scispace - formally typeset
S

Shi-Min Hu

Researcher at Tsinghua University

Publications -  330
Citations -  16809

Shi-Min Hu is an academic researcher from Tsinghua University. The author has contributed to research in topics: Computer science & Image segmentation. The author has an hindex of 54, co-authored 321 publications receiving 13301 citations. Previous affiliations of Shi-Min Hu include Microsoft & Beihang University.

Papers
More filters
Journal ArticleDOI

Semantic Labeling and Instance Segmentation of 3D Point Clouds Using Patch Context Analysis and Multiscale Processing

TL;DR: A novel algorithm for semantic segmentation and labeling of 3D point clouds of indoor scenes, where objects in point clouds can have significant variations and complex configurations, which outperforms state-of-the-art methods on several representative point cloud datasets.
Proceedings ArticleDOI

Cracking App Isolation on Apple: Unauthorized Cross-App Resource Access on MAC OS~X and iOS

TL;DR: XARA as mentioned in this paper exploits inter-app interaction services, including the keychain, WebSocket and NSConnection on OS~X and URL Scheme on the MAC OS and iOS, to steal confidential information such as the passwords for iCloud, email and bank, and secret token of Evernote.
Journal ArticleDOI

ChoreoMaster: choreography-oriented music-driven dance synthesis

TL;DR: ChoreoMaster as discussed by the authors is a production-ready music-driven dance motion synthesis system, which can automatically generate a high-quality dance motion sequence to accompany the input music in terms of style, rhythm and structure.
Journal ArticleDOI

Applications of Geometry Processing: Visual storylines: Semantic visualization of movie sequence

TL;DR: A video summarization approach that automatically extracts and visualizes movie storylines in a static image for the purposes of efficient representation and quick overview and can be used to assist viewers to understand video contents when they are familiar with the context of the video or when a text synopsis is provided.
Journal ArticleDOI

Real-time High-accuracy Three-Dimensional Reconstruction with Consumer RGB-D Cameras

TL;DR: The proposed method outperforms state-of-the-art systems in terms of the accuracy of both recovered camera trajectories and reconstructed models and has implemented the proposed algorithm on the GPU, achieving real-time 3D scanning frame rates and updating the reconstructed model on thefly.