Y
Yuwen Xiong
Researcher at University of Toronto
Publications - 38
Citations - 7038
Yuwen Xiong is an academic researcher from University of Toronto. The author has contributed to research in topics: Segmentation & Object detection. The author has an hindex of 18, co-authored 36 publications receiving 4081 citations. Previous affiliations of Yuwen Xiong include Uber & Microsoft.
Papers
More filters
Proceedings ArticleDOI
Deformable Convolutional Networks
TL;DR: Deformable convolutional networks as discussed by the authors augment the spatial sampling locations in the modules with additional offsets and learn the offsets from the target tasks, without additional supervision, which can readily replace their plain counterparts in existing CNNs and can be easily trained end-to-end by standard backpropagation.
Posted Content
Deformable Convolutional Networks
TL;DR: This work introduces two new modules to enhance the transformation modeling capability of CNNs, namely, deformable convolution and deformable RoI pooling, based on the idea of augmenting the spatial sampling locations in the modules with additional offsets and learning the offsets from the target tasks, without additional supervision.
Proceedings ArticleDOI
Deep Feature Flow for Video Recognition
TL;DR: Deep Feature Flow as mentioned in this paper runs the expensive convolutional sub-network only on sparse key frames and propagates their deep feature maps to other frames via a flow field, which achieves significant speedup as flow computation is relatively fast.
Proceedings ArticleDOI
UPSNet: A Unified Panoptic Segmentation Network
TL;DR: UPSNet as mentioned in this paper proposes a unified panoptic segmentation network to solve the problem of conflicts between semantic and instance segmentation by combining a deformable convolution based head and a Mask R-CNN style instance head.
Posted Content
Deep Feature Flow for Video Recognition
TL;DR: Deep feature flow is presented, a fast and accurate framework for video recognition that runs the expensive convolutional sub-network only on sparse key frames and propagates their deep feature maps to other frames via a flow field and achieves significant speedup as flow computation is relatively fast.