368 citations · 395 across the 7 of their papers we have counts for
5 papers · 1 filter
Improving Anomaly Segmentation with Multi-Granularity Cross-Domain Alignment
Ji Zhang, Xiao Wu, Zhi-Qi Cheng +2
Anomaly segmentation plays a pivotal role in identifying atypical objects in images, crucial for hazard detection in autonomous driving systems. While existing methods demonstrate…
Rethinking Spatial Invariance of Convolutional Networks for Object Counting
Zhi-Qi Cheng, Qi Dai, Hong Li +3
Previous work generally believes that improving the spatial invariance of convolutional networks is the key to object counting. However, after verifying several mainstream counting…
On the Selection of Anchors and Targets for Video Hyperlinking
Zhi-Qi Cheng, Hao Zhang, Xiao Wu +1
A problem not well understood in video hyperlinking is what qualifies a fragment as an anchor or target. Ideally, anchors provide good starting points for navigation, and targets s…
Video2Shop: Exact Matching Clothes in Videos to Online Shopping Images
Zhi-Qi Cheng, Xiao Wu, Yang Liu +1
In recent years, both online retail and video hosting service are exponentially growing. In this paper, we explore a new cross-domain task, Video2Shop, targeting for matching cloth…
Diversified Visual Attention Networks for Fine-Grained Object Classification
Bo Zhao, Xiao Wu, Jiashi Feng +2
Fine-grained object classification is a challenging task due to the subtle inter-class difference and large intra-class variation. Recently, visual attention models have been appli…