{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:5VX2N3APQZMJQYFIYUOQ7EOJP3","short_pith_number":"pith:5VX2N3AP","schema_version":"1.0","canonical_sha256":"ed6fa6ec0f86589860a8c51d0f91c97ee88ed2d98ba843e7f61a08f96ce5303b","source":{"kind":"arxiv","id":"2202.09277","version":2},"attestation_state":"computed","paper":{"title":"(2.5+1)D Spatio-Temporal Scene Graphs for Video Question Answering","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.CV","authors_text":"Anoop Cherian, Chiori Hori, Jonathan Le Roux, Tim K. Marks","submitted_at":"2022-02-18T15:58:54Z","abstract_excerpt":"Spatio-temporal scene-graph approaches to video-based reasoning tasks, such as video question-answering (QA), typically construct such graphs for every video frame. These approaches often ignore the fact that videos are essentially sequences of 2D \"views\" of events happening in a 3D space, and that the semantics of the 3D scene can thus be carried over from frame to frame. Leveraging this insight, we propose a (2.5+1)D scene graph representation to better capture the spatio-temporal information flows inside the videos. Specifically, we first create a 2.5D (pseudo-3D) scene graph by transformin"},"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":"2202.09277","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2022-02-18T15:58:54Z","cross_cats_sorted":["cs.AI","cs.LG"],"title_canon_sha256":"699922fa72e3085e9bd10e3a18744358979dae8fb8466193c1fd2da7a936e7e3","abstract_canon_sha256":"bc97527aed1be5db5a8d5f4aae95eca578253d9215c48d922ead16ab5f9d4514"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T04:08:42.252268Z","signature_b64":"Osk1Mpd+Yn88QukraNs7OiwhesIgN4g8CwhfyvT8vxy29rguGoT9kGxekBbStZam6vqwfR0MLw5VUbe7dCXoDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"ed6fa6ec0f86589860a8c51d0f91c97ee88ed2d98ba843e7f61a08f96ce5303b","last_reissued_at":"2026-07-05T04:08:42.251765Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T04:08:42.251765Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"(2.5+1)D Spatio-Temporal Scene Graphs for Video Question Answering","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.CV","authors_text":"Anoop Cherian, Chiori Hori, Jonathan Le Roux, Tim K. Marks","submitted_at":"2022-02-18T15:58:54Z","abstract_excerpt":"Spatio-temporal scene-graph approaches to video-based reasoning tasks, such as video question-answering (QA), typically construct such graphs for every video frame. These approaches often ignore the fact that videos are essentially sequences of 2D \"views\" of events happening in a 3D space, and that the semantics of the 3D scene can thus be carried over from frame to frame. Leveraging this insight, we propose a (2.5+1)D scene graph representation to better capture the spatio-temporal information flows inside the videos. Specifically, we first create a 2.5D (pseudo-3D) scene graph by transformin"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2202.09277","kind":"arxiv","version":2},"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/2202.09277/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":"2202.09277","created_at":"2026-07-05T04:08:42.251826+00:00"},{"alias_kind":"arxiv_version","alias_value":"2202.09277v2","created_at":"2026-07-05T04:08:42.251826+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2202.09277","created_at":"2026-07-05T04:08:42.251826+00:00"},{"alias_kind":"pith_short_12","alias_value":"5VX2N3APQZMJ","created_at":"2026-07-05T04:08:42.251826+00:00"},{"alias_kind":"pith_short_16","alias_value":"5VX2N3APQZMJQYFI","created_at":"2026-07-05T04:08:42.251826+00:00"},{"alias_kind":"pith_short_8","alias_value":"5VX2N3AP","created_at":"2026-07-05T04:08:42.251826+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2501.07109","citing_title":"The Quest for Visual Understanding: A Journey Through the Evolution of Visual Question Answering","ref_index":16,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/5VX2N3APQZMJQYFIYUOQ7EOJP3","json":"https://pith.science/pith/5VX2N3APQZMJQYFIYUOQ7EOJP3.json","graph_json":"https://pith.science/api/pith-number/5VX2N3APQZMJQYFIYUOQ7EOJP3/graph.json","events_json":"https://pith.science/api/pith-number/5VX2N3APQZMJQYFIYUOQ7EOJP3/events.json","paper":"https://pith.science/paper/5VX2N3AP"},"agent_actions":{"view_html":"https://pith.science/pith/5VX2N3APQZMJQYFIYUOQ7EOJP3","download_json":"https://pith.science/pith/5VX2N3APQZMJQYFIYUOQ7EOJP3.json","view_paper":"https://pith.science/paper/5VX2N3AP","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2202.09277&json=true","fetch_graph":"https://pith.science/api/pith-number/5VX2N3APQZMJQYFIYUOQ7EOJP3/graph.json","fetch_events":"https://pith.science/api/pith-number/5VX2N3APQZMJQYFIYUOQ7EOJP3/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/5VX2N3APQZMJQYFIYUOQ7EOJP3/action/timestamp_anchor","attest_storage":"https://pith.science/pith/5VX2N3APQZMJQYFIYUOQ7EOJP3/action/storage_attestation","attest_author":"https://pith.science/pith/5VX2N3APQZMJQYFIYUOQ7EOJP3/action/author_attestation","sign_citation":"https://pith.science/pith/5VX2N3APQZMJQYFIYUOQ7EOJP3/action/citation_signature","submit_replication":"https://pith.science/pith/5VX2N3APQZMJQYFIYUOQ7EOJP3/action/replication_record"}},"created_at":"2026-07-05T04:08:42.251826+00:00","updated_at":"2026-07-05T04:08:42.251826+00:00"}