Title :
What Do You Do? Occupation Recognition in a Photo via Social Context
Author :
Ming Shao ; Liangyue Li ; Yun Fu
Author_Institution :
Coll. of Comput. & Inf. Sci., Northeastern Univ., Boston, MA, USA
Abstract :
In this paper, we investigate the problem of recognizing occupations of multiple people with arbitrary poses in a photo. Previous work utilizing single person´s nearly frontal clothing information and fore/background context preliminarily proves that occupation recognition is computationally feasible in computer vision. However, in practice, multiple people with arbitrary poses are common in a photo, and recognizing their occupations is even more challenging. We argue that with appropriately built visual attributes, co-occurrence, and spatial configuration model that is learned through structure SVM, we can recognize multiple people´s occupations in a photo simultaneously. To evaluate our method´s performance, we conduct extensive experiments on a new well-labeled occupation database with 14 representative occupations and over 7K images. Results on this database validate our method´s effectiveness and show that occupation recognition is solvable in a more general case.
Keywords :
clothing; computer vision; pose estimation; support vector machines; visual databases; SVM structure; computer vision; fore-background context; frontal clothing information; occupation recognition; photo; social context; spatial configuration model; Clothing; Databases; Standards; Support vector machines; Vectors; Visualization; Zinc; Occupation Recognition; Social Context; Visual Attributes;
Conference_Titel :
Computer Vision (ICCV), 2013 IEEE International Conference on
Conference_Location :
Sydney, NSW
DOI :
10.1109/ICCV.2013.451