{"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/opt-omni-perception-pre-trainer-for-cross","title":"OPT: Omni-Perception Pre-Trainer for Cross-Modal Understanding and Generation","arxiv_id":"2107.00249","date":"2021-07-01","proceeding":null,"authors":["Jing Liu","Xinxin Zhu","Fei Liu","Longteng Guo","Zijia Zhao","Mingzhen Sun","Weining Wang","Hanqing Lu","Shiyu Zhou","Jiajun Zhang","Jinqiao Wang"],"abstract":"In this paper, we propose an Omni-perception Pre-Trainer (OPT) for cross-modal understanding and generation, by jointly modeling visual, text and audio resources. OPT is constructed in an encoder-decoder framework, including three single-modal encoders to generate token-based embeddings for each modality, a cross-modal encoder to encode the correlations among the three modalities, and two cross-modal decoders to generate text and image respectively. For the OPT's pre-training, we design a multi-task pretext learning scheme to model multi-modal resources from three different data granularities, \\ie, token-, modality-, and sample-level modeling, through which OPT learns to align and translate among different modalities. The pre-training task is carried out on a large amount of image-text-audio triplets from Open Images. Experimental results show that OPT can learn strong image-text-audio multi-modal representations and achieve promising results on a variety of cross-modal understanding and generation tasks.","url_abs":"https://arxiv.org/abs/2107.00249v2","url_pdf":"https://arxiv.org/pdf/2107.00249v2.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":"opt-omni-perception-pre-trainer-for-cross","repo_url":"https://github.com/2023-MindSpore-1/ms-code-161","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"mindspore","reach":{"status":"ok"}},{"paper_slug":"opt-omni-perception-pre-trainer-for-cross","repo_url":"https://github.com/mindspore-ai/models/tree/master/research/mm/opt","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"mindspore","reach":null}],"tasks":[{"task_slug":"audio-to-text-retrieval","task_name":"Audio to Text Retrieval"},{"task_slug":"cross-modal-retrieval","task_name":"Cross-Modal Retrieval"},{"task_slug":"decoder","task_name":"Decoder"},{"task_slug":"image-retrieval","task_name":"Image Retrieval"},{"task_slug":"image-to-text-retrieval","task_name":"Image-to-Text Retrieval"},{"task_slug":"text-to-audio-retrieval","task_name":"Text to Audio Retrieval"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/image-retrieval-on-localized-narratives","task":"Image Retrieval","dataset":"Localized Narratives","model":"OPT","rank_in_archive_order":1,"of":1,"metrics":{"Text-to-image R@1":"0.4196","Text-to-image R@10":"0.8126","Text-to-image R@5":"0.72"},"uses_additional_data":false},{"leaderboard":"/sota/text-to-audio-retrieval-on-localized","task":"Text to Audio Retrieval","dataset":"Localized Narratives","model":"OPT","rank_in_archive_order":1,"of":1,"metrics":{"Text-to-audio R@1":"0.78","Text-to-audio R@10":"0.958","Text-to-audio R@5":"0.927"},"uses_additional_data":false}],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2107.00249","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}