B
Baopeng Zhang
Researcher at Beijing Jiaotong University
Publications - 32
Citations - 660
Baopeng Zhang is an academic researcher from Beijing Jiaotong University. The author has contributed to research in topics: Computer science & Discriminative model. The author has an hindex of 7, co-authored 24 publications receiving 493 citations. Previous affiliations of Baopeng Zhang include University of North Carolina at Charlotte.
Papers
More filters
Journal ArticleDOI
iPrivacy: Image Privacy Protection by Identifying Sensitive Objects via Deep Multi-Task Learning
TL;DR: This paper consists of the following contributions: massive social images and their privacy settings are leveraged to learn the object-privacy relatedness effectively and identify a set of privacy-sensitive object classes automatically and a deep multi-task learning algorithm is developed.
Journal ArticleDOI
Leveraging Content Sensitiveness and User Trustworthiness to Recommend Fine-Grained Privacy Settings for Social Image Sharing
TL;DR: Both the image content sensitiveness and the user trustworthiness are integrated to train a tree classifier to recommend fine-grained privacy settings for social image sharing.
Journal ArticleDOI
Embedding Visual Hierarchy With Deep Networks for Large-Scale Visual Recognition
TL;DR: By learning the tree classifier, the deep network and the visual hierarchy adaptation jointly in an end-to-end manner, the LMM algorithm can achieve higher accuracy rates on hierarchical visual recognition.
Journal ArticleDOI
Visual railway detection by superpixel based intracellular decisions
Zhu Teng,Feng Liu,Baopeng Zhang +2 more
TL;DR: The proposed railway detection method is evaluated on a number of challenging images and experiments demonstrate that the proposed method is an effective and detailed solution to railway detection, and is superior to other railway detection methods.
Journal ArticleDOI
Deep Spatial and Temporal Network for Robust Visual Object Tracking
TL;DR: A deep spatial and temporal network (DSTN) is developed for visual tracking by explicitly exploiting both the object representations from each frame and their dynamics along multiple frames in a video, such that it can seamlessly integrate the object appearances with their motions to produce compact object appearances and capture their temporal variations effectively.