CVPR 2016 accepted papers on Video
69 of the 643 papers accepted at CVPR 2016 (10.7%) are on Video. They fall into 4 topics.
See CVPR 2016 in the interactive map
Submitting to CVPR? Checklist →
Working on something in this area? Describe your idea in scime atlas to see the closest papers by meaning and how crowded the spot has become.
Topics and papers
Video segmentation and tracking · 35 papers
- A Benchmark Dataset and Evaluation Methodology for Video Object Segmentation (2,095 citations)
- Face2Face: Real-Time Face Capture and Reenactment of RGB Videos (1,843 citations)
- Learning Temporal Regularity in Video Sequences (1,422 citations)
- Recurrent Convolutional Network for Video-Based Person Re-Identification (596 citations)
- Multimodal Spontaneous Emotion Corpus for Human Behavior Analysis (437 citations)
- Hierarchical Recurrent Neural Encoder for Video Representation With Application to Captioning (427 citations)
- Video Segmentation via Object Flow (344 citations)
- Unsupervised Learning From Narrated Instruction Videos (295 citations)
- Highlight Detection With Pairwise Deep Ranking for First-Person Video Summarization (291 citations)
- Deep Hand: How to Train a CNN on 1 Million Hand Images When Your Data Is Continuous and Weakly Labelled (288 citations)
- Bilateral Space Video Segmentation (231 citations)
- Detecting Events and Key Actors in Multi-Person Videos (225 citations)
and 23 more in the interactive map.
Action recognition · 30 papers
- NTU RGB+D: A Large Scale Dataset for 3D Human Activity Analysis (3,062 citations)
- Convolutional Two-Stream Network Fusion for Video Action Recognition (2,806 citations)
- Temporal Action Localization in Untrimmed Videos via Multi-Stage CNNs (967 citations)
- End-To-End Learning of Action Detection From Frame Glimpses in Videos (627 citations)
- Dynamic Image Networks for Action Recognition (606 citations)
- Anticipating Visual Representations From Unlabeled Video (543 citations)
- A Hierarchical Deep Temporal Model for Group Activity Recognition (539 citations)
- A Multi-Stream Bi-Directional Recurrent Neural Network for Fine-Grained Action Detection (473 citations)
- Real-Time Action Recognition With Enhanced Motion Vector CNNs (431 citations)
- Fast Temporal Activity Proposals for Efficient Detection of Human Actions in Untrimmed Videos (304 citations)
- A Key Volume Mining Deep Framework for Action Recognition (262 citations)
- Temporal Action Detection Using a Statistical Language Model (243 citations)
and 18 more in the interactive map.
Video-language understanding · 3 papers
- MSR-VTT: A Large Video Description Dataset for Bridging Video and Language (1,822 citations)
- MovieQA: Understanding Stories in Movies Through Question-Answering (681 citations)
- Video Paragraph Captioning Using Hierarchical Recurrent Neural Networks (563 citations)
Video generation · 1 paper
- Video2GIF: Automatic Generation of Animated GIFs From Video (139 citations)
