G
Guiyu Tian
Researcher at Peking University
Publications - 8
Citations - 71
Guiyu Tian is an academic researcher from Peking University. The author has contributed to research in topics: Image segmentation & Block (data storage). The author has an hindex of 4, co-authored 8 publications receiving 37 citations.
Papers
More filters
Proceedings ArticleDOI
Cap2Seg: Inferring Semantic and Spatial Context from Captions for Zero-Shot Image Segmentation
TL;DR: Cap2Seg is described, a novel solution of zero-shot image segmentation that harnesses accompanying image captions for intelligently inferring spatial and semantic context for the zero- shot image segmentations task.
Proceedings ArticleDOI
WiFit: Ubiquitous Bodyweight Exercise Monitoring with Commodity Wi-Fi Devices
TL;DR: This work proposes WiFit, a bodyweight exercises monitoring system that supports accurate repetition counting using a pair of commodity Wi-Fi devices without attaching anything to the human body, and develops an impulse-based method to segment and count the number of repeats.
Proceedings ArticleDOI
Two-Stream Video Classification with Cross-Modality Attention
TL;DR: Wang et al. as discussed by the authors proposed a cross-modality attention operation, which can obtain information from other modality in a more effective way than two-stream. But, the most popular method up to now is still simply fusing each stream's prediction scores at the last stage.
Proceedings ArticleDOI
Fast Non-Local Neural Networks with Spectral Residual Learning
TL;DR: Spectral residual learning is proposed, a novel network architectural design for achieving fully global receptive field and its equivalence to conducting residual learning in some spectral domain is shown and performance improvement by large margins is shown.
Posted Content
Two-Stream Video Classification with Cross-Modality Attention
TL;DR: A cross-modality attention operation, which can obtain information from other modality in a more effective way than two-stream, is proposed and a compatible block named CMA block is implemented, which is a wrapper of the proposed attention operation.