{"about":{"site":"https://codewithpapers.app","non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page"},"url":"/paper/see-hear-and-read-deep-aligned","title":"See, Hear, and Read: Deep Aligned Representations","arxiv_id":"1706.00932","date":"2017-06-03","proceeding":null,"authors":["Yusuf Aytar","Carl Vondrick","Antonio Torralba"],"abstract":"We capitalize on large amounts of readily-available, synchronous data to\nlearn a deep discriminative representations shared across three major natural\nmodalities: vision, sound and language. By leveraging over a year of sound from\nvideo and millions of sentences paired with images, we jointly train a deep\nconvolutional network for aligned representation learning. Our experiments\nsuggest that this representation is useful for several tasks, such as\ncross-modal retrieval or transferring classifiers between modalities. Moreover,\nalthough our network is only trained with image+text and image+sound pairs, it\ncan transfer between text and sound as well, a transfer the network never\nobserved during training. Visualizations of our representation reveal many\nhidden units which automatically emerge to detect concepts, independent of the\nmodality.","url_abs":"http://arxiv.org/abs/1706.00932v1","url_pdf":"http://arxiv.org/pdf/1706.00932v1.pdf","source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","row_kind":"abstracts"},"code_links":[{"paper_slug":"see-hear-and-read-deep-aligned","repo_url":"https://github.com/jingliao132/CrossModalRetrieval","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"unanswered"}}],"tasks":[{"task_slug":"cross-modal-retrieval","task_name":"Cross-Modal Retrieval"},{"task_slug":"representation-learning","task_name":"Representation Learning"},{"task_slug":"retrieval","task_name":"Retrieval"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1706.00932","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}