Carnegie Mellon University
Browse

Optimal no-intersection multi-label binary localization for time series using totally unimodular linear programming

Download (767.95 kB)
journal contribution
posted on 2014-10-01, 00:00 authored by Ricardo da Silveira Cabral, Joao Costeira, Alexandre Bernardino, Fernando de la Torre

We propose a new model for simultaneously localizing different classes in the same media, casting it as an integer optimization problem. Our model subsumes into a single formulation previous single and multi-class localization methods, as well as allows us to exploit optimal relaxations to the linear domain. We apply our model to the problem of multi-label multiple instance learning for tagging video collections. Given weakly labeled training samples, where tags for actions in video and objects in images are known but not their locations, our aim is to train classifiers for both detection and localization of said classes on new data. Experimental results demonstrate our approach obtains similar performances when compared to fully supervised methods.

History

Publisher Statement

© 2014 IEEE. Personal use of this material is permitted. Permission from IEEE must be obtained for all other uses, in any current or future media, including reprinting/republishing this material for advertising or promotional purposes, creating new collective works, for resale or redistribution to servers or lists, or reuse of any copyrighted component of this work in other works.

Date

2014-10-01

Usage metrics

    Exports

    RefWorks
    BibTeX
    Ref. manager
    Endnote
    DataCite
    NLM
    DC