{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2019:6IVVZX7MBYYXKQB6Z4FFDBICEQ","short_pith_number":"pith:6IVVZX7M","schema_version":"1.0","canonical_sha256":"f22b5cdfec0e3175403ecf0a5185022411aec59ece1a8cafe33bcd70999bedbd","source":{"kind":"arxiv","id":"1912.04316","version":3},"attestation_state":"computed","paper":{"title":"Video action detection by learning graph-based spatio-temporal interactions","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Lorenzo Baraldi, Matteo Tomei, Rita Cucchiara, Simone Bronzin, Simone Calderara","submitted_at":"2019-12-09T19:01:46Z","abstract_excerpt":"Action Detection is a complex task that aims to detect and classify human actions in video clips. Typically, it has been addressed by processing fine-grained features extracted from a video classification backbone. Recently, thanks to the robustness of object and people detectors, a deeper focus has been added on relationship modelling. Following this line, we propose a graph-based framework to learn high-level interactions between people and objects, in both space and time. In our formulation, spatio-temporal relationships are learned through self-attention on a multi-layer graph structure wh"},"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":"1912.04316","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2019-12-09T19:01:46Z","cross_cats_sorted":[],"title_canon_sha256":"f3123e99b41ba915b55b911884ef7547ab573f8ef4e1369aa5034b07397b6004","abstract_canon_sha256":"2c2cb8ceebb48e4c62ddc137c9ff0820cb9d639e9622b7ce522faf13d7066b46"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T02:18:49.949167Z","signature_b64":"z76r+COMIDlJ0m5cD9IGGZ6RJbYW/+2Q64U81kcxAAejZTdG2V40M2NEHI/0pXp8QViLXz2wZBGDB3crkWhtAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"f22b5cdfec0e3175403ecf0a5185022411aec59ece1a8cafe33bcd70999bedbd","last_reissued_at":"2026-07-05T02:18:49.948674Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T02:18:49.948674Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Video action detection by learning graph-based spatio-temporal interactions","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Lorenzo Baraldi, Matteo Tomei, Rita Cucchiara, Simone Bronzin, Simone Calderara","submitted_at":"2019-12-09T19:01:46Z","abstract_excerpt":"Action Detection is a complex task that aims to detect and classify human actions in video clips. Typically, it has been addressed by processing fine-grained features extracted from a video classification backbone. Recently, thanks to the robustness of object and people detectors, a deeper focus has been added on relationship modelling. Following this line, we propose a graph-based framework to learn high-level interactions between people and objects, in both space and time. In our formulation, spatio-temporal relationships are learned through self-attention on a multi-layer graph structure wh"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1912.04316","kind":"arxiv","version":3},"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/1912.04316/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":"1912.04316","created_at":"2026-07-05T02:18:49.948732+00:00"},{"alias_kind":"arxiv_version","alias_value":"1912.04316v3","created_at":"2026-07-05T02:18:49.948732+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1912.04316","created_at":"2026-07-05T02:18:49.948732+00:00"},{"alias_kind":"pith_short_12","alias_value":"6IVVZX7MBYYX","created_at":"2026-07-05T02:18:49.948732+00:00"},{"alias_kind":"pith_short_16","alias_value":"6IVVZX7MBYYXKQB6","created_at":"2026-07-05T02:18:49.948732+00:00"},{"alias_kind":"pith_short_8","alias_value":"6IVVZX7M","created_at":"2026-07-05T02:18:49.948732+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2507.21247","citing_title":"Dual Guidance Semi-Supervised Action Detection","ref_index":43,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/6IVVZX7MBYYXKQB6Z4FFDBICEQ","json":"https://pith.science/pith/6IVVZX7MBYYXKQB6Z4FFDBICEQ.json","graph_json":"https://pith.science/api/pith-number/6IVVZX7MBYYXKQB6Z4FFDBICEQ/graph.json","events_json":"https://pith.science/api/pith-number/6IVVZX7MBYYXKQB6Z4FFDBICEQ/events.json","paper":"https://pith.science/paper/6IVVZX7M"},"agent_actions":{"view_html":"https://pith.science/pith/6IVVZX7MBYYXKQB6Z4FFDBICEQ","download_json":"https://pith.science/pith/6IVVZX7MBYYXKQB6Z4FFDBICEQ.json","view_paper":"https://pith.science/paper/6IVVZX7M","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1912.04316&json=true","fetch_graph":"https://pith.science/api/pith-number/6IVVZX7MBYYXKQB6Z4FFDBICEQ/graph.json","fetch_events":"https://pith.science/api/pith-number/6IVVZX7MBYYXKQB6Z4FFDBICEQ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/6IVVZX7MBYYXKQB6Z4FFDBICEQ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/6IVVZX7MBYYXKQB6Z4FFDBICEQ/action/storage_attestation","attest_author":"https://pith.science/pith/6IVVZX7MBYYXKQB6Z4FFDBICEQ/action/author_attestation","sign_citation":"https://pith.science/pith/6IVVZX7MBYYXKQB6Z4FFDBICEQ/action/citation_signature","submit_replication":"https://pith.science/pith/6IVVZX7MBYYXKQB6Z4FFDBICEQ/action/replication_record"}},"created_at":"2026-07-05T02:18:49.948732+00:00","updated_at":"2026-07-05T02:18:49.948732+00:00"}