Jointly Discovering Visual Objects and Spoken Words from Raw Sensory Input
Name
1804.01452.pdf
Description
Submitted version
Size
4.66 MB
Format
Adobe PDF
Checksum (MD5)
e24d35ed205227d26d83c43a1fc44fed
Author(s)
Harwath, David F.
Recasens, Adria
Suris Coll-Vinent, Didac
Chuang, Galen
Torralba, Antonio
Glass, James R
Date Issued
October 6, 2018
Journal
Computer Vision – ECCV 2018
Publisher
Springer International Publishing
Citation
Harwath, David et al. "Jointly Discovering Visual Objects and Spoken Words from Raw Sensory Input." Computer Vision – ECCV 2018, September 8–14, 2018, Munich, Germany, edited by V. Ferrari et al., Springer, 2018
Version
Original manuscript
Abstract
In this paper, we explore neural network models that learn to associate segments of spoken audio captions with the semantically relevant portions of natural images that they refer to. We demonstrate that these audio-visual associative localizations emerge from network-internal representations learned as a by-product of training to perform an image-audio retrieval task. Our models operate directly on the image pixels and speech waveform, and do not rely on any conventional supervision in the form of labels, segmentations, or alignments between the modalities during training. We perform analysis using the Places 205 and ADE20k datasets demonstrating that our models implicitly learn semantically-coupled object and word detectors. Keywords: vision and language; sound; speech; convolutional networks; multimodal learning; unsupervised learning
MIT Department
Massachusetts Institute of Technology. Computer Science and Artificial Intelligence Laboratory
Massachusetts Institute of Technology. Department of Electrical Engineering and Computer Science
Terms of Use
Creative Commons Attribution-Noncommercial-Share Alike
Persistent DSpace Link
DOI of Published Version
https://doi.org/10.1007/978-3-030-01231-1_40
