Thomas S. Huang
0000-0001-8474-5859
Publication & Citation Trends
Publications
1,411 total
CCNet: Criss-Cross Attention for Semantic Segmentation OA
Cited by 84
Semantic Scholar
Human Expression Recognition using Facial Features
Cited by 2
Semantic Scholar
Parallel Implementation of Shape based Image Retrieval Approach on CUDA in Compressed Domain
Cited by 3
Semantic Scholar
Social Relation based Scalable Semantic Search Refinement
Cited by 5
Semantic Scholar
Factorization-based Non-rigid Shape Modeling and Tracking in Stereo-Motion
Cited by 0
Semantic Scholar
INTERNATIONAL ORGANISATION FOR STANDARDISATION ORGANISATION INTERNATIONALE DE NORMALISATION ISO/IEC JTC1/SC29/WG11 CODING OF MOVING PICTURES AND AUDIO
Cited by 4
Semantic Scholar
Highlights Extraction from Unscripted Video
Cited by 1
Semantic Scholar
AVICAR: audio-visual speech corpus in a car environment
Cited by 50
Semantic Scholar
Research Topics
Advanced Image and Video Retrieval Techniques
(316)
Advanced Vision and Imaging
(231)
Image Retrieval and Classification Techniques
(220)
Face and Expression Recognition
(203)
Video Analysis and Summarization
(149)
Affiliations
Northwestern University
Leibniz University Hannover
Purdue University Northwest
California Institute of Technology
AT&T (United States)