{"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/comprehensive-image-captioning-via-scene","title":"Comprehensive Image Captioning via Scene Graph Decomposition","arxiv_id":"2007.11731","date":"2020-07-23","proceeding":"ECCV 2020 8","authors":["Yiwu Zhong","Li-Wei Wang","Jianshu Chen","Dong Yu","Yin Li"],"abstract":"We address the challenging problem of image captioning by revisiting the representation of image scene graph. At the core of our method lies the decomposition of a scene graph into a set of sub-graphs, with each sub-graph capturing a semantic component of the input image. We design a deep model to select important sub-graphs, and to decode each selected sub-graph into a single target sentence. By using sub-graphs, our model is able to attend to different components of the image. Our method thus accounts for accurate, diverse, grounded and controllable captioning at the same time. We present extensive experiments to demonstrate the benefits of our comprehensive captioning model. Our method establishes new state-of-the-art results in caption diversity, grounding, and controllability, and compares favourably to latest methods in caption quality. Our project website can be found at http://pages.cs.wisc.edu/~yiwuzhong/Sub-GC.html.","url_abs":"https://arxiv.org/abs/2007.11731v1","url_pdf":"https://arxiv.org/pdf/2007.11731v1.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":"comprehensive-image-captioning-via-scene","repo_url":"https://github.com/yiwuzhong/sub-gc","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}}],"tasks":[{"task_slug":"diversity","task_name":"Diversity"},{"task_slug":"image-captioning","task_name":"Image Captioning"},{"task_slug":"sentence","task_name":"Sentence"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2007.11731","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2007.11731"}},"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/yiwuzhong/sub-gc","reach":{"status":"ok","spdx":"MIT"}}],"summary":{"ran_draft_wrong":3,"unverified":3},"by_repo_kind":{"listed":{"samples":6,"ran":3,"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":"bfac58a04b6835f5","entry":"pad_unsort_packed_sequence","repo":"yiwuzhong/sub-gc","repo_kind":"listed","path":"models/AttModel.py","file_url":"https://github.com/yiwuzhong/sub-gc/blob/HEAD/models/AttModel.py","link_basis":"harvester_set","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":"invariant","behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"bfac58a04b6835f5"}},{"code_sha256_prefix":"ec4448373d72d636","entry":"precook","repo":"yiwuzhong/sub-gc","repo_kind":"listed","path":"misc/diversity/bleu_scorer.py","file_url":"https://github.com/yiwuzhong/sub-gc/blob/HEAD/misc/diversity/bleu_scorer.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":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"ec4448373d72d636"}},{"code_sha256_prefix":"e56d2f9cbd9cb8b1","entry":"sort_pack_padded_sequence","repo":"yiwuzhong/sub-gc","repo_kind":"listed","path":"models/AttModel.py","file_url":"https://github.com/yiwuzhong/sub-gc/blob/HEAD/models/AttModel.py","link_basis":"harvester_set","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"e56d2f9cbd9cb8b1"}},{"code_sha256_prefix":"39b6c760a9bd2617","entry":"cook_refs","repo":"yiwuzhong/sub-gc","repo_kind":"listed","path":"misc/diversity/bleu_scorer.py","file_url":"https://github.com/yiwuzhong/sub-gc/blob/HEAD/misc/diversity/bleu_scorer.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"39b6c760a9bd2617"}},{"code_sha256_prefix":"efa004f9940cb5c8","entry":"cook_test","repo":"yiwuzhong/sub-gc","repo_kind":"listed","path":"misc/diversity/bleu_scorer.py","file_url":"https://github.com/yiwuzhong/sub-gc/blob/HEAD/misc/diversity/bleu_scorer.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"efa004f9940cb5c8"}},{"code_sha256_prefix":"c555e7f1fba71b9c","entry":"pack_wrapper","repo":"yiwuzhong/sub-gc","repo_kind":"listed","path":"models/AttModel.py","file_url":"https://github.com/yiwuzhong/sub-gc/blob/HEAD/models/AttModel.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"c555e7f1fba71b9c"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}