{"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/extending-phrase-grounding-with-pronouns-in","title":"Extending Phrase Grounding with Pronouns in Visual Dialogues","arxiv_id":"2210.12658","date":"2022-10-23","proceeding":null,"authors":["Panzhong Lu","Xin Zhang","Meishan Zhang","Min Zhang"],"abstract":"Conventional phrase grounding aims to localize noun phrases mentioned in a given caption to their corresponding image regions, which has achieved great success recently. Apparently, sole noun phrase grounding is not enough for cross-modal visual language understanding. Here we extend the task by considering pronouns as well. First, we construct a dataset of phrase grounding with both noun phrases and pronouns to image regions. Based on the dataset, we test the performance of phrase grounding by using a state-of-the-art literature model of this line. Then, we enhance the baseline grounding model with coreference information which should help our task potentially, modeling the coreference structures with graph convolutional networks. Experiments on our dataset, interestingly, show that pronouns are easier to ground than noun phrases, where the possible reason might be that these pronouns are much less ambiguous. Additionally, our final model with coreference information can significantly boost the grounding performance of both noun phrases and pronouns.","url_abs":"https://arxiv.org/abs/2210.12658v1","url_pdf":"https://arxiv.org/pdf/2210.12658v1.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":"extending-phrase-grounding-with-pronouns-in","repo_url":"https://github.com/izhx/phrase-grounding-with-pronoun","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"pytorch","reach":{"status":"ok","spdx":"Apache-2.0"}}],"tasks":[{"task_slug":"phrase-grounding","task_name":"Phrase Grounding"}],"methods":[{"method_slug":"test","method_name":"Test"}],"datasets_introduced":[{"slug":"vd-ref","name":"VD-Ref","full_name":""}],"methods_introduced":[],"results":[],"syntology":{"syntology_url":"https://syntology.ai/paper/2210.12658","atlas_url":"https://app.syntology.ai/?focus=2210.12658","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2210.12658"}},"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":"deterministic:regex_extraction","url":"https://github.com/izhx/Phrase-Grounding-with-Pronoun","reach":{"status":"ok","spdx":"Apache-2.0"}}],"summary":{"ran":6,"unverified":3},"by_repo_kind":{"official":{"samples":9,"ran":6,"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":"58b3179dfda21236","entry":"box_area","repo":"izhx/Phrase-Grounding-with-Pronoun","repo_kind":"official","path":"code/src/metrics.py","file_url":"https://github.com/izhx/Phrase-Grounding-with-Pronoun/blob/HEAD/code/src/metrics.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":"58b3179dfda21236"}},{"code_sha256_prefix":"ac3d20339465e1a7","entry":"box_iou","repo":"izhx/Phrase-Grounding-with-Pronoun","repo_kind":"official","path":"code/src/metrics.py","file_url":"https://github.com/izhx/Phrase-Grounding-with-Pronoun/blob/HEAD/code/src/metrics.py","link_basis":"harvester_set","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":"ac3d20339465e1a7"}},{"code_sha256_prefix":"1b6e04ba3ceda006","entry":"build_position_encoding","repo":"izhx/Phrase-Grounding-with-Pronoun","repo_kind":"official","path":"code/src/mdetr/position_encoding.py","file_url":"https://github.com/izhx/Phrase-Grounding-with-Pronoun/blob/HEAD/code/src/mdetr/position_encoding.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":"1b6e04ba3ceda006"}},{"code_sha256_prefix":"d160fa9a2fd27d2e","entry":"safe_recall","repo":"izhx/Phrase-Grounding-with-Pronoun","repo_kind":"official","path":"code/src/metrics.py","file_url":"https://github.com/izhx/Phrase-Grounding-with-Pronoun/blob/HEAD/code/src/metrics.py","link_basis":"harvester_set","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":"d160fa9a2fd27d2e"}},{"code_sha256_prefix":"3aecd2a717339545","entry":"span_clusters","repo":"izhx/Phrase-Grounding-with-Pronoun","repo_kind":"official","path":"code/src/coref_reader.py","file_url":"https://github.com/izhx/Phrase-Grounding-with-Pronoun/blob/HEAD/code/src/coref_reader.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":"3aecd2a717339545"}},{"code_sha256_prefix":"1b75c920b73202c3","entry":"valid_crop_box","repo":"izhx/Phrase-Grounding-with-Pronoun","repo_kind":"official","path":"code/src/readers.py","file_url":"https://github.com/izhx/Phrase-Grounding-with-Pronoun/blob/HEAD/code/src/readers.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":"1b75c920b73202c3"}},{"code_sha256_prefix":"ca02dee1629c9dbd","entry":"build_backbone","repo":"izhx/Phrase-Grounding-with-Pronoun","repo_kind":"official","path":"code/src/mdetr/backbone.py","file_url":"https://github.com/izhx/Phrase-Grounding-with-Pronoun/blob/HEAD/code/src/mdetr/backbone.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":"ca02dee1629c9dbd"}},{"code_sha256_prefix":"3189378f2936393a","entry":"build_matcher","repo":"izhx/Phrase-Grounding-with-Pronoun","repo_kind":"official","path":"code/src/mdetr/matcher.py","file_url":"https://github.com/izhx/Phrase-Grounding-with-Pronoun/blob/HEAD/code/src/mdetr/matcher.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":"3189378f2936393a"}},{"code_sha256_prefix":"84d8f1cad596b621","entry":"evaulate","repo":"izhx/Phrase-Grounding-with-Pronoun","repo_kind":"official","path":"code/hf_neuralcoref.py","file_url":"https://github.com/izhx/Phrase-Grounding-with-Pronoun/blob/HEAD/code/hf_neuralcoref.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":"84d8f1cad596b621"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}