Concepts not alone: Exploring pairwise relationships for zero-shot video activity recognition

Chuang Gan, Ming Lin, Yi Yang, Gerard De Melo, Alexander G. Hauptmann

Research output: Chapter in Book/Report/Conference proceedingConference contribution

31 Scopus citations

Abstract

Vast quantities of videos are now being captured at astonishing rates, but the majority of these are not labelled. To cope with such data, we consider the task of content-based activity recognition in videos without any manually labelled examples, also known as zero-shot video recognition. To achieve this, videos are represented in terms of detected visual concepts, which are then scored as relevant or irrelevant according to their similarity with a given textual query. In this paper, we propose a more robust approach for scoring concepts in order to alleviate many of the brittleness and low precision problems of previous work. Not only do we jointly consider semantic relatedness, visual reliability, and discriminative power. To handle noise and non-linearities in the ranking scores of the selected concepts, we propose a novel pairwise order matrix approach for score aggregation. Extensive experiments on the large-scale TRECVID Multimedia Event Detection data show the superiority of our approach.

Original languageEnglish (US)
Title of host publication30th AAAI Conference on Artificial Intelligence, AAAI 2016
PublisherAAAI press
Pages3487-3493
Number of pages7
ISBN (Electronic)9781577357605
StatePublished - Jan 1 2016
Externally publishedYes
Event30th AAAI Conference on Artificial Intelligence, AAAI 2016 - Phoenix, United States
Duration: Feb 12 2016Feb 17 2016

Publication series

Name30th AAAI Conference on Artificial Intelligence, AAAI 2016

Other

Other30th AAAI Conference on Artificial Intelligence, AAAI 2016
CountryUnited States
CityPhoenix
Period2/12/162/17/16

All Science Journal Classification (ASJC) codes

  • Artificial Intelligence

Fingerprint Dive into the research topics of 'Concepts not alone: Exploring pairwise relationships for zero-shot video activity recognition'. Together they form a unique fingerprint.

  • Cite this

    Gan, C., Lin, M., Yang, Y., De Melo, G., & Hauptmann, A. G. (2016). Concepts not alone: Exploring pairwise relationships for zero-shot video activity recognition. In 30th AAAI Conference on Artificial Intelligence, AAAI 2016 (pp. 3487-3493). (30th AAAI Conference on Artificial Intelligence, AAAI 2016). AAAI press.