{"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/polysemous-visual-semantic-embedding-for-1","title":"Polysemous Visual-Semantic Embedding for Cross-Modal Retrieval","arxiv_id":"1906.04402","date":"2019-06-11","proceeding":"CVPR 2019 6","authors":["Yale Song","Mohammad Soleymani"],"abstract":"Visual-semantic embedding aims to find a shared latent space where related visual and textual instances are close to each other. Most current methods learn injective embedding functions that map an instance to a single point in the shared space. Unfortunately, injective embedding cannot effectively handle polysemous instances with multiple possible meanings; at best, it would find an average representation of different meanings. This hinders its use in real-world scenarios where individual instances and their cross-modal associations are often ambiguous. In this work, we introduce Polysemous Instance Embedding Networks (PIE-Nets) that compute multiple and diverse representations of an instance by combining global context with locally-guided features via multi-head self-attention and residual learning. To learn visual-semantic embedding, we tie-up two PIE-Nets and optimize them jointly in the multiple instance learning framework. Most existing work on cross-modal retrieval focuses on image-text data. Here, we also tackle a more challenging case of video-text retrieval. To facilitate further research in video-text retrieval, we release a new dataset of 50K video-sentence pairs collected from social media, dubbed MRW (my reaction when). We demonstrate our approach on both image-text and video-text retrieval scenarios using MS-COCO, TGIF, and our new MRW dataset.","url_abs":"https://arxiv.org/abs/1906.04402v2","url_pdf":"https://arxiv.org/pdf/1906.04402v2.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":"polysemous-visual-semantic-embedding-for-1","repo_url":"https://github.com/yalesong/pvse","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}}],"tasks":[{"task_slug":"cross-modal-retrieval","task_name":"Cross-Modal Retrieval"},{"task_slug":"multiple-instance-learning","task_name":"Multiple Instance Learning"},{"task_slug":"retrieval","task_name":"Retrieval"},{"task_slug":"sentence","task_name":"Sentence"},{"task_slug":"text-retrieval","task_name":"Text Retrieval"},{"task_slug":"video-text-retrieval","task_name":"Video-Text Retrieval"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/cross-modal-retrieval-on-coco-2014","task":"Cross-Modal Retrieval","dataset":"COCO 2014","model":"PVSE","rank_in_archive_order":34,"of":36,"metrics":{"Image-to-text R@1":"45.2","Image-to-text R@10":"84.5","Image-to-text R@5":"74.3","Text-to-image R@1":"32.4","Text-to-image R@10":"75.0","Text-to-image R@5":"63.0"},"uses_additional_data":false}],"syntology":{"syntology_url":"https://syntology.ai/paper/1906.04402","atlas_url":"https://app.syntology.ai/?focus=1906.04402","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1906.04402"}},"developers":"https://syntology.ai/developers","read_at":"2026-09-25T09:33:49+00:00","read_at_is":"when the build read Syntology's graph, not when any sample ran","claim":"Per-sample execution status on synthesized fixtures; not a correctness claim about the paper. Samples come from repositories linked to the paper, official or community; repo_kind says which.","repos":[{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/yalesong/pvse","reach":{"status":"ok","spdx":"MIT"}}],"summary":{"ran":12},"by_repo_kind":{"listed":{"samples":12,"ran":12,"repositories":1}},"repo_kind_vocabulary":{"official":"The archive marks this repository official for the paper","named_in_paper":"The archive records that the paper mentions this repository; it is not marked official","listed":"In the archive's code links for this paper, not marked official and not recorded as mentioned in the paper","found_in_text":"Syntology found this repository in the paper's own text; whether it is the authors' implementation is not asserted","community":"Not in the archive's code links for this paper; a community repository Syntology harvested"},"n_pointer_only_for_licence":0,"samples":[{"code_sha256_prefix":"067569ab2ca0cb91","entry":"collate_fn","repo":"yalesong/pvse","repo_kind":"listed","path":"data.py","file_url":"https://github.com/yalesong/pvse/blob/HEAD/data.py","link_basis":"harvester_set","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"067569ab2ca0cb91"}},{"code_sha256_prefix":"e42286bdac3eb647","entry":"cosine_sim","repo":"yalesong/pvse","repo_kind":"listed","path":"loss.py","file_url":"https://github.com/yalesong/pvse/blob/HEAD/loss.py","link_basis":"harvester_set","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"e42286bdac3eb647"}},{"code_sha256_prefix":"bea183ae94fb8b9d","entry":"from_mrw_json","repo":"yalesong/pvse","repo_kind":"listed","path":"vocab.py","file_url":"https://github.com/yalesong/pvse/blob/HEAD/vocab.py","link_basis":"harvester_set","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"bea183ae94fb8b9d"}},{"code_sha256_prefix":"fd9b502b79464525","entry":"from_tgif_tsv","repo":"yalesong/pvse","repo_kind":"listed","path":"vocab.py","file_url":"https://github.com/yalesong/pvse/blob/HEAD/vocab.py","link_basis":"harvester_set","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"fd9b502b79464525"}},{"code_sha256_prefix":"2a091499b862ef78","entry":"get_cnn","repo":"yalesong/pvse","repo_kind":"listed","path":"model.py","file_url":"https://github.com/yalesong/pvse/blob/HEAD/model.py","link_basis":"harvester_set","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"2a091499b862ef78"}},{"code_sha256_prefix":"38b1696acd2ad684","entry":"get_pad_mask","repo":"yalesong/pvse","repo_kind":"listed","path":"model.py","file_url":"https://github.com/yalesong/pvse/blob/HEAD/model.py","link_basis":"harvester_set","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"38b1696acd2ad684"}},{"code_sha256_prefix":"9919713948f52bff","entry":"get_paths","repo":"yalesong/pvse","repo_kind":"listed","path":"data.py","file_url":"https://github.com/yalesong/pvse/blob/HEAD/data.py","link_basis":"harvester_set","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"9919713948f52bff"}},{"code_sha256_prefix":"41c61aa3138d76aa","entry":"get_uid_tgif","repo":"yalesong/pvse","repo_kind":"listed","path":"data.py","file_url":"https://github.com/yalesong/pvse/blob/HEAD/data.py","link_basis":"harvester_set","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"41c61aa3138d76aa"}},{"code_sha256_prefix":"7db07517e868f2bd","entry":"l2norm","repo":"yalesong/pvse","repo_kind":"listed","path":"loss.py","file_url":"https://github.com/yalesong/pvse/blob/HEAD/loss.py","link_basis":"harvester_set","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"7db07517e868f2bd"}},{"code_sha256_prefix":"0e45ef681f2e9391","entry":"l2norm","repo":"yalesong/pvse","repo_kind":"listed","path":"model.py","file_url":"https://github.com/yalesong/pvse/blob/HEAD/model.py","link_basis":"harvester_set","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"0e45ef681f2e9391"}},{"code_sha256_prefix":"27932a44f7af1fe7","entry":"order_sim","repo":"yalesong/pvse","repo_kind":"listed","path":"loss.py","file_url":"https://github.com/yalesong/pvse/blob/HEAD/loss.py","link_basis":"harvester_set","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"27932a44f7af1fe7"}},{"code_sha256_prefix":"1a7561ed4bd4cf47","entry":"verify_input_args","repo":"yalesong/pvse","repo_kind":"listed","path":"option.py","file_url":"https://github.com/yalesong/pvse/blob/HEAD/option.py","link_basis":"harvester_set","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"1a7561ed4bd4cf47"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}