Seeing What You’re Told: Sentence-Guided Activity Recognition In Video

TitleSeeing What You’re Told: Sentence-Guided Activity Recognition In Video
Publication TypeConference Paper
Year of Publication2014
AuthorsSiddharth, N, Barbu, A, Siskind, JMark
Conference NameCVPR
Date Published07/2014
Conference LocationColumbus, Ohio
Abstract

We present a system that demonstrates how the compositional structure of events, in concert with the compositional structure of language, can interplay with the underlying focusing mechanisms in video action recognition, providing a medium for top-down and bottom-up integration as well as multi-modal integration between vision and language. We show how the roles played by participants (nouns), their characteristics (adjectives), the actions performed (verbs), the manner of such actions (adverbs), and changing spatial relations between participants (prepositions), in the form of whole-sentence descriptions mediated by a grammar, guides the activity-recognition process. Further, the utility and expressiveness of our framework is demonstrated by performing three separate tasks in the domain of multiactivity video: sentence-guided focus of attention, generation of sentential description, and query-based search, simply by leveraging the framework in different manners

Refereed DesignationRefereed
Download:  PDF icon Publication

Research Area: 

CBMM Relationship: 

  • CBMM Funded