Blar i forfatter "Zhang, Yujia"
-
ConnNet: A Long-Range Relation-Aware Pixel-Connectivity Network for Salient Segmentation
Kampffmeyer, Michael C.; Dong, Nanqing; Liang, Xiaodan; Zhang, Yujia; Xing, Eric P. (Journal article; Tidsskriftartikkel; Peer reviewed, 2018-12-14)Salient segmentation aims to segment out attention-grabbing regions, a critical yet challenging task and the foundation of many high-level computer vision applications. It requires semantic-aware grouping of pixels into salient regions and benefits from the utilization of global multi-scale contexts to achieve good local reasoning. Previous works often address it as two-class segmentation problems ... -
Deep Reinforcement Learning for Query-Conditioned Video Summarization
Zhang, Yujia; Kampffmeyer, Michael C.; Zhao, Xiaoguang; Tan, Min (Journal article; Tidsskriftartikkel; Peer reviewed, 2019-02-21)Query-conditioned video summarization requires to (1) find a diverse set of video shots/frames that are representative for the whole video, and that (2) the selected shots/frames are related to a given query. Thus it can be tailored to different user interests leading to a better personalized summary and differs from the generic video summarization which only focuses on video content. Our work targets ... -
Dilated temporal relational adversarial network for generic video summarization
Zhang, Yujia; Kampffmeyer, Michael C.; Liang, Xiaodan; Zhang, Dingwen; Tan, Min; Xing, Eric P. (Journal article; Tidsskriftartikkel; Peer reviewed, 2019-10-12)The large amount of videos popping up every day, make it more and more critical that key information within videos can be extracted and understood in a very short time. Video summarization, the task of finding the smallest subset of frames, which still conveys the whole story of a given video, is thus of great significance to improve efficiency of video understanding. We propose a novel Dilated ... -
Rethinking knowledge graph propagation for zero-shot learning
Kampffmeyer, Michael C.; Chen, Yinbo; Liang, Xiaodan; Wang, Hao; Zhang, Yujia; Xing, Eric P. (Journal article; Tidsskriftartikkel; Peer reviewed, 2019)Graph convolutional neural networks have recently shown great potential for the task of zero-shot learning. These models are highly sample efficient as related concepts in the graph structure share statistical strength allowing generalization to new classes when faced with a lack of data. However, multi-layer architectures, which are required to propagate knowledge to distant nodes in the graph, ...