{"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/zero-shot-referring-expression-comprehension","title":"Zero-shot Referring Expression Comprehension via Structural Similarity Between Images and Captions","arxiv_id":"2311.17048","date":"2023-11-28","proceeding":"CVPR 2024 1","authors":["Zeyu Han","Fangrui Zhu","Qianru Lao","Huaizu Jiang"],"abstract":"Zero-shot referring expression comprehension aims at localizing bounding boxes in an image corresponding to provided textual prompts, which requires: (i) a fine-grained disentanglement of complex visual scene and textual context, and (ii) a capacity to understand relationships among disentangled entities. Unfortunately, existing large vision-language alignment (VLA) models, e.g., CLIP, struggle with both aspects so cannot be directly used for this task. To mitigate this gap, we leverage large foundation models to disentangle both images and texts into triplets in the format of (subject, predicate, object). After that, grounding is accomplished by calculating the structural similarity matrix between visual and textual triplets with a VLA model, and subsequently propagate it to an instance-level similarity matrix. Furthermore, to equip VLA models with the ability of relationship understanding, we design a triplet-matching objective to fine-tune the VLA models on a collection of curated dataset containing abundant entity relationships. Experiments demonstrate that our visual grounding performance increase of up to 19.5% over the SOTA zero-shot model on RefCOCO/+/g. On the more challenging Who's Waldo dataset, our zero-shot approach achieves comparable accuracy to the fully supervised model. Code is available at https://github.com/Show-han/Zeroshot_REC.","url_abs":"https://arxiv.org/abs/2311.17048v3","url_pdf":"https://arxiv.org/pdf/2311.17048v3.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":"zero-shot-referring-expression-comprehension","repo_url":"https://github.com/show-han/zeroshot_rec","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"Apache-2.0"}}],"tasks":[{"task_slug":"disentanglement","task_name":"Disentanglement"},{"task_slug":"referring-expression","task_name":"Referring Expression"},{"task_slug":"referring-expression-comprehension","task_name":"Referring Expression Comprehension"},{"task_slug":null,"task_name":"Triplet"},{"task_slug":"visual-grounding","task_name":"Visual Grounding"}],"methods":[{"method_slug":"clip","method_name":"CLIP"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2311.17048","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2311.17048"}},"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/show-han/zeroshot_rec","reach":{"status":"ok","spdx":"Apache-2.0"}}],"summary":{"ran_draft_wrong":4,"ran":6,"ran_violates":3,"unverified":7},"by_repo_kind":{"official":{"samples":20,"ran":13,"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":"98f385d847636a3e","entry":"basic_clean","repo":"show-han/zeroshot_rec","repo_kind":"official","path":"VLA_finetune/open_clip/tokenizer.py","file_url":"https://github.com/show-han/zeroshot_rec/blob/HEAD/VLA_finetune/open_clip/tokenizer.py","link_basis":"harvester_set","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":true,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"98f385d847636a3e"}},{"code_sha256_prefix":"d919ae32e5e4e616","entry":"get_pairs","repo":"show-han/zeroshot_rec","repo_kind":"official","path":"VLA_finetune/open_clip/tokenizer.py","file_url":"https://github.com/show-han/zeroshot_rec/blob/HEAD/VLA_finetune/open_clip/tokenizer.py","link_basis":"harvester_set","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"d919ae32e5e4e616"}},{"code_sha256_prefix":"181856ae1295b257","entry":"image_transform","repo":"show-han/zeroshot_rec","repo_kind":"official","path":"VLA_finetune/open_clip/transform.py","file_url":"https://github.com/show-han/zeroshot_rec/blob/HEAD/VLA_finetune/open_clip/transform.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":"181856ae1295b257"}},{"code_sha256_prefix":"b3288ad88c4922cc","entry":"is_bbox_invalid","repo":"show-han/zeroshot_rec","repo_kind":"official","path":"VLA_finetune/training/data.py","file_url":"https://github.com/show-han/zeroshot_rec/blob/HEAD/VLA_finetune/training/data.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":"b3288ad88c4922cc"}},{"code_sha256_prefix":"7c29b374198bddcd","entry":"is_global_master","repo":"show-han/zeroshot_rec","repo_kind":"official","path":"VLA_finetune/training/distributed.py","file_url":"https://github.com/show-han/zeroshot_rec/blob/HEAD/VLA_finetune/training/distributed.py","link_basis":"harvester_set","language":"python","status":"ran_violates","verification_level":1,"contract_check":"VIOLATES","metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"7c29b374198bddcd"}},{"code_sha256_prefix":"0377e309e95cfc3e","entry":"is_local_master","repo":"show-han/zeroshot_rec","repo_kind":"official","path":"VLA_finetune/training/distributed.py","file_url":"https://github.com/show-han/zeroshot_rec/blob/HEAD/VLA_finetune/training/distributed.py","link_basis":"harvester_set","language":"python","status":"ran_violates","verification_level":1,"contract_check":"VIOLATES","metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"0377e309e95cfc3e"}},{"code_sha256_prefix":"b092791002b40e8a","entry":"is_master","repo":"show-han/zeroshot_rec","repo_kind":"official","path":"VLA_finetune/training/distributed.py","file_url":"https://github.com/show-han/zeroshot_rec/blob/HEAD/VLA_finetune/training/distributed.py","link_basis":"harvester_set","language":"python","status":"ran_violates","verification_level":1,"contract_check":"VIOLATES","metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"b092791002b40e8a"}},{"code_sha256_prefix":"8b49391377816761","entry":"list_pretrained_tag_models","repo":"show-han/zeroshot_rec","repo_kind":"official","path":"VLA_finetune/open_clip/pretrained.py","file_url":"https://github.com/show-han/zeroshot_rec/blob/HEAD/VLA_finetune/open_clip/pretrained.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":"8b49391377816761"}},{"code_sha256_prefix":"ad4accadc0057d93","entry":"load_checkpoint","repo":"show-han/zeroshot_rec","repo_kind":"official","path":"VLA_finetune/open_clip/factory.py","file_url":"https://github.com/show-han/zeroshot_rec/blob/HEAD/VLA_finetune/open_clip/factory.py","link_basis":"harvester_set","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":"ad4accadc0057d93"}},{"code_sha256_prefix":"4b3a4d17e1df3140","entry":"load_state_dict","repo":"show-han/zeroshot_rec","repo_kind":"official","path":"VLA_finetune/open_clip/factory.py","file_url":"https://github.com/show-han/zeroshot_rec/blob/HEAD/VLA_finetune/open_clip/factory.py","link_basis":"harvester_set","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":"4b3a4d17e1df3140"}},{"code_sha256_prefix":"8e95157106d1df8c","entry":"trace_model","repo":"show-han/zeroshot_rec","repo_kind":"official","path":"VLA_finetune/open_clip/model.py","file_url":"https://github.com/show-han/zeroshot_rec/blob/HEAD/VLA_finetune/open_clip/model.py","link_basis":"harvester_set","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"8e95157106d1df8c"}},{"code_sha256_prefix":"149543b13e8a1623","entry":"union_bbox","repo":"show-han/zeroshot_rec","repo_kind":"official","path":"VLA_finetune/training/data.py","file_url":"https://github.com/show-han/zeroshot_rec/blob/HEAD/VLA_finetune/training/data.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":"149543b13e8a1623"}},{"code_sha256_prefix":"9542161e9640b858","entry":"whitespace_clean","repo":"show-han/zeroshot_rec","repo_kind":"official","path":"VLA_finetune/open_clip/tokenizer.py","file_url":"https://github.com/show-han/zeroshot_rec/blob/HEAD/VLA_finetune/open_clip/tokenizer.py","link_basis":"harvester_set","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":true,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"9542161e9640b858"}},{"code_sha256_prefix":"e209d001d7c966cf","entry":"build_model_from_openai_state_dict","repo":"show-han/zeroshot_rec","repo_kind":"official","path":"VLA_finetune/open_clip/model.py","file_url":"https://github.com/show-han/zeroshot_rec/blob/HEAD/VLA_finetune/open_clip/model.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":"e209d001d7c966cf"}},{"code_sha256_prefix":"23d02ffb86d06cff","entry":"create_model","repo":"show-han/zeroshot_rec","repo_kind":"official","path":"VLA_finetune/open_clip/factory.py","file_url":"https://github.com/show-han/zeroshot_rec/blob/HEAD/VLA_finetune/open_clip/factory.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":"23d02ffb86d06cff"}},{"code_sha256_prefix":"9b5765523c6d17fd","entry":"freeze_batch_norm_2d","repo":"show-han/zeroshot_rec","repo_kind":"official","path":"VLA_finetune/open_clip/utils.py","file_url":"https://github.com/show-han/zeroshot_rec/blob/HEAD/VLA_finetune/open_clip/utils.py","link_basis":"harvester_set","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":"9b5765523c6d17fd"}},{"code_sha256_prefix":"ddcbd45e940484ee","entry":"gather_features","repo":"show-han/zeroshot_rec","repo_kind":"official","path":"VLA_finetune/open_clip/loss.py","file_url":"https://github.com/show-han/zeroshot_rec/blob/HEAD/VLA_finetune/open_clip/loss.py","link_basis":"harvester_set","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":"ddcbd45e940484ee"}},{"code_sha256_prefix":"2d83d0f60f01d050","entry":"list_pretrained","repo":"show-han/zeroshot_rec","repo_kind":"official","path":"VLA_finetune/open_clip/pretrained.py","file_url":"https://github.com/show-han/zeroshot_rec/blob/HEAD/VLA_finetune/open_clip/pretrained.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":"2d83d0f60f01d050"}},{"code_sha256_prefix":"8ce0ee4c850e934d","entry":"list_pretrained_model_tags","repo":"show-han/zeroshot_rec","repo_kind":"official","path":"VLA_finetune/open_clip/pretrained.py","file_url":"https://github.com/show-han/zeroshot_rec/blob/HEAD/VLA_finetune/open_clip/pretrained.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":"8ce0ee4c850e934d"}},{"code_sha256_prefix":"f22c4b3b6fb51672","entry":"load_openai_model","repo":"show-han/zeroshot_rec","repo_kind":"official","path":"VLA_finetune/open_clip/openai.py","file_url":"https://github.com/show-han/zeroshot_rec/blob/HEAD/VLA_finetune/open_clip/openai.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":"f22c4b3b6fb51672"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}