{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:NGBCDQUC637MFOWHYOBWEVMI7M","short_pith_number":"pith:NGBCDQUC","schema_version":"1.0","canonical_sha256":"698221c282f6fec2bac7c383625588fb1ebee821ab3b1f9189ad27897d7c0572","source":{"kind":"arxiv","id":"2207.10075","version":2},"attestation_state":"computed","paper":{"title":"Is an Object-Centric Video Representation Beneficial for Transfer?","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Andrew Zisserman, Ankush Gupta, Chuhan Zhang","submitted_at":"2022-07-20T17:59:44Z","abstract_excerpt":"The objective of this work is to learn an object-centric video representation, with the aim of improving transferability to novel tasks, i.e., tasks different from the pre-training task of action classification. To this end, we introduce a new object-centric video recognition model based on a transformer architecture. The model learns a set of object-centric summary vectors for the video, and uses these vectors to fuse the visual and spatio-temporal trajectory 'modalities' of the video clip. We also introduce a novel trajectory contrast loss to further enhance objectness in these summary vecto"},"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":"2207.10075","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2022-07-20T17:59:44Z","cross_cats_sorted":[],"title_canon_sha256":"76eccd0becba6c6528f08f8c7c45f9965630a5aa209d140a5a331170428ad50a","abstract_canon_sha256":"576d9cf8c8102144b54fa8d8ba1d482b869864905a34aecc3f8d003baaec4d19"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:04:30.334516Z","signature_b64":"5GIqdbd5Rsh1J2dn4p1ZCfuQHjg1HZZyOFKccx3wPQSW6gShuiItgQRmYM+fQQXRlGHmfMEnipmQ1Z65iTW4Bg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"698221c282f6fec2bac7c383625588fb1ebee821ab3b1f9189ad27897d7c0572","last_reissued_at":"2026-07-05T05:04:30.334079Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:04:30.334079Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Is an Object-Centric Video Representation Beneficial for Transfer?","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Andrew Zisserman, Ankush Gupta, Chuhan Zhang","submitted_at":"2022-07-20T17:59:44Z","abstract_excerpt":"The objective of this work is to learn an object-centric video representation, with the aim of improving transferability to novel tasks, i.e., tasks different from the pre-training task of action classification. To this end, we introduce a new object-centric video recognition model based on a transformer architecture. The model learns a set of object-centric summary vectors for the video, and uses these vectors to fuse the visual and spatio-temporal trajectory 'modalities' of the video clip. We also introduce a novel trajectory contrast loss to further enhance objectness in these summary vecto"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2207.10075","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/2207.10075/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":"2207.10075","created_at":"2026-07-05T05:04:30.334135+00:00"},{"alias_kind":"arxiv_version","alias_value":"2207.10075v2","created_at":"2026-07-05T05:04:30.334135+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2207.10075","created_at":"2026-07-05T05:04:30.334135+00:00"},{"alias_kind":"pith_short_12","alias_value":"NGBCDQUC637M","created_at":"2026-07-05T05:04:30.334135+00:00"},{"alias_kind":"pith_short_16","alias_value":"NGBCDQUC637MFOWH","created_at":"2026-07-05T05:04:30.334135+00:00"},{"alias_kind":"pith_short_8","alias_value":"NGBCDQUC","created_at":"2026-07-05T05:04:30.334135+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2506.19408","citing_title":"Is an object-centric representation beneficial for robotic manipulation ?","ref_index":42,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/NGBCDQUC637MFOWHYOBWEVMI7M","json":"https://pith.science/pith/NGBCDQUC637MFOWHYOBWEVMI7M.json","graph_json":"https://pith.science/api/pith-number/NGBCDQUC637MFOWHYOBWEVMI7M/graph.json","events_json":"https://pith.science/api/pith-number/NGBCDQUC637MFOWHYOBWEVMI7M/events.json","paper":"https://pith.science/paper/NGBCDQUC"},"agent_actions":{"view_html":"https://pith.science/pith/NGBCDQUC637MFOWHYOBWEVMI7M","download_json":"https://pith.science/pith/NGBCDQUC637MFOWHYOBWEVMI7M.json","view_paper":"https://pith.science/paper/NGBCDQUC","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2207.10075&json=true","fetch_graph":"https://pith.science/api/pith-number/NGBCDQUC637MFOWHYOBWEVMI7M/graph.json","fetch_events":"https://pith.science/api/pith-number/NGBCDQUC637MFOWHYOBWEVMI7M/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/NGBCDQUC637MFOWHYOBWEVMI7M/action/timestamp_anchor","attest_storage":"https://pith.science/pith/NGBCDQUC637MFOWHYOBWEVMI7M/action/storage_attestation","attest_author":"https://pith.science/pith/NGBCDQUC637MFOWHYOBWEVMI7M/action/author_attestation","sign_citation":"https://pith.science/pith/NGBCDQUC637MFOWHYOBWEVMI7M/action/citation_signature","submit_replication":"https://pith.science/pith/NGBCDQUC637MFOWHYOBWEVMI7M/action/replication_record"}},"created_at":"2026-07-05T05:04:30.334135+00:00","updated_at":"2026-07-05T05:04:30.334135+00:00"}