{"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/seeing-what-you-miss-vision-language-pre","title":"Seeing What You Miss: Vision-Language Pre-training with Semantic Completion Learning","arxiv_id":"2211.13437","date":"2022-11-24","proceeding":"CVPR 2023 1","authors":["Yatai Ji","RongCheng Tu","Jie Jiang","Weijie Kong","Chengfei Cai","Wenzhe Zhao","Hongfa Wang","Yujiu Yang","Wei Liu"],"abstract":"Cross-modal alignment is essential for vision-language pre-training (VLP) models to learn the correct corresponding information across different modalities. For this purpose, inspired by the success of masked language modeling (MLM) tasks in the NLP pre-training area, numerous masked modeling tasks have been proposed for VLP to further promote cross-modal interactions. The core idea of previous masked modeling tasks is to focus on reconstructing the masked tokens based on visible context for learning local-to-local alignment. However, most of them pay little attention to the global semantic features generated for the masked data, resulting in a limited cross-modal alignment ability of global representations. Therefore, in this paper, we propose a novel Semantic Completion Learning (SCL) task, complementary to existing masked modeling tasks, to facilitate global-to-local alignment. Specifically, the SCL task complements the missing semantics of masked data by capturing the corresponding information from the other modality, promoting learning more representative global features which have a great impact on the performance of downstream tasks. Moreover, we present a flexible vision encoder, which enables our model to perform image-text and video-text multimodal tasks simultaneously. Experimental results show that our proposed method obtains state-of-the-art performance on various vision-language benchmarks, such as visual question answering, image-text retrieval, and video-text retrieval.","url_abs":"https://arxiv.org/abs/2211.13437v2","url_pdf":"https://arxiv.org/pdf/2211.13437v2.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":"seeing-what-you-miss-vision-language-pre","repo_url":"https://github.com/iigroup/scl","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok"}}],"tasks":[{"task_slug":"image-text-retrieval","task_name":"Image-text Retrieval"},{"task_slug":"language-modeling","task_name":"Language Modeling"},{"task_slug":"language-modelling","task_name":"Language Modelling"},{"task_slug":"masked-language-modeling","task_name":"Masked Language Modeling"},{"task_slug":"question-answering","task_name":"Question Answering"},{"task_slug":"retrieval","task_name":"Retrieval"},{"task_slug":"text-retrieval","task_name":"Text Retrieval"},{"task_slug":"video-text-retrieval","task_name":"Video-Text Retrieval"},{"task_slug":"visual-question-answering-1","task_name":"Visual Question Answering"},{"task_slug":"visual-question-answering","task_name":"Visual Question Answering (VQA)"},{"task_slug":"zero-shot-video-retrieval","task_name":"Zero-Shot Video Retrieval"},{"task_slug":"cross-modal-alignment","task_name":"cross-modal alignment"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/zero-shot-video-retrieval-on-lsmdc","task":"Zero-Shot Video Retrieval","dataset":"LSMDC","model":"Yatai Ji et. al.","rank_in_archive_order":10,"of":16,"metrics":{"text-to-video R@1":"17.2","text-to-video R@10":"39.1","text-to-video R@5":"32.4"},"uses_additional_data":false},{"leaderboard":"/sota/zero-shot-video-retrieval-on-msr-vtt","task":"Zero-Shot Video Retrieval","dataset":"MSR-VTT","model":"Yatai Ji et. al.","rank_in_archive_order":22,"of":41,"metrics":{"text-to-video R@1":"30.9","text-to-video R@10":"65.0","text-to-video R@5":"54.4"},"uses_additional_data":false}],"syntology":{"syntology_url":"https://syntology.ai/paper/2211.13437","atlas_url":"https://app.syntology.ai/?focus=2211.13437","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}