People search with textual queries about clothing appearance attributes

TitlePeople search with textual queries about clothing appearance attributes
Publication TypeBook Chapter
Year of Publication2014
AuthorsSatta, R, Pala, F, Fumera, G, Roli, F
EditorGong, S, Cristani, M, Yan, S, Loy, CChange
Book TitlePerson Re‐Identification, Advances in Computer Vision and Pattern Recognition
ISBN Number978-1-4471-6295-7

Person re-identification consists of searching for an individual of interest in video sequences acquired by a camera network, using animage of that individual as a query. Here we consider a related task, named people search with textual queries, which consists of searching images of individuals that match a textual description of clothing appearance, given by a Boolean combination of predefined attributes. People search can be useful in applications like forensic video analysis, where the query can be obtained from a eyewitness report. We propose a general method for implementing people search as an extension of any given re-identification system that uses any multiple part-multiple component appearance descriptor. In our method the same descriptor of the re-identification system at hand is used, and attributes are chosen by taking into account the information it provides. The original descriptor is then transformed into a dissimilarity one. Attribute detectors are finally constructed as supervised classifiers, using dissimilarity descriptors as the input feature vectors. We experimentally evaluate our method on a benchmark re-identification data set.

Citation Key 1468
Satta_BookChapterREID2013.pdf1.07 MB