This is not the latest version of this item. The latest version can be found here.
Jointly Discovering Visual Objects and Spoken Words from Raw Sensory Input
Name
11263_2019_1205_ReferencePDF.pdf
Size
39.36 MB
Format
Adobe PDF
Checksum (MD5)
18a4a38af04d227d45d2f76b07d12f07
Author(s)
Harwath, David
Recasens, Adrià
Surís, Dídac
Chuang, Galen
Torralba, Antonio
Glass, James
Date Issued
August 5, 2019
Publisher
Springer US
Version
Author's final manuscript
Abstract
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.
Terms of Use
Creative Commons Attribution-Noncommercial-Share Alike
Persistent DSpace Link
DOI of Published Version
https://doi.org/10.1007/s11263-019-01205-0
