Dear Guest, Please Register to Download Free Seminar Reports and PPT of each topic. The Download link will be visible only after the registration.Please search the topic before posting.

Please click the Facebook Like Button if you are satisfied

 Subscribe To Get Latest Seminar Reports and PPT

Receive all seminar updates via Facebook. Just Click the Like Button Below


Talking Pictures: Temporal Grouping and Dialog-Supervise ppt

Huge Collection of Information Technology Seminar Topics, Reports and PPT.

Talking Pictures: Temporal Grouping and Dialog-Supervise ppt

Postby ritupilaniya » Sat Feb 04, 2012 2:41 pm

topic:Talking Pictures: Temporal Grouping and Dialog-Supervised Person Recognition.
please send me it's report & ppt.
Posts: 1
Joined: Sat Feb 04, 2012 1:40 pm

Re: ppt

Postby Prasanth » Sun Feb 05, 2012 2:18 pm

We address the character identification problem in movies and television videos: assigning names to faces on the screen. Most prior work on person recognition in video
assumes some supervised data such as screenplay or handlabeled faces. In this paper, our only source of ‘supervision’ are the dialog cues: first, second and third person
references (such as “I’m Jack”, “Hey, Jack!” and “Jack left”). While this kind of supervision is sparse and indirect, we exploit multiple modalities and their interactions (appearance, dialog, mouth movement, synchrony, continuityediting cues) to effectively resolve identities through local temporal grouping followed by global weakly supervised recognition. We propose a novel temporal grouping model that partitions face tracks across multiple shots while respecting appearance, geometric and film-editing cues and constraints. In this model, states represent partitions of the k most recent face tracks, and transitions represent compatibility of consecutive partitions. We present dynamic programming inference and discriminative learning for the model.

The individual face tracks are subsequently assigned a name by learning a classifier from partial label constraints. The weakly supervised classifier incorporates multiple-instance constraints from dialog cues as well as soft grouping constraints from our temporal grouping. We evaluate both the temporal grouping and final character naming on several hours of TV and movies.

Presented By Timothee Cour, INRIA - WILLOW Project,Benjamin Sapp Akash Nagle Ben Taskar,University of Pennsylvania

Reference :

Tags : Talking Pictures: Temporal Grouping and Dialog-Supervised Person Recognition PDF, PPT, Seminar report
You do not have the required permissions to download the files attached to this post. You must LOGIN or REGISTER to download these files.
User avatar
Site Admin
Posts: 488
Joined: Sat May 28, 2011 6:29 pm

Return to Information Technology Seminar Topics