An Attention-Based Activity Recognition for Egocentric Video
Authors:
- Kenji MatsuoKMKenji Matsuo
- Kentaro YamadaKYKentaro Yamada
- Satoshi UenoSUSatoshi Ueno
- Sei NaitoSNSei Naito
- 1 June 2014
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- No. 21607508,p. 565-570
Abstract
In this paper, we propose a human activity recognition method from first-person videos, which provides a supplementary method to improve the recognition accuracy. Conventional methods detect objects and derive a user's behavior based on their taxonomy. One of the recent works has achieved accuracy improvement by determining key objects based on hand manipulation. However, such manipulation-based approach has a restriction on applicable scenes and object types because the user's hands don't always present significant information. In contrast, our proposed attention-based approach provides a solution to detect visually salient objects as key objects in a non-contact manner. Experimental results show that the proposed method classifies first-person actions more accurately than the previous method by 6.4 percentage points and its average accuracy reaches 43.3%.Keywords
This publication has 21 references indexed in Scilit:
- Attention Prediction in Egocentric Video Using Motion and Visual Saliency2011
- Object Detection with Discriminatively Trained Part-Based ModelsIEEE Transactions on Pattern Analysis and Machine Intelligence, 2009
- Temporal segmentation and activity classification from first-person sensing2009
- What can saliency models predict about eye movements? Spatial and sequential aspects of fixations during encoding and recognitionJournal of Vision, 2008
- Retrieving actions in movies2007
- InSense: Interest-Based Life LoggingIEEE MultiMedia, 2006
- Fine-Grained Activity Recognition by Aggregating Abstract Object Usage2005
- Inferring Activities from Interactions with ObjectsIEEE Pervasive Computing, 2004
- Activity Recognition in the Home Using Simple and Ubiquitous Sensors2004
- Looking at people: sensing for ubiquitous and wearable computingIEEE Transactions on Pattern Analysis and Machine Intelligence, 2000