2 citations · 4 across the 5 of their papers we have counts for
5 papers
ControlCap: Controllable Region-level Captioning
Yuzhong Zhao, Yue Liu, Zonghao Guo +4
Region-level captioning is challenged by the caption degeneration issue, which refers to that pre-trained multimodal models tend to predict the most frequent captions but miss the…
Generative Prompt Model for Weakly Supervised Object Localization
Yuzhong Zhao, Qixiang Ye, Weijia Wu +2
Weakly supervised object localization (WSOL) remains challenging when learning object localization models from image category labels. Conventional methods that discriminatively tra…
FlowText: Synthesizing Realistic Scene Text Video with Optical Flow Estimation
Yuzhong Zhao, Weijia Wu, Zhuang Li +2
Current video text spotting methods can achieve preferable performance, powered with sufficient labeled training data. However, labeling data manually is time-consuming and labor-i…
Explore Faster Localization Learning For Scene Text Detection
Yuzhong Zhao, Yuanqiang Cai, Weijia Wu +1
Generally pre-training and long-time training computation are necessary for obtaining a good-performance text detector based on deep networks. In this paper, we present a new scene…
Multi-task Sentence Encoding Model for Semantic Retrieval in Question Answering Systems
Qiang Huang, Jianhui Bu, Weijian Xie +3
Question Answering (QA) systems are used to provide proper responses to users' questions automatically. Sentence matching is an essential task in the QA systems and is usually refo…