{"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/fashion-captioning-towards-generating","title":"Fashion Captioning: Towards Generating Accurate Descriptions with Semantic Rewards","arxiv_id":"2008.02693","date":"2020-08-06","proceeding":"ECCV 2020 8","authors":["Xuewen Yang","Heming Zhang","Di Jin","Yingru Liu","Chi-Hao Wu","Jianchao Tan","Dongliang Xie","Jue Wang","Xin Wang"],"abstract":"Generating accurate descriptions for online fashion items is important not only for enhancing customers' shopping experiences, but also for the increase of online sales. Besides the need of correctly presenting the attributes of items, the expressions in an enchanting style could better attract customer interests. The goal of this work is to develop a novel learning framework for accurate and expressive fashion captioning. Different from popular work on image captioning, it is hard to identify and describe the rich attributes of fashion items. We seed the description of an item by first identifying its attributes, and introduce attribute-level semantic (ALS) reward and sentence-level semantic (SLS) reward as metrics to improve the quality of text descriptions. We further integrate the training of our model with maximum likelihood estimation (MLE), attribute embedding, and Reinforcement Learning (RL). To facilitate the learning, we build a new FAshion CAptioning Dataset (FACAD), which contains 993K images and 130K corresponding enchanting and diverse descriptions. Experiments on FACAD demonstrate the effectiveness of our model.","url_abs":"https://arxiv.org/abs/2008.02693v2","url_pdf":"https://arxiv.org/pdf/2008.02693v2.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":"fashion-captioning-towards-generating","repo_url":"https://github.com/xuewyang/Fashion_Captioning","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"NOASSERTION"}},{"paper_slug":"fashion-captioning-towards-generating","repo_url":"https://github.com/xuewyang/Fashion-Image-Captioning-Benchmark","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}}],"tasks":[{"task_slug":"attribute","task_name":"Attribute"},{"task_slug":"image-captioning","task_name":"Image Captioning"},{"task_slug":"reinforcement-learning-1","task_name":"Reinforcement Learning (RL)"},{"task_slug":"sentence","task_name":"Sentence"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":null,"atlas_url":"https://app.syntology.ai/?focus=2008.02693","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2008.02693"}},"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/xuewyang/Fashion_Captioning","reach":{"status":"ok","spdx":"NOASSERTION"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/xuewyang/Fashion-Image-Captioning-Benchmark","reach":{"status":"ok","spdx":"MIT"}}],"summary":{"ran":1,"ran_draft_wrong":4,"ran_honours":1,"ran_violates":2},"by_repo_kind":{"listed":{"samples":8,"ran":8,"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":"269003e7c21d565d","entry":"attention","repo":"xuewyang/Fashion-Image-Captioning-Benchmark","repo_kind":"listed","path":"captioning/models/TransformerModel.py","file_url":"https://github.com/xuewyang/Fashion-Image-Captioning-Benchmark/blob/HEAD/captioning/models/TransformerModel.py","link_basis":"harvester_set","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"269003e7c21d565d"}},{"code_sha256_prefix":"a3722169bbc81569","entry":"clones","repo":"xuewyang/Fashion-Image-Captioning-Benchmark","repo_kind":"listed","path":"captioning/models/TransformerModel.py","file_url":"https://github.com/xuewyang/Fashion-Image-Captioning-Benchmark/blob/HEAD/captioning/models/TransformerModel.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":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"a3722169bbc81569"}},{"code_sha256_prefix":"d2379d710eedc4ae","entry":"pack_wrapper","repo":"xuewyang/Fashion-Image-Captioning-Benchmark","repo_kind":"listed","path":"captioning/models/AttModel.py","file_url":"https://github.com/xuewyang/Fashion-Image-Captioning-Benchmark/blob/HEAD/captioning/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":"d2379d710eedc4ae"}},{"code_sha256_prefix":"bfac58a04b6835f5","entry":"pad_unsort_packed_sequence","repo":"xuewyang/Fashion-Image-Captioning-Benchmark","repo_kind":"listed","path":"captioning/models/AttModel.py","file_url":"https://github.com/xuewyang/Fashion-Image-Captioning-Benchmark/blob/HEAD/captioning/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":"b317109a6e9a36e3","entry":"repeat_tensors","repo":"xuewyang/Fashion-Image-Captioning-Benchmark","repo_kind":"listed","path":"captioning/models/utils.py","file_url":"https://github.com/xuewyang/Fashion-Image-Captioning-Benchmark/blob/HEAD/captioning/models/utils.py","link_basis":"harvester_set","language":"python","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"b317109a6e9a36e3"}},{"code_sha256_prefix":"e56d2f9cbd9cb8b1","entry":"sort_pack_padded_sequence","repo":"xuewyang/Fashion-Image-Captioning-Benchmark","repo_kind":"listed","path":"captioning/models/AttModel.py","file_url":"https://github.com/xuewyang/Fashion-Image-Captioning-Benchmark/blob/HEAD/captioning/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":"936178513bc7b9d7","entry":"split_tensors","repo":"xuewyang/Fashion-Image-Captioning-Benchmark","repo_kind":"listed","path":"captioning/models/utils.py","file_url":"https://github.com/xuewyang/Fashion-Image-Captioning-Benchmark/blob/HEAD/captioning/models/utils.py","link_basis":"harvester_set","language":"python","status":"ran_violates","verification_level":1,"contract_check":"VIOLATES","metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"936178513bc7b9d7"}},{"code_sha256_prefix":"dd03765c7da9ca51","entry":"subsequent_mask","repo":"xuewyang/Fashion-Image-Captioning-Benchmark","repo_kind":"listed","path":"captioning/models/TransformerModel.py","file_url":"https://github.com/xuewyang/Fashion-Image-Captioning-Benchmark/blob/HEAD/captioning/models/TransformerModel.py","link_basis":"harvester_set","language":"python","status":"ran_violates","verification_level":1,"contract_check":"VIOLATES","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"dd03765c7da9ca51"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}