Thumbnail
Access Restriction
Open

Author Gaidon, Adrien ♦ Harchaoui, Zaid ♦ Schmid, Cordelia
Source CiteSeerX
Content type Text
Publisher MSR-INRIA
File Format PDF
Language English
Subject Domain (in DDC) Computer science, information & general works ♦ Data processing & computer science
Subject Keyword Actom-anchored Vi-sual Feature ♦ Non Parametric Model ♦ Atomic Action Unit ♦ Structured Extension ♦ Efficient Action Detection ♦ Test Time ♦ Temporal Action Detec-tion ♦ Recent Benchmark ♦ Present Experimental Re-sults ♦ Asm Method ♦ Current State ♦ Video Data ♦ Action Clip ♦ Actom Sequence Model ♦ Temporal Structure ♦ Temporal Action Detection ♦ Action Temporal Structure
Description In IEEE Conference on Computer Vision & Pattern Recognition
We address the problem of detecting actions, such as drinking or opening a door, in hours of challenging video data. We propose a model based on a sequence of atomic action units, termed “actoms”, that are characteristic for the action. Our model represents the temporal structure of actions as a sequence of histograms of actom-anchored vi-sual features. Our representation, which can be seen as a temporally structured extension of the bag-of-features, is flexible, sparse and discriminative. We refer to our model as Actom Sequence Model (ASM). Training requires the an-notation of actoms for action clips. At test time, actoms are detected automatically, based on a non parametric model of the distribution of actoms, which also acts as a prior on an action’s temporal structure. We present experimental re-sults on two recent benchmarks for temporal action detec-tion, “Coffee and Cigarettes ” [12] and the dataset of [3]. We show that our ASM method outperforms the current state of the art in temporal action detection. 1.
Educational Role Student ♦ Teacher
Age Range above 22 year
Educational Use Research
Education Level UG and PG ♦ Career/Technical Study
Learning Resource Type Article
Publisher Date 2011-01-01