2018/03/15 by Gedas Bertasius, Bertasius, Gedas, Lorenzo Torresani +3 · 7 citations
Computer Science · #Advanced Neural Network Applications #Domain Adaptation and Few-Shot Learning #Human Pose and Action Recognition #cs.CV
paper · pdf · doi:10.48550/arxiv.1803.05549
arxiv created 2018/07/24 · arxiv updated 2018/07/25
We propose a Spatiotemporal Sampling Network (STSN) that uses deformable convolutions across time for object detection in videos. Our STSN performs object detection in a video frame by learning to spatially sample features from the adjacent frames. This naturally renders the approach robust to occlusion or motion blur in individual frames. Our framework does not require additional supervision, as it optimizes sampling locations directly with respect to object detection performance. Our STSN outperforms the state-of-the-art on the ImageNet VID dataset and compared to prior video object detection methods it uses a simpler design, and does not require optical flow data for training.