H
Hao Su
Researcher at University of California, San Diego
Publications - 364
Citations - 82843
Hao Su is an academic researcher from University of California, San Diego. The author has contributed to research in topics: Computer science & Point cloud. The author has an hindex of 57, co-authored 302 publications receiving 55902 citations. Previous affiliations of Hao Su include Philips & Jiangxi University of Science and Technology.
Papers
More filters
Journal ArticleDOI
Wearable Knee Assistive Devices for Kneeling Tasks in Construction
TL;DR: The proposed system provides an enabling intervention to potentially reduce musculoskeletal injury risks of construction workers by controlling the assistive knee joint torque provided by lightweight exoskeletons with powerful quasi-direct drive actuation.
Posted Content
Beyond Holistic Object Recognition: Enriching Image Understanding with Part States
TL;DR: This paper addresses the problem of inferring rich semantics imparted by an object part in still images by proposing to tokenize the semantic space as a discrete set of part states, and presents a part state dataset which contains rich part-level semantic annotations.
Book ChapterDOI
Meshing Point Clouds with Predicted Intrinsic-Extrinsic Ratio Guidance
TL;DR: In this paper, a surrogate of local connectivity is calculated by comparing the intrinsic/extrinsic metrics, which is then used to predict which triplets of points should form faces.
Journal ArticleDOI
Therapeutic supramolecular tubustecan hydrogel combined with checkpoint inhibitor elicits immunity to combat cancer
Feihu Wang,Hao Su,Dongqing Xu,Maya K. Monroe,Caleb F. Anderson,Weijie Zhang,Richard Oh,Zongyuan Wang,Xuanrong Sun,Xuanrong Sun,Han Wang,Fengyi Wan,Fengyi Wan,Honggang Cui,Honggang Cui +14 more
TL;DR: In this article, a localized chemo-immunotherapy system was developed using an anti-cancer drug-based supramolecular polymer (SP) hydrogel to re-edit the host's immune system to combat cancer.
Proceedings ArticleDOI
Deep Keypoint-Based Camera Pose Estimation with Geometric Constraints
TL;DR: In this article, an end-to-end trainable framework consisting of learnable modules for detection, feature extraction, matching and outlier rejection, while directly optimizing for the geometric pose objective is proposed.