{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:VEK5F3QCA2NHFQVBLTYYKHFQHX","short_pith_number":"pith:VEK5F3QC","schema_version":"1.0","canonical_sha256":"a915d2ee02069a72c2a15cf1851cb03de983a22dc0a64deffbbf097229e1e7ab","source":{"kind":"arxiv","id":"2302.13668","version":2},"attestation_state":"computed","paper":{"title":"Contrastive Video Question Answering via Video Graph Transformer","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.MM"],"primary_cat":"cs.CV","authors_text":"Angela Yao, Junbin Xiao, Pan Zhou, Richang Hong, Shuicheng Yan, Tat-Seng Chua, Yicong Li","submitted_at":"2023-02-27T11:09:13Z","abstract_excerpt":"We propose to perform video question answering (VideoQA) in a Contrastive manner via a Video Graph Transformer model (CoVGT). CoVGT's uniqueness and superiority are three-fold: 1) It proposes a dynamic graph transformer module which encodes video by explicitly capturing the visual objects, their relations and dynamics, for complex spatio-temporal reasoning. 2) It designs separate video and text transformers for contrastive learning between the video and text to perform QA, instead of multi-modal transformer for answer classification. Fine-grained video-text communication is done by additional "},"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":"2302.13668","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2023-02-27T11:09:13Z","cross_cats_sorted":["cs.MM"],"title_canon_sha256":"b776a2841154c8a05708840ef82e7ba67ab58afc7336c8666468fa19bbbbba41","abstract_canon_sha256":"7e6d6a3745616ea2ac5a22c62d549b3a223afd61ab17b48db883a3745e292d47"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:29:20.036742Z","signature_b64":"VMnilIb+QL//8gsnJW7ZeyoQV90ttKq/XF/sw5MMV4ivhNpFEbKGef5uOIySVh7Mby/rkKEo/H1wEb4UWlsoAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"a915d2ee02069a72c2a15cf1851cb03de983a22dc0a64deffbbf097229e1e7ab","last_reissued_at":"2026-07-05T06:29:20.036337Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:29:20.036337Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Contrastive Video Question Answering via Video Graph Transformer","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.MM"],"primary_cat":"cs.CV","authors_text":"Angela Yao, Junbin Xiao, Pan Zhou, Richang Hong, Shuicheng Yan, Tat-Seng Chua, Yicong Li","submitted_at":"2023-02-27T11:09:13Z","abstract_excerpt":"We propose to perform video question answering (VideoQA) in a Contrastive manner via a Video Graph Transformer model (CoVGT). CoVGT's uniqueness and superiority are three-fold: 1) It proposes a dynamic graph transformer module which encodes video by explicitly capturing the visual objects, their relations and dynamics, for complex spatio-temporal reasoning. 2) It designs separate video and text transformers for contrastive learning between the video and text to perform QA, instead of multi-modal transformer for answer classification. Fine-grained video-text communication is done by additional "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2302.13668","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/2302.13668/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":"2302.13668","created_at":"2026-07-05T06:29:20.036392+00:00"},{"alias_kind":"arxiv_version","alias_value":"2302.13668v2","created_at":"2026-07-05T06:29:20.036392+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2302.13668","created_at":"2026-07-05T06:29:20.036392+00:00"},{"alias_kind":"pith_short_12","alias_value":"VEK5F3QCA2NH","created_at":"2026-07-05T06:29:20.036392+00:00"},{"alias_kind":"pith_short_16","alias_value":"VEK5F3QCA2NHFQVB","created_at":"2026-07-05T06:29:20.036392+00:00"},{"alias_kind":"pith_short_8","alias_value":"VEK5F3QC","created_at":"2026-07-05T06:29:20.036392+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/VEK5F3QCA2NHFQVBLTYYKHFQHX","json":"https://pith.science/pith/VEK5F3QCA2NHFQVBLTYYKHFQHX.json","graph_json":"https://pith.science/api/pith-number/VEK5F3QCA2NHFQVBLTYYKHFQHX/graph.json","events_json":"https://pith.science/api/pith-number/VEK5F3QCA2NHFQVBLTYYKHFQHX/events.json","paper":"https://pith.science/paper/VEK5F3QC"},"agent_actions":{"view_html":"https://pith.science/pith/VEK5F3QCA2NHFQVBLTYYKHFQHX","download_json":"https://pith.science/pith/VEK5F3QCA2NHFQVBLTYYKHFQHX.json","view_paper":"https://pith.science/paper/VEK5F3QC","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2302.13668&json=true","fetch_graph":"https://pith.science/api/pith-number/VEK5F3QCA2NHFQVBLTYYKHFQHX/graph.json","fetch_events":"https://pith.science/api/pith-number/VEK5F3QCA2NHFQVBLTYYKHFQHX/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/VEK5F3QCA2NHFQVBLTYYKHFQHX/action/timestamp_anchor","attest_storage":"https://pith.science/pith/VEK5F3QCA2NHFQVBLTYYKHFQHX/action/storage_attestation","attest_author":"https://pith.science/pith/VEK5F3QCA2NHFQVBLTYYKHFQHX/action/author_attestation","sign_citation":"https://pith.science/pith/VEK5F3QCA2NHFQVBLTYYKHFQHX/action/citation_signature","submit_replication":"https://pith.science/pith/VEK5F3QCA2NHFQVBLTYYKHFQHX/action/replication_record"}},"created_at":"2026-07-05T06:29:20.036392+00:00","updated_at":"2026-07-05T06:29:20.036392+00:00"}