Action Detection with Improved Dense Trajectories and Sliding Window

In this paper we describe an action/interaction detection system based on improved dense trajectories [19], multiple visual descriptors and bag-of-features representation. Given that the actions/interactions are not mutual exclusive, we train a binary classifier for every predefined action/interacti...

Full description

Saved in:
Bibliographic Details
Published inComputer Vision - ECCV 2014 Workshops pp. 541 - 551
Main Authors Shu, Zhixin, Yun, Kiwon, Samaras, Dimitris
Format Book Chapter
LanguageEnglish
Published Cham Springer International Publishing 2015
SeriesLecture Notes in Computer Science
Subjects
Action detection
Action recognition
Dense trajectories
Video analysis
Online AccessGet full text

Cover

More Information
Summary:In this paper we describe an action/interaction detection system based on improved dense trajectories [19], multiple visual descriptors and bag-of-features representation. Given that the actions/interactions are not mutual exclusive, we train a binary classifier for every predefined action/interaction. We rely on a non-overlapped temporal sliding window to enable the temporal localization. We have tested our system in ChaLearn Looking at People Challenge 2014 Track 2 dataset [1, 2]. We obtained 0.4226 average overlap, which is the 3rd place in the track of the challenge. Finally, we provide an extensive analysis of the performance of this system on different actions and provide possible ways to improve a general action detection system.
ISBN:9783319161778
3319161776
ISSN:0302-9743
1611-3349
DOI:10.1007/978-3-319-16178-5_38