| HAL-Inria | Publications, software ... of Inria's scientists |
Conference papers
Finding Actors and Actions in Movies
Abstract : We address the problem of learning a joint model of actors and actions in movies using weak supervision provided by scripts. Specifically, we extract actor/action pairs from the script and use them as constraints in a discriminative clustering framework. The corresponding optimization problem is formulated as a quadratic program under linear constraints. People in video are represented by automatically extracted and tracked faces together with corresponding motion features. First, we apply the proposed framework to the task of learning names of characters in the movie and demonstrate significant improvements over previous methods used for this task. Second, we explore the joint actor/action constraint and show its advantage for weakly supervised action learning. We validate our method in the challenging setting of localizing and recognizing characters and their actions in feature length movies Casablanca and American Beauty.
Cited literature [25 references]
https://hal.inria.fr/hal-00904991
Contributor : Piotr Bojanowski <>
Submitted on : Friday, November 15, 2013 - 4:26:19 PM
Last modification on : Friday, July 3, 2020 - 4:48:15 PM
Document(s) archivé(s) le : Monday, February 17, 2014 - 4:46:01 PM
Contributor : Piotr Bojanowski <>
Submitted on : Friday, November 15, 2013 - 4:26:19 PM
Last modification on : Friday, July 3, 2020 - 4:48:15 PM
Document(s) archivé(s) le : Monday, February 17, 2014 - 4:46:01 PM
File
joint_learning_names.pdf
Files produced by the author(s)