{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:GRM2WLEZGHFFTGBOABN63RI2AA","short_pith_number":"pith:GRM2WLEZ","schema_version":"1.0","canonical_sha256":"3459ab2c9931ca59982e005bedc51a0002288b7c3b04300c47cfc41a8ca5589e","source":{"kind":"arxiv","id":"2305.06310","version":4},"attestation_state":"computed","paper":{"title":"SoGAR: Self-supervised Spatiotemporal Attention-based Social Group Activity Recognition","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Alexander H Nelson, Han-Seok Seo, Khoa Luu, Naga VS Raviteja Chappa, Page Daniel Dobbs, Pha Nguyen, Xin Li","submitted_at":"2023-04-27T03:41:15Z","abstract_excerpt":"This paper introduces a novel approach to Social Group Activity Recognition (SoGAR) using Self-supervised Transformers network that can effectively utilize unlabeled video data. To extract spatio-temporal information, we created local and global views with varying frame rates. Our self-supervised objective ensures that features extracted from contrasting views of the same video were consistent across spatio-temporal domains. Our proposed approach is efficient in using transformer-based encoders to alleviate the weakly supervised setting of group activity recognition. By leveraging the benefits"},"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":"2305.06310","kind":"arxiv","version":4},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2023-04-27T03:41:15Z","cross_cats_sorted":[],"title_canon_sha256":"4b5f943148616a2187b80ea85915bf0013c2896dd8f2d1f1994a4a0381edc08c","abstract_canon_sha256":"9e8730cb87c1c643b99bd782c1e8256aec1d26edd7c7901859a47d5c2f61e175"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:37:04.284007Z","signature_b64":"eqFT2n/IL1pSmk1+P4IUnyF1ujf1rtPoN9d6XFMb+WAKKsYxmjheV3v/Tekvr96xuS1Zba33Wp0hSxD+XYWkAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"3459ab2c9931ca59982e005bedc51a0002288b7c3b04300c47cfc41a8ca5589e","last_reissued_at":"2026-07-05T09:37:04.283597Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:37:04.283597Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"SoGAR: Self-supervised Spatiotemporal Attention-based Social Group Activity Recognition","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Alexander H Nelson, Han-Seok Seo, Khoa Luu, Naga VS Raviteja Chappa, Page Daniel Dobbs, Pha Nguyen, Xin Li","submitted_at":"2023-04-27T03:41:15Z","abstract_excerpt":"This paper introduces a novel approach to Social Group Activity Recognition (SoGAR) using Self-supervised Transformers network that can effectively utilize unlabeled video data. To extract spatio-temporal information, we created local and global views with varying frame rates. Our self-supervised objective ensures that features extracted from contrasting views of the same video were consistent across spatio-temporal domains. Our proposed approach is efficient in using transformer-based encoders to alleviate the weakly supervised setting of group activity recognition. By leveraging the benefits"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2305.06310","kind":"arxiv","version":4},"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/2305.06310/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":"2305.06310","created_at":"2026-07-05T09:37:04.283655+00:00"},{"alias_kind":"arxiv_version","alias_value":"2305.06310v4","created_at":"2026-07-05T09:37:04.283655+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2305.06310","created_at":"2026-07-05T09:37:04.283655+00:00"},{"alias_kind":"pith_short_12","alias_value":"GRM2WLEZGHFF","created_at":"2026-07-05T09:37:04.283655+00:00"},{"alias_kind":"pith_short_16","alias_value":"GRM2WLEZGHFFTGBO","created_at":"2026-07-05T09:37:04.283655+00:00"},{"alias_kind":"pith_short_8","alias_value":"GRM2WLEZ","created_at":"2026-07-05T09:37:04.283655+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2501.13950","citing_title":"DEFEND: A Large-scale 1M Dataset and Foundation Model for Tobacco Addiction Prevention","ref_index":4,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/GRM2WLEZGHFFTGBOABN63RI2AA","json":"https://pith.science/pith/GRM2WLEZGHFFTGBOABN63RI2AA.json","graph_json":"https://pith.science/api/pith-number/GRM2WLEZGHFFTGBOABN63RI2AA/graph.json","events_json":"https://pith.science/api/pith-number/GRM2WLEZGHFFTGBOABN63RI2AA/events.json","paper":"https://pith.science/paper/GRM2WLEZ"},"agent_actions":{"view_html":"https://pith.science/pith/GRM2WLEZGHFFTGBOABN63RI2AA","download_json":"https://pith.science/pith/GRM2WLEZGHFFTGBOABN63RI2AA.json","view_paper":"https://pith.science/paper/GRM2WLEZ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2305.06310&json=true","fetch_graph":"https://pith.science/api/pith-number/GRM2WLEZGHFFTGBOABN63RI2AA/graph.json","fetch_events":"https://pith.science/api/pith-number/GRM2WLEZGHFFTGBOABN63RI2AA/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/GRM2WLEZGHFFTGBOABN63RI2AA/action/timestamp_anchor","attest_storage":"https://pith.science/pith/GRM2WLEZGHFFTGBOABN63RI2AA/action/storage_attestation","attest_author":"https://pith.science/pith/GRM2WLEZGHFFTGBOABN63RI2AA/action/author_attestation","sign_citation":"https://pith.science/pith/GRM2WLEZGHFFTGBOABN63RI2AA/action/citation_signature","submit_replication":"https://pith.science/pith/GRM2WLEZGHFFTGBOABN63RI2AA/action/replication_record"}},"created_at":"2026-07-05T09:37:04.283655+00:00","updated_at":"2026-07-05T09:37:04.283655+00:00"}