Concepts not alone: Exploring pairwise relationships for zero-shot video activity recognition
- Publication Type:
- Conference Proceeding
- Citation:
- 30th AAAI Conference on Artificial Intelligence, AAAI 2016, 2016, pp. 3487 - 3493
- Issue Date:
- 2016-01-01
Closed Access
Filename | Description | Size | |||
---|---|---|---|---|---|
12259-56312-1-PB (1).pdf | Published version | 728.92 kB |
Copyright Clearance Process
- Recently Added
- In Progress
- Closed Access
This item is closed access and not available.
© Copyright 2016, Association for the Advancement of Artificial Intelligence (www.aaai.org). All rights reserved. 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.
Please use this identifier to cite or link to this item: