPR 2020 · 2,481 citations)
- Temporal Convolutional Networks for Action Segmentation and Detection (CVPR 2017 · 2,175 citations)
- Real-World Anomaly Detection in Surveillance Videos (CVPR 2018 · 2,159 citations)
- A Benchmark Dataset and Evaluation Methodology for Video Object Segmentation (CVPR 2016 · 2,095 citations)
- Face2Face: Real-Time Face Capture and Reenactment of RGB Videos (CVPR 2016 · 1,843 citations)
- MSR-VTT: A Large Video Description Dataset for Bridging Video and Language (CVPR 2016 · 1,822 citations)
- Celeb-DF: A Large-Scale Challenging Dataset for DeepFake Forensics (CVPR 2020 · 1,725 citations)
- MoCoGAN: Decomposing Motion and Content for Video Generation (CVPR 2018 · 1,116 citations)
- AVA: A Video Dataset of Spatio-Temporally Localized Atomic Visual Actions (CVPR 2018 · 1,021 citations)
- One-Shot Video Object Segmentation (CVPR 2017 · 926 citations)