{"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/3shnet-boosting-image-sentence-retrieval-via","title":"3SHNet: Boosting Image-Sentence Retrieval via Visual Semantic-Spatial Self-Highlighting","arxiv_id":"2404.17273","date":"2024-04-26","proceeding":null,"authors":["Xuri Ge","Songpei Xu","Fuhai Chen","Jie Wang","Guoxin Wang","Shan An","Joemon M. Jose"],"abstract":"In this paper, we propose a novel visual Semantic-Spatial Self-Highlighting Network (termed 3SHNet) for high-precision, high-efficiency and high-generalization image-sentence retrieval. 3SHNet highlights the salient identification of prominent objects and their spatial locations within the visual modality, thus allowing the integration of visual semantics-spatial interactions and maintaining independence between two modalities. This integration effectively combines object regions with the corresponding semantic and position layouts derived from segmentation to enhance the visual representation. And the modality-independence guarantees efficiency and generalization. Additionally, 3SHNet utilizes the structured contextual visual scene information from segmentation to conduct the local (region-based) or global (grid-based) guidance and achieve accurate hybrid-level retrieval. Extensive experiments conducted on MS-COCO and Flickr30K benchmarks substantiate the superior performances, inference efficiency and generalization of the proposed 3SHNet when juxtaposed with contemporary state-of-the-art methodologies. Specifically, on the larger MS-COCO 5K test set, we achieve 16.3%, 24.8%, and 18.3% improvements in terms of rSum score, respectively, compared with the state-of-the-art methods using different image representations, while maintaining optimal retrieval efficiency. Moreover, our performance on cross-dataset generalization improves by 18.6%. Data and code are available at https://github.com/XuriGe1995/3SHNet.","url_abs":"https://arxiv.org/abs/2404.17273v1","url_pdf":"https://arxiv.org/pdf/2404.17273v1.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":"3shnet-boosting-image-sentence-retrieval-via","repo_url":"https://github.com/xurige1995/3shnet","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"pytorch","reach":{"status":"ok","spdx":"Apache-2.0"}}],"tasks":[{"task_slug":"cross-modal-retrieval","task_name":"Cross-Modal Retrieval"},{"task_slug":"retrieval","task_name":"Retrieval"},{"task_slug":"sentence","task_name":"Sentence"},{"task_slug":"sentence-retrieval","task_name":"Sentence Retrieval"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/cross-modal-retrieval-on-coco-2014","task":"Cross-Modal Retrieval","dataset":"COCO 2014","model":"3SHNet","rank_in_archive_order":23,"of":36,"metrics":{"Image-to-text R@1":"67.9","Image-to-text R@10":"95.4","Image-to-text R@5":"90.5","Text-to-image R@1":"50.3","Text-to-image R@10":"87.7","Text-to-image R@5":"79.3"},"uses_additional_data":false},{"leaderboard":"/sota/cross-modal-retrieval-on-flickr30k","task":"Cross-Modal Retrieval","dataset":"Flickr30k","model":"3SHNet","rank_in_archive_order":12,"of":27,"metrics":{"Image-to-text R@1":"87.1","Image-to-text R@10":"99.2","Image-to-text R@5":"98.2","Text-to-image R@1":"69.5","Text-to-image R@10":"94.7","Text-to-image R@5":"91.0"},"uses_additional_data":false},{"leaderboard":"/sota/cross-modal-retrieval-on-mscoco","task":"Cross-Modal Retrieval","dataset":"MSCOCO","model":"3SHNet","rank_in_archive_order":1,"of":1,"metrics":{"Image-to-text R@1":"85.8"},"uses_additional_data":false}],"syntology":{"syntology_url":"https://syntology.ai/paper/2404.17273","atlas_url":"https://app.syntology.ai/?focus=2404.17273","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2404.17273"}},"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/xurige1995/3shnet","reach":{"status":"ok","spdx":"Apache-2.0"}}],"summary":{"ran":8,"ran_draft_wrong":2},"by_repo_kind":{"official":{"samples":10,"ran":10,"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":"92939f518491d46a","entry":"compute_sim","repo":"xurige1995/3shnet","repo_kind":"official","path":"lib/evaluation_rgn_seg_sp_se.py","file_url":"https://github.com/xurige1995/3shnet/blob/HEAD/lib/evaluation_rgn_seg_sp_se.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"92939f518491d46a"}},{"code_sha256_prefix":"61e35a6b0af63e50","entry":"default_collate_override","repo":"xurige1995/3shnet","repo_kind":"official","path":"eval_rgn_seg_sp_se.py","file_url":"https://github.com/xurige1995/3shnet/blob/HEAD/eval_rgn_seg_sp_se.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"61e35a6b0af63e50"}},{"code_sha256_prefix":"56b228e2d72c6b46","entry":"encode_data","repo":"xurige1995/3shnet","repo_kind":"official","path":"lib/evaluation_rgn_seg_sp_se.py","file_url":"https://github.com/xurige1995/3shnet/blob/HEAD/lib/evaluation_rgn_seg_sp_se.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"56b228e2d72c6b46"}},{"code_sha256_prefix":"a624aee24b1da924","entry":"encode_data","repo":"xurige1995/3shnet","repo_kind":"official","path":"lib/evaluation_rgn_seg_sp_se_cross.py","file_url":"https://github.com/xurige1995/3shnet/blob/HEAD/lib/evaluation_rgn_seg_sp_se_cross.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"a624aee24b1da924"}},{"code_sha256_prefix":"dd78f2924d527191","entry":"func_attention","repo":"xurige1995/3shnet","repo_kind":"official","path":"lib/Crossmodal_Fusion4_sm.py","file_url":"https://github.com/xurige1995/3shnet/blob/HEAD/lib/Crossmodal_Fusion4_sm.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"dd78f2924d527191"}},{"code_sha256_prefix":"9e0a6b0cf8aa2ef0","entry":"func_attention","repo":"xurige1995/3shnet","repo_kind":"official","path":"lib/Crossmodal_Fusion4_sp.py","file_url":"https://github.com/xurige1995/3shnet/blob/HEAD/lib/Crossmodal_Fusion4_sp.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"9e0a6b0cf8aa2ef0"}},{"code_sha256_prefix":"64aed5eaff276e96","entry":"i2t","repo":"xurige1995/3shnet","repo_kind":"official","path":"lib/evaluation_rgn_seg_sp_se.py","file_url":"https://github.com/xurige1995/3shnet/blob/HEAD/lib/evaluation_rgn_seg_sp_se.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"64aed5eaff276e96"}},{"code_sha256_prefix":"9bf455ab09372ab4","entry":"l1norm","repo":"xurige1995/3shnet","repo_kind":"official","path":"lib/Crossmodal_Fusion4_sm.py","file_url":"https://github.com/xurige1995/3shnet/blob/HEAD/lib/Crossmodal_Fusion4_sm.py","link_basis":"plan_row","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"9bf455ab09372ab4"}},{"code_sha256_prefix":"be7c4a676b9f1e19","entry":"l2norm","repo":"xurige1995/3shnet","repo_kind":"official","path":"lib/Crossmodal_Fusion4_sm.py","file_url":"https://github.com/xurige1995/3shnet/blob/HEAD/lib/Crossmodal_Fusion4_sm.py","link_basis":"plan_row","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"be7c4a676b9f1e19"}},{"code_sha256_prefix":"84519de0fc36134e","entry":"maxk_pool1d_var","repo":"xurige1995/3shnet","repo_kind":"official","path":"lib/encoders_rgn_seg_sp_se.py","file_url":"https://github.com/xurige1995/3shnet/blob/HEAD/lib/encoders_rgn_seg_sp_se.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"84519de0fc36134e"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}