{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:NZPPEOR5HI6PGQ3TVVROKLIK65","short_pith_number":"pith:NZPPEOR5","schema_version":"1.0","canonical_sha256":"6e5ef23a3d3a3cf34373ad62e52d0af776ff0c6a1ac297667f6756a8ff76a16a","source":{"kind":"arxiv","id":"2111.10135","version":1},"attestation_state":"computed","paper":{"title":"Grounded Situation Recognition with Transformers","license":"http://creativecommons.org/licenses/by-sa/4.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.CV","authors_text":"Hyeonjun Lee, Junhyeong Cho, Suha Kwak, Youngseok Yoon","submitted_at":"2021-11-19T10:10:03Z","abstract_excerpt":"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 i"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"2111.10135","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2021-11-19T10:10:03Z","cross_cats_sorted":["cs.AI","cs.LG"],"title_canon_sha256":"3e80825cf32bf74c6eed402b1f7e032e3e2d7370f0b957810c19a2f59bedabc4","abstract_canon_sha256":"0688c169ae7c44412078982887050a2f53eefded1042248bfe6b76f15a622fdc"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T03:33:28.534240Z","signature_b64":"YTC8AbisZYur40YJkLmAPRsHpe33SMOvUsU1ah8ut4625fNLf+jCCjPbX4dSPIKlq+RxT3kL7NJv7i70GXfCAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"6e5ef23a3d3a3cf34373ad62e52d0af776ff0c6a1ac297667f6756a8ff76a16a","last_reissued_at":"2026-07-05T03:33:28.533713Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T03:33:28.533713Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Grounded Situation Recognition with Transformers","license":"http://creativecommons.org/licenses/by-sa/4.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.CV","authors_text":"Hyeonjun Lee, Junhyeong Cho, Suha Kwak, Youngseok Yoon","submitted_at":"2021-11-19T10:10:03Z","abstract_excerpt":"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 i"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2111.10135","kind":"arxiv","version":1},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2111.10135/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"references":{"count":0,"sample":[],"resolved_work":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","internal_anchors":0},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"author_claims":{"count":0,"strong_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"builder_version":"pith-number-builder-2026-05-17-v1"},"aliases":[{"alias_kind":"arxiv","alias_value":"2111.10135","created_at":"2026-07-05T03:33:28.533772+00:00"},{"alias_kind":"arxiv_version","alias_value":"2111.10135v1","created_at":"2026-07-05T03:33:28.533772+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2111.10135","created_at":"2026-07-05T03:33:28.533772+00:00"},{"alias_kind":"pith_short_12","alias_value":"NZPPEOR5HI6P","created_at":"2026-07-05T03:33:28.533772+00:00"},{"alias_kind":"pith_short_16","alias_value":"NZPPEOR5HI6PGQ3T","created_at":"2026-07-05T03:33:28.533772+00:00"},{"alias_kind":"pith_short_8","alias_value":"NZPPEOR5","created_at":"2026-07-05T03:33:28.533772+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2508.21816","citing_title":"The Demon is in Ambiguity: Revisiting Situation Recognition with Single Positive Multi-Label Learning","ref_index":28,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/NZPPEOR5HI6PGQ3TVVROKLIK65","json":"https://pith.science/pith/NZPPEOR5HI6PGQ3TVVROKLIK65.json","graph_json":"https://pith.science/api/pith-number/NZPPEOR5HI6PGQ3TVVROKLIK65/graph.json","events_json":"https://pith.science/api/pith-number/NZPPEOR5HI6PGQ3TVVROKLIK65/events.json","paper":"https://pith.science/paper/NZPPEOR5"},"agent_actions":{"view_html":"https://pith.science/pith/NZPPEOR5HI6PGQ3TVVROKLIK65","download_json":"https://pith.science/pith/NZPPEOR5HI6PGQ3TVVROKLIK65.json","view_paper":"https://pith.science/paper/NZPPEOR5","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2111.10135&json=true","fetch_graph":"https://pith.science/api/pith-number/NZPPEOR5HI6PGQ3TVVROKLIK65/graph.json","fetch_events":"https://pith.science/api/pith-number/NZPPEOR5HI6PGQ3TVVROKLIK65/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/NZPPEOR5HI6PGQ3TVVROKLIK65/action/timestamp_anchor","attest_storage":"https://pith.science/pith/NZPPEOR5HI6PGQ3TVVROKLIK65/action/storage_attestation","attest_author":"https://pith.science/pith/NZPPEOR5HI6PGQ3TVVROKLIK65/action/author_attestation","sign_citation":"https://pith.science/pith/NZPPEOR5HI6PGQ3TVVROKLIK65/action/citation_signature","submit_replication":"https://pith.science/pith/NZPPEOR5HI6PGQ3TVVROKLIK65/action/replication_record"}},"created_at":"2026-07-05T03:33:28.533772+00:00","updated_at":"2026-07-05T03:33:28.533772+00:00"}