Title | ||
---|---|---|
From Actemes to Action: A Strongly-Supervised Representation for Detailed Action Understanding |
Abstract | ||
---|---|---|
This paper presents a novel approach for analyzing human actions in non-scripted, unconstrained video settings based on volumetric, x-y-t, patch classifiers, termed actemes. Unlike previous action-related work, the discovery of patch classifiers is posed as a strongly-supervised process. Specifically, key point labels (e.g., position) across space time are used in a data-driven training process to discover patches that are highly clustered in the space time key point configuration space. To support this process, a new human action dataset consisting of challenging consumer videos is introduced, where notably the action label, the 2D position of a set of key points and their visibilities are provided for each video frame. On a novel input video, each acteme is used in a sliding volume scheme to yield a set of sparse, non-overlapping detections. These detections provide the intermediate substrate for segmenting out the action. For action classification, the proposed representation shows significant improvement over state-of-the-art low-level features, while providing spatiotemporal localization as additional output, which sheds further light into detailed action understanding. |
Year | DOI | Venue |
---|---|---|
2013 | 10.1109/ICCV.2013.280 | ICCV |
Keywords | Field | DocType |
supervised representation,video signal processing,action detection,data-driven training process,image representation,strongly-supervised representation,space time,action-related work,spatiotemporal localization,human action dataset,actemes,detailed action understanding,spacetime key-point configuration space,sliding volume scheme,unconstrained video settings,consumer video,sparse nonoverlapping detections,new human action dataset,action understanding,image classification,patch classifiers discovery,consumer videos,configuration space,action label,patch classifier,gesture recognition,key point,human action,action classification,human actions analyzing | Space time,Computer vision,Market segmentation,Pattern recognition,Computer science,Image representation,Gesture recognition,Artificial intelligence,Contextual image classification,Configuration space | Conference |
Volume | Issue | ISSN |
2013 | 1 | 1550-5499 |
Citations | PageRank | References |
44 | 1.07 | 20 |
Authors | ||
3 |
Name | Order | Citations | PageRank |
---|---|---|---|
Weiyu Zhang | 1 | 87 | 12.67 |
Menglong Zhu | 2 | 186 | 8.21 |
Konstantinos G. Derpanis | 3 | 431 | 22.45 |