{"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/vse-improving-visual-semantic-embeddings-with","title":"VSE++: Improving Visual-Semantic Embeddings with Hard Negatives","arxiv_id":"1707.05612","date":"2017-07-18","proceeding":null,"authors":["Fartash Faghri","David J. Fleet","Jamie Ryan Kiros","Sanja Fidler"],"abstract":"We present a new technique for learning visual-semantic embeddings for\ncross-modal retrieval. Inspired by hard negative mining, the use of hard\nnegatives in structured prediction, and ranking loss functions, we introduce a\nsimple change to common loss functions used for multi-modal embeddings. That,\ncombined with fine-tuning and use of augmented data, yields significant gains\nin retrieval performance. We showcase our approach, VSE++, on MS-COCO and\nFlickr30K datasets, using ablation studies and comparisons with existing\nmethods. On MS-COCO our approach outperforms state-of-the-art methods by 8.8%\nin caption retrieval and 11.3% in image retrieval (at R@1).","url_abs":"http://arxiv.org/abs/1707.05612v4","url_pdf":"http://arxiv.org/pdf/1707.05612v4.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":"vse-improving-visual-semantic-embeddings-with","repo_url":"https://github.com/fartashf/vsepp","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"vse-improving-visual-semantic-embeddings-with","repo_url":"https://github.com/Cadene/recipe1m.bootstrap.pytorch","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"unanswered"}},{"paper_slug":"vse-improving-visual-semantic-embeddings-with","repo_url":"https://github.com/armandvilalta/Full-network-multimodal-embeddings","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"none","reach":{"status":"unanswered"}},{"paper_slug":"vse-improving-visual-semantic-embeddings-with","repo_url":"https://github.com/cshizhe/hgr_v2t","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}},{"paper_slug":"vse-improving-visual-semantic-embeddings-with","repo_url":"https://github.com/gorjanradevski/vsepp_tensorflow","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":{"status":"unanswered"}},{"paper_slug":"vse-improving-visual-semantic-embeddings-with","repo_url":"https://github.com/kadarakos/mulisera","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"vse-improving-visual-semantic-embeddings-with","repo_url":"https://github.com/leolee99/CLIP_ITM","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"unanswered"}},{"paper_slug":"vse-improving-visual-semantic-embeddings-with","repo_url":"https://github.com/mitjanikolaus/compositional-image-captioning","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"vse-improving-visual-semantic-embeddings-with","repo_url":"https://github.com/rohitbhaskar/online-ads-repository","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"unanswered"}},{"paper_slug":"vse-improving-visual-semantic-embeddings-with","repo_url":"https://github.com/salanueva/UniVSE","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":"image-retrieval","task_name":"Image Retrieval"},{"task_slug":"retrieval","task_name":"Retrieval"},{"task_slug":"structured-prediction","task_name":"Structured Prediction"},{"task_slug":"visual-reasoning","task_name":"Visual Reasoning"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/cross-modal-retrieval-on-flickr30k","task":"Cross-Modal Retrieval","dataset":"Flickr30k","model":"VSE++\n  (ResNet)","rank_in_archive_order":24,"of":27,"metrics":{"Image-to-text R@1":"52.9","Image-to-text R@10":"87.2","Image-to-text R@5":"80.5","Text-to-image R@1":"39.6","Text-to-image R@10":"79.5","Text-to-image R@5":"70.1"},"uses_additional_data":false}],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1707.05612","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1707.05612"}},"developers":"https://syntology.ai/developers","read_at":"2026-09-24T18:15:14+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/armandvilalta/Full-network-multimodal-embeddings","reach":{"status":"unanswered"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/gorjanradevski/vsepp_tensorflow","reach":{"status":"unanswered"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/rohitbhaskar/online-ads-repository","reach":{"status":"unanswered"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/Cadene/recipe1m.bootstrap.pytorch","reach":{"status":"unanswered"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/salanueva/UniVSE","reach":{"status":"unanswered"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/kadarakos/mulisera","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/mitjanikolaus/compositional-image-captioning","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/fartashf/vsepp","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/cshizhe/hgr_v2t","reach":{"status":"ok","spdx":"MIT"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/leolee99/CLIP_ITM","reach":{"status":"unanswered"}}],"summary":{"ran_draft_wrong":2,"unverified":3},"by_repo_kind":{"official":{"samples":1,"ran":0,"repositories":1},"listed":{"samples":4,"ran":2,"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":4,"samples":[{"code_sha256_prefix":"9b0a787b92a87023","entry":"cosine_sim","repo":"kadarakos/mulisera","repo_kind":"listed","path":"model.py","file_url":"https://github.com/kadarakos/mulisera/blob/HEAD/model.py","link_basis":"first_harvest_node","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"9b0a787b92a87023"}},{"code_sha256_prefix":"741174c85c8d06ad","entry":"l2norm","repo":"kadarakos/mulisera","repo_kind":"listed","path":"model.py","file_url":"https://github.com/kadarakos/mulisera/blob/HEAD/model.py","link_basis":"first_harvest_node","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"741174c85c8d06ad"}},{"code_sha256_prefix":"7052aa5f302958f1","entry":"encode_data","repo":"kadarakos/mulisera","repo_kind":"listed","path":"evaluation.py","file_url":"https://github.com/kadarakos/mulisera/blob/HEAD/evaluation.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"7052aa5f302958f1"}},{"code_sha256_prefix":"abbc3bafa0111c56","entry":"encode_data","repo":"fartashf/vsepp","repo_kind":"official","path":"evaluation.py","file_url":"https://github.com/fartashf/vsepp/blob/HEAD/evaluation.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"abbc3bafa0111c56"}},{"code_sha256_prefix":"3396cb90d1c553f2","entry":"sentencepair_eval","repo":"kadarakos/mulisera","repo_kind":"listed","path":"evaluation.py","file_url":"https://github.com/kadarakos/mulisera/blob/HEAD/evaluation.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"3396cb90d1c553f2"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}