Papers › Jointly Discovering Visual Objects and Spoken Words from Raw Sensory Input

Jointly Discovering Visual Objects and Spoken Words from Raw Sensory Input

4 Apr 2018ECCV 2018 9arXiv:1804.01452archive 2025-07-28

David Harwath, Adrià Recasens, Dídac Surís, Galen Chuang, Antonio Torralba, James Glass

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.

PaperPDFConference PDF

In Syntology Open this paper in Syntology's Atlas, the map of the papers in Syntology's graph and their citations.

Code

No code repository is listed for this paper in the archive or in Syntology's graph.

Code Syntology ran Syntology

Not run by Syntology. Nothing on this page verifies that the listed code works.

Tasks

RetrievalSound Prompted Semantic SegmentationSpeech Prompted Semantic Segmentation

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Sound Prompted Semantic Segmentation ADE20K DAVENet mAP 16.8 #4 of 4 Archive leaderboard report
Sound Prompted Semantic Segmentation ADE20K DAVENet mIoU 18.1 #4 of 4 Archive leaderboard report
Speech Prompted Semantic Segmentation ADE20K DAVENet mAP 32.2 #2 of 4 Archive leaderboard report
Speech Prompted Semantic Segmentation ADE20K DAVENet mIoU 26.3 #2 of 4 Archive leaderboard report

Ranks are positions in the archive's leaderboards as they stood at the 2025-07-28 snapshot. Results published since then are not among these rows, so a rank here is not a current standing.

Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections