{"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/grounded-situation-recognition-with","title":"Grounded Situation Recognition with Transformers","arxiv_id":"2111.10135","date":"2021-11-19","proceeding":null,"authors":["Junhyeong Cho","Youngseok Yoon","Hyeonjun Lee","Suha Kwak"],"abstract":"Grounded Situation Recognition (GSR) is the task that not only classifies a salient action (verb), but also predicts entities (nouns) associated with semantic roles and their locations in the given image. Inspired by the remarkable success of Transformers in vision tasks, we propose a GSR model based on a Transformer encoder-decoder architecture. The attention mechanism of our model enables accurate verb classification by capturing high-level semantic feature of an image effectively, and allows the model to flexibly deal with the complicated and image-dependent relations between entities for improved noun classification and localization. Our model is the first Transformer architecture for GSR, and achieves the state of the art in every evaluation metric on the SWiG benchmark. Our code is available at https://github.com/jhcho99/gsrtr .","url_abs":"https://arxiv.org/abs/2111.10135v1","url_pdf":"https://arxiv.org/pdf/2111.10135v1.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":"grounded-situation-recognition-with","repo_url":"https://github.com/jhcho99/gsrtr","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"Apache-2.0"}}],"tasks":[{"task_slug":"decoder","task_name":"Decoder"},{"task_slug":"grounded-situation-recognition","task_name":"Grounded Situation Recognition"},{"task_slug":"image-classification","task_name":"Image Classification"},{"task_slug":"object-detection","task_name":"Object Detection"},{"task_slug":"scene-understanding","task_name":"Scene Understanding"},{"task_slug":"situation-recognition","task_name":"Situation Recognition"},{"task_slug":"visual-grounding","task_name":"Visual Grounding"},{"task_slug":"visual-reasoning","task_name":"Visual Reasoning"}],"methods":[{"method_slug":"adam","method_name":"Adam"},{"method_slug":"attention","method_name":"Attention"},{"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":"residual-connection","method_name":"Residual Connection"},{"method_slug":"softmax","method_name":"Softmax"},{"method_slug":"transformer","method_name":"Transformer"}],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/grounded-situation-recognition-on-swig","task":"Grounded Situation Recognition","dataset":"SWiG","model":"GSRTR","rank_in_archive_order":6,"of":13,"metrics":{"Top-1 Verb":"40.63","Top-1 Verb & Grounded-Value":"25.49","Top-1 Verb & Value":"32.15","Top-5 Verbs":"69.81","Top-5 Verbs & Grounded-Value":"42.5","Top-5 Verbs & Value":"54.13"},"uses_additional_data":false},{"leaderboard":"/sota/situation-recognition-on-imsitu","task":"Situation Recognition","dataset":"imSitu","model":"GSRTR","rank_in_archive_order":6,"of":13,"metrics":{"Top-1 Verb":"40.63","Top-1 Verb & Value":"32.15","Top-5 Verbs":"69.81","Top-5 Verbs & Value":"54.13"},"uses_additional_data":false}],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2111.10135","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2111.10135"}},"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/jhcho99/gsrtr","reach":{"status":"ok","spdx":"Apache-2.0"}}],"summary":{"ran":2,"ran_honours":2,"unverified":5},"by_repo_kind":{"official":{"samples":9,"ran":4,"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":9,"samples":[{"code_sha256_prefix":"aa6da43d05cfaf65","entry":"all_gather","repo":"jhcho99/gsrtr","repo_kind":"official","path":"util/misc.py","file_url":"https://github.com/jhcho99/gsrtr/blob/HEAD/util/misc.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":false,"mcp_get_code":{"code_sha256":"aa6da43d05cfaf65"}},{"code_sha256_prefix":"e0a06ded5d4f6c3c","entry":"box_cxcywh_to_xyxy","repo":"jhcho99/gsrtr","repo_kind":"official","path":"util/box_ops.py","file_url":"https://github.com/jhcho99/gsrtr/blob/HEAD/util/box_ops.py","link_basis":"harvester_set","language":"python","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"Apache-2.0","inline_ok":false,"mcp_get_code":{"code_sha256":"e0a06ded5d4f6c3c"}},{"code_sha256_prefix":"031b02fb990284ba","entry":"box_xyxy_to_cxcywh","repo":"jhcho99/gsrtr","repo_kind":"official","path":"util/box_ops.py","file_url":"https://github.com/jhcho99/gsrtr/blob/HEAD/util/box_ops.py","link_basis":"harvester_set","language":"python","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"Apache-2.0","inline_ok":false,"mcp_get_code":{"code_sha256":"031b02fb990284ba"}},{"code_sha256_prefix":"05992505df9ef0cd","entry":"reduce_dict","repo":"jhcho99/gsrtr","repo_kind":"official","path":"util/misc.py","file_url":"https://github.com/jhcho99/gsrtr/blob/HEAD/util/misc.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":false,"mcp_get_code":{"code_sha256":"05992505df9ef0cd"}},{"code_sha256_prefix":"edfd696fbd294e13","entry":"build","repo":"jhcho99/gsrtr","repo_kind":"official","path":"datasets/swig.py","file_url":"https://github.com/jhcho99/gsrtr/blob/HEAD/datasets/swig.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":false,"mcp_get_code":{"code_sha256":"edfd696fbd294e13"}},{"code_sha256_prefix":"9888762109072b2a","entry":"build_transformer","repo":"jhcho99/gsrtr","repo_kind":"official","path":"models/transformer.py","file_url":"https://github.com/jhcho99/gsrtr/blob/HEAD/models/transformer.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":false,"mcp_get_code":{"code_sha256":"9888762109072b2a"}},{"code_sha256_prefix":"458a46394aa87a2f","entry":"collate_fn","repo":"jhcho99/gsrtr","repo_kind":"official","path":"util/misc.py","file_url":"https://github.com/jhcho99/gsrtr/blob/HEAD/util/misc.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":false,"mcp_get_code":{"code_sha256":"458a46394aa87a2f"}},{"code_sha256_prefix":"7f06889563fd00ce","entry":"noun2synset","repo":"jhcho99/gsrtr","repo_kind":"official","path":"inference.py","file_url":"https://github.com/jhcho99/gsrtr/blob/HEAD/inference.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":false,"mcp_get_code":{"code_sha256":"7f06889563fd00ce"}},{"code_sha256_prefix":"fdd34e83fa6d7086","entry":"swig_box_xyxy_to_cxcywh","repo":"jhcho99/gsrtr","repo_kind":"official","path":"util/box_ops.py","file_url":"https://github.com/jhcho99/gsrtr/blob/HEAD/util/box_ops.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":false,"mcp_get_code":{"code_sha256":"fdd34e83fa6d7086"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}