{"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/collaborative-transformers-for-grounded","title":"Collaborative Transformers for Grounded Situation Recognition","arxiv_id":"2203.16518","date":"2022-03-30","proceeding":"CVPR 2022 1","authors":["Junhyeong Cho","Youngseok Yoon","Suha Kwak"],"abstract":"Grounded situation recognition is the task of predicting the main activity, entities playing certain roles within the activity, and bounding-box groundings of the entities in the given image. To effectively deal with this challenging task, we introduce a novel approach where the two processes for activity classification and entity estimation are interactive and complementary. To implement this idea, we propose Collaborative Glance-Gaze TransFormer (CoFormer) that consists of two modules: Glance transformer for activity classification and Gaze transformer for entity estimation. Glance transformer predicts the main activity with the help of Gaze transformer that analyzes entities and their relations, while Gaze transformer estimates the grounded entities by focusing only on the entities relevant to the activity predicted by Glance transformer. Our CoFormer achieves the state of the art in all evaluation metrics on the SWiG dataset. Training code and model weights are available at https://github.com/jhcho99/CoFormer.","url_abs":"https://arxiv.org/abs/2203.16518v1","url_pdf":"https://arxiv.org/pdf/2203.16518v1.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":"collaborative-transformers-for-grounded","repo_url":"https://github.com/jhcho99/coformer","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"Apache-2.0"}},{"paper_slug":"collaborative-transformers-for-grounded","repo_url":"https://github.com/ruipingl/opensu","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"collaborative-transformers-for-grounded","repo_url":"https://github.com/towhee-io/towhee/tree/main/towhee/models/coformer","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"pytorch","reach":null}],"tasks":[{"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":"CoFormer","rank_in_archive_order":3,"of":13,"metrics":{"Top-1 Verb":"44.66","Top-1 Verb & Grounded-Value":"29.05","Top-1 Verb & Value":"35.98","Top-5 Verbs":"73.31","Top-5 Verbs & Grounded-Value":"46.25","Top-5 Verbs & Value":"57.76"},"uses_additional_data":false},{"leaderboard":"/sota/situation-recognition-on-imsitu","task":"Situation Recognition","dataset":"imSitu","model":"CoFormer","rank_in_archive_order":3,"of":13,"metrics":{"Top-1 Verb":"44.66","Top-1 Verb & Value":"35.98","Top-5 Verbs":"73.31","Top-5 Verbs & Value":"57.76"},"uses_additional_data":false}],"syntology":{"syntology_url":"https://syntology.ai/paper/2203.16518","atlas_url":"https://app.syntology.ai/?focus=2203.16518","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2203.16518"}},"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":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/ruipingl/opensu","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/towhee-io/towhee/tree/main/towhee/models/coformer","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/jhcho99/coformer","reach":{"status":"ok","spdx":"Apache-2.0"}},{"provenance":"deterministic:regex_extraction","url":"https://github.com/jhcho99/CoFormer","reach":{"status":"ok","spdx":"Apache-2.0"}}],"summary":{"ran":3,"ran_draft_wrong":2,"unverified":2},"by_repo_kind":{"official":{"samples":3,"ran":2,"repositories":1},"listed":{"samples":4,"ran":3,"repositories":2}},"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":"b2ba2a748ffd3281","entry":"CoFormer","repo":"towhee-io/towhee","repo_kind":"listed","path":"towhee/models/coformer/coformer.py","file_url":"https://github.com/towhee-io/towhee/blob/HEAD/towhee/models/coformer/coformer.py","link_basis":"first_harvest_node","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":"b2ba2a748ffd3281"}},{"code_sha256_prefix":"42fe8f9fc92da57d","entry":"NestedTensor","repo":"towhee-io/towhee","repo_kind":"listed","path":"towhee/models/coformer/coformer.py","file_url":"https://github.com/towhee-io/towhee/blob/HEAD/towhee/models/coformer/coformer.py","link_basis":"first_harvest_node","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":"42fe8f9fc92da57d"}},{"code_sha256_prefix":"8ae3464a294cdaed","entry":"NestedTensor","repo":"jhcho99/CoFormer","repo_kind":"official","path":"models/coformer.py","file_url":"https://github.com/jhcho99/CoFormer/blob/HEAD/models/coformer.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"8ae3464a294cdaed"}},{"code_sha256_prefix":"32db9196c8ba7a26","entry":"nested_tensor_from_tensor_list","repo":"towhee-io/towhee","repo_kind":"listed","path":"towhee/models/coformer/coformer.py","file_url":"https://github.com/towhee-io/towhee/blob/HEAD/towhee/models/coformer/coformer.py","link_basis":"first_harvest_node","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"32db9196c8ba7a26"}},{"code_sha256_prefix":"ab1a441fc7e324ad","entry":"nested_tensor_from_tensor_list","repo":"jhcho99/CoFormer","repo_kind":"official","path":"models/coformer.py","file_url":"https://github.com/jhcho99/CoFormer/blob/HEAD/models/coformer.py","link_basis":"first_harvest_node","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"ab1a441fc7e324ad"}},{"code_sha256_prefix":"984efcc5a150c7e9","entry":"CoFormer","repo":"jhcho99/CoFormer","repo_kind":"official","path":"models/coformer.py","file_url":"https://github.com/jhcho99/CoFormer/blob/HEAD/models/coformer.py","link_basis":"first_harvest_node","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":"984efcc5a150c7e9"}},{"code_sha256_prefix":"0d4f3b554a49c218","entry":"CoFormer","repo":"ruipingl/opensu","repo_kind":"listed","path":"models/coformer.py","file_url":"https://github.com/ruipingl/opensu/blob/HEAD/models/coformer.py","link_basis":"first_harvest_node","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":"0d4f3b554a49c218"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}