Harnessing lab knowledge for real-world action recognition

DOI10.1007/S11263-014-0717-5zbMATH Open1328.68247OpenAlexW2128840666MaRDI QIDQ903539FDOQ903539

Authors: Zhigang Ma, Yi Yang, Feiping Nie, Nicu Sebe, Shuicheng Yan, Alexander G. Hauptmann 

Publication date: 6 January 2016

Published in: International Journal of Computer Vision (Search for Journal in Brave)

Full work available at URL: https://doi.org/10.1007/s11263-014-0717-5

Recommendations

• Transductive zero-shot action recognition by word-vector embedding
• Boosted multi-class semi-supervised learning for human action recognition
• Max-margin heterogeneous information machine for RGB-D action recognition
• Weakly-supervised cross-domain dictionary learning for visual recognition
• Human action segmentation and recognition using discriminative semi-Markov models

zbMATH Keywords

transfer learningaction recognitiongeneral Schatten-\(p\) normlab to real-world

Mathematics Subject Classification ID

Learning and adaptive systems in artificial intelligence (68T05) Machine vision and scene understanding (68T45)

Cites Work

• Convex multi-task feature learning
• Human action segmentation and recognition using discriminative semi-Markov models
• Mining layered grammar rules for action recognition
• Title not available (Why is that?)
• On spectral learning

Cited In (1)

• Joint consensus and diversity for multi-view semi-supervised classification

Uses Software

• LIBSVM
• HumanEva
• SIFT

This page was built for publication: Harnessing lab knowledge for real-world action recognition

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q903539)