Timezone: »
Given a corpus of news items consisting of images accompanied by text captions, we want to find out `whos doing what, i.e. associate names and action verbs in the captions to the face and body pose of the persons in the images. We present a joint model for simultaneously solving the image-caption correspondences and learning visual appearance models for the face and pose classes occurring in the corpus. These models can then be used to recognize people and actions in novel images without captions. We demonstrate experimentally that our joint
face and pose model solves the correspondence problem better than earlier models covering only the face, and that it can perform recognition of new uncaptioned images.
Author Information
Jie Luo (Snap Inc.)
Barbara Caputo (Politecnico di Torino)
Vittorio Ferrari (University of Edinburgh)
More from the Same Authors
-
2023 Poster: StoryBench: A Multifaceted Benchmark for Continuous Story Visualization »
Emanuele Bugliarello · H. Hernan Moraldo · Ruben Villegas · Mohammad Babaeizadeh · Mohammad Taghi Saffar · Han Zhang · Dumitru Erhan · Vittorio Ferrari · Pieter-Jan Kindermans · Paul Voigtlaender -
2023 Poster: Estimating Generic 3D Room Structures from 2D Annotations »
Denys Rozumnyi · Stefan Popov · Kevis-kokitsi Maninis · Matthias Niessner · Vittorio Ferrari -
2023 Poster: NAVI: Category-Agnostic Image Collections with High-Quality 3D Shape and Pose Annotations »
Varun Jampani · Kevis-kokitsi Maninis · Andreas Engelhardt · Arjun Karpur · Karen Truong · Kyle Sargent · Stefan Popov · Andre Araujo · Ricardo Martin Brualla · Kaushal Patel · Daniel Vlasic · Vittorio Ferrari · Ameesh Makadia · Ce Liu · Yuanzhen Li · Howard Zhou -
2021 : Live panel: The future of ImageNet »
Matthias Bethge · Vittorio Ferrari · Olga Russakovsky -
2021 : OpenImages: One Dataset for Many Computer Vision Tasks »
Vittorio Ferrari -
2012 Poster: Searching for objects driven by context »
Bogdan Alexe · Nicolas Heess · Yee Whye Teh · Vittorio Ferrari -
2012 Spotlight: Searching for objects driven by context »
Bogdan Alexe · Nicolas Heess · Yee Whye Teh · Vittorio Ferrari -
2011 Poster: Exploiting spatial overlap to efficiently compute appearance distances between image windows »
Bogdan Alexe · Viviana Petrescu · Vittorio Ferrari -
2010 Spotlight: Learning from Candidate Labeling Sets »
Jie Luo · Francesco Orabona -
2010 Poster: Learning from Candidate Labeling Sets »
Jie Luo · Francesco Orabona -
2009 Workshop: Learning from Multiple Sources with Applications to Robotics »
Barbara Caputo · Nicolò Cesa-Bianchi · David R Hardoon · Gayle Leen · Francesco Orabona · Jaakko Peltonen · Simon Rogers -
2008 Poster: Beyond Novelty Detection: Incongruent Events, when General and Specific Classifiers Disagree »
Daphna Weinshall · Hynek Hermansky · Alon Zweig · Jie Luo · Holly B Jimison · Frank W Ohl · Misha Pavel -
2008 Oral: Beyond Novelty Detection: Incongruent Events, when General and Specific Classifiers Disagree »
Daphna Weinshall · Hynek Hermansky · Alon Zweig · Jie Luo · Holly B Jimison · Frank W Ohl · Misha Pavel -
2007 Spotlight: Learning Visual Attributes »
Vittorio Ferrari · Andrew Zisserman -
2007 Poster: Learning Visual Attributes »
Vittorio Ferrari · Andrew Zisserman