Title :
Formulating Action Recognition as a Ranking Problem
Author :
Can, Ethem F. ; Manmatha, R.
Author_Institution :
Sch. of Comput. Sci., Univ. of Massachusetts, Amherst, MA, USA
Abstract :
Action recognition is one of the major challenges of computer vision. Several approaches have been proposed using different descriptors and multi-class models. In this paper, we focus on binary ranking models for the action recognition problem and address the action recognition as a ranking problem. A binary ranking model is trained for each action and used to recognize the test videos for that action. Binary ranking models are constructed using dense SIFT (DSIFT) descriptors and histogram of oriented gradients / histogram of optical flows (HOG/HOF) descriptors. We show that using ranking models, it is possible to obtain higher recognition accuracies from a baseline that is based on multi-class models on the very recent and challenging benchmark datasets, Human Motion Database (HMDB) and The Action Similarity Labeling (ASLAN).
Keywords :
computer vision; image sequences; object recognition; video signal processing; visual databases; ASLAN; DSIFT descriptors; HMDB; HOG-HOF descriptors; action recognition; action similarity labeling; binary ranking model; computer vision; dense SIFT descriptors; histogram of optical flow descriptor; histogram of oriented gradient descriptor; human motion database; multiclass models; ranking problem; test video recognition; Accuracy; Benchmark testing; Computational modeling; Histograms; Support vector machines; Training; Videos; ASLAN; Action recognition; HMDB; ranking; svm-rank; video retrieval;
Conference_Titel :
Computer Vision and Pattern Recognition Workshops (CVPRW), 2013 IEEE Conference on
Conference_Location :
Portland, OR
DOI :
10.1109/CVPRW.2013.44