Enhancing Action Recognition by Cross-Domain Dictionary Learning

Fan Zhu, Ling Shao

Research output: Contribution to conferencePaper

9 Citations (Scopus)

Abstract

We present a novel cross-dataset action recognition framework that utilizes relevant actions from other visual domains as auxiliary knowledge for enhancing the learning system in the target domain. The data distribution of relevant actions from a source dataset is adapted to match the data distribution of actions in the target dataset via a cross-domain discriminative dictionary learning method, through which a reconstructive, discriminative and domain-adaptive dictionary-pair can be learned. Using selected categories from the HMDB51 dataset as the source domain actions, the proposed framework achieves outstanding performance on the UCF YouTube dataset.
Original languageEnglish
DOIs
Publication statusPublished - Sep 2013
EventBritish Machine Vision Conference 2013 - Bristol, UK
Duration: 1 Sep 2013 → …

Conference

ConferenceBritish Machine Vision Conference 2013
Period1/09/13 → …

Fingerprint

Dive into the research topics of 'Enhancing Action Recognition by Cross-Domain Dictionary Learning'. Together they form a unique fingerprint.

Cite this