{"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/image-captioning-transforming-objects-into","title":"Image Captioning: Transforming Objects into Words","arxiv_id":"1906.05963","date":"2019-06-14","proceeding":"NeurIPS 2019 12","authors":["Simao Herdade","Armin Kappeler","Kofi Boakye","Joao Soares"],"abstract":"Image captioning models typically follow an encoder-decoder architecture which uses abstract image feature vectors as input to the encoder. One of the most successful algorithms uses feature vectors extracted from the region proposals obtained from an object detector. In this work we introduce the Object Relation Transformer, that builds upon this approach by explicitly incorporating information about the spatial relationship between input detected objects through geometric attention. Quantitative and qualitative results demonstrate the importance of such geometric attention for image captioning, leading to improvements on all common captioning metrics on the MS-COCO dataset.","url_abs":"https://arxiv.org/abs/1906.05963v2","url_pdf":"https://arxiv.org/pdf/1906.05963v2.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":"image-captioning-transforming-objects-into","repo_url":"https://github.com/yahoo/object_relation_transformer","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}},{"paper_slug":"image-captioning-transforming-objects-into","repo_url":"https://github.com/Japanese-Image-Captioning/ORT-for-Japanese","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}},{"paper_slug":"image-captioning-transforming-objects-into","repo_url":"https://github.com/hieunghia-pat/ObjectRelationTransformerAoA","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"none","reach":{"status":"ok"}},{"paper_slug":"image-captioning-transforming-objects-into","repo_url":"https://github.com/hieunghia-pat/uit-objectaoa","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"none","reach":{"status":"ok"}}],"tasks":[{"task_slug":"decoder","task_name":"Decoder"},{"task_slug":"image-captioning","task_name":"Image Captioning"},{"task_slug":"object","task_name":"Object"}],"methods":[{"method_slug":"absolute-position-encodings","method_name":"Absolute Position Encodings"},{"method_slug":"adam","method_name":"Adam"},{"method_slug":"attention","method_name":"Attention"},{"method_slug":"bpe","method_name":"BPE"},{"method_slug":"dense-connections","method_name":"Dense Connections"},{"method_slug":"dropout","method_name":"Dropout"},{"method_slug":"label-smoothing","method_name":"Label Smoothing"},{"method_slug":"layer-normalization","method_name":"Layer Normalization"},{"method_slug":"linear-layer","method_name":"Linear Layer"},{"method_slug":"multi-head-attention","method_name":"Multi-Head Attention"},{"method_slug":"position-wise-feed-forward-layer","method_name":"Position-Wise Feed-Forward Layer"},{"method_slug":"relu","method_name":"ReLU"},{"method_slug":"residual-connection","method_name":"Residual Connection"},{"method_slug":"softmax","method_name":"Softmax"},{"method_slug":"transformer","method_name":"Transformer"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1906.05963","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1906.05963"}},"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/yahoo/object_relation_transformer","reach":{"status":"ok","spdx":"MIT"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/Japanese-Image-Captioning/ORT-for-Japanese","reach":{"status":"ok","spdx":"MIT"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/hieunghia-pat/uit-objectaoa","reach":{"status":"ok"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/hieunghia-pat/ObjectRelationTransformerAoA","reach":{"status":"ok"}}],"summary":{"ran_draft_wrong":5,"ran_violates":1,"unverified":4},"by_repo_kind":{"official":{"samples":6,"ran":3,"repositories":1},"listed":{"samples":1,"ran":0,"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":3,"samples":[{"code_sha256_prefix":"20bb0ff4a2d77a03","entry":"attention","repo":null,"repo_kind":null,"path":null,"file_url":null,"link_basis":"identical_code_first_harvested_elsewhere","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":null,"inline_ok":false,"mcp_get_code":{"code_sha256":"20bb0ff4a2d77a03"}},{"code_sha256_prefix":"a3722169bbc81569","entry":"clones","repo":null,"repo_kind":null,"path":null,"file_url":null,"link_basis":"identical_code_first_harvested_elsewhere","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":null,"inline_ok":false,"mcp_get_code":{"code_sha256":"a3722169bbc81569"}},{"code_sha256_prefix":"d2379d710eedc4ae","entry":"pack_wrapper","repo":"yahoo/object_relation_transformer","repo_kind":"official","path":"models/AttModel.py","file_url":"https://github.com/yahoo/object_relation_transformer/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":"d2379d710eedc4ae"}},{"code_sha256_prefix":"bfac58a04b6835f5","entry":"pad_unsort_packed_sequence","repo":"yahoo/object_relation_transformer","repo_kind":"official","path":"models/AttModel.py","file_url":"https://github.com/yahoo/object_relation_transformer/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":"e56d2f9cbd9cb8b1","entry":"sort_pack_padded_sequence","repo":"yahoo/object_relation_transformer","repo_kind":"official","path":"models/AttModel.py","file_url":"https://github.com/yahoo/object_relation_transformer/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":"dd03765c7da9ca51","entry":"subsequent_mask","repo":null,"repo_kind":null,"path":null,"file_url":null,"link_basis":"identical_code_first_harvested_elsewhere","language":"python","status":"ran_violates","verification_level":1,"contract_check":"VIOLATES","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":null,"inline_ok":false,"mcp_get_code":{"code_sha256":"dd03765c7da9ca51"}},{"code_sha256_prefix":"5ca5b96b8c214e19","entry":"pack_wrapper","repo":"Japanese-Image-Captioning/ORT-for-Japanese","repo_kind":"listed","path":"models/AttModel.py","file_url":"https://github.com/Japanese-Image-Captioning/ORT-for-Japanese/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":"5ca5b96b8c214e19"}},{"code_sha256_prefix":"2b17380e9938d559","entry":"resnet18","repo":"yahoo/object_relation_transformer","repo_kind":"official","path":"misc/resnet.py","file_url":"https://github.com/yahoo/object_relation_transformer/blob/HEAD/misc/resnet.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":"2b17380e9938d559"}},{"code_sha256_prefix":"d206d964368eeb24","entry":"resnet34","repo":"yahoo/object_relation_transformer","repo_kind":"official","path":"misc/resnet.py","file_url":"https://github.com/yahoo/object_relation_transformer/blob/HEAD/misc/resnet.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":"d206d964368eeb24"}},{"code_sha256_prefix":"fade30a7dab7a039","entry":"resnet50","repo":"yahoo/object_relation_transformer","repo_kind":"official","path":"misc/resnet.py","file_url":"https://github.com/yahoo/object_relation_transformer/blob/HEAD/misc/resnet.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":"fade30a7dab7a039"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}