Jointly Discovering Visual Objects and Spoken Words from Raw Sensory Input
David Harwath, Adria Recasens, Didac Suris, Galen Chuang, Antonio Torralba, James Glass
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.
BibTeX
@inproceedings{eccv2018_jointlydiscoveri,
title = {Jointly Discovering Visual Objects and Spoken Words from Raw Sensory Input},
author = {David Harwath and Adria Recasens and Didac Suris and Galen Chuang and Antonio Torralba and James Glass},
booktitle = {ECCV 2018},
year = {2018}
}