{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:JGJMVFHXAL63XITLRUR45R7R7W","short_pith_number":"pith:JGJMVFHX","schema_version":"1.0","canonical_sha256":"4992ca94f702fdbba26b8d23cec7f1fd8ee1a4bd7f3db89f367e714a362b870f","source":{"kind":"arxiv","id":"2403.17937","version":3},"attestation_state":"computed","paper":{"title":"Efficient Video Object Segmentation via Modulated Cross-Attention Memory","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Abdelrahman Shaker, Fahad Shahbaz Khan, Martin Danelljan, Ming-Hsuan Yang, Salman Khan, Syed Talal Wasim","submitted_at":"2024-03-26T17:59:58Z","abstract_excerpt":"Recently, transformer-based approaches have shown promising results for semi-supervised video object segmentation. However, these approaches typically struggle on long videos due to increased GPU memory demands, as they frequently expand the memory bank every few frames. We propose a transformer-based approach, named MAVOS, that introduces an optimized and dynamic long-term modulated cross-attention (MCA) memory to model temporal smoothness without requiring frequent memory expansion. The proposed MCA effectively encodes both local and global features at various levels of granularity while eff"},"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":"2403.17937","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-03-26T17:59:58Z","cross_cats_sorted":[],"title_canon_sha256":"a27838af118c97943d66d2008eaf0dd1174381801ee2246ac1e125da087b0314","abstract_canon_sha256":"9090a4d8fc438b71b17f60c32a2f761d5007731714e99bec4dcf1ed4d73bf3cd"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:12:03.580340Z","signature_b64":"MMh5mN5M7qFN9k9wk9V/VT3naP+SxE9wy7G3/hN+Z1MP1R4XHZ+D02ZYjrMfJ0zggkmN8pSUOl4+ePL3DsnQBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"4992ca94f702fdbba26b8d23cec7f1fd8ee1a4bd7f3db89f367e714a362b870f","last_reissued_at":"2026-07-05T09:12:03.579872Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:12:03.579872Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Efficient Video Object Segmentation via Modulated Cross-Attention Memory","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Abdelrahman Shaker, Fahad Shahbaz Khan, Martin Danelljan, Ming-Hsuan Yang, Salman Khan, Syed Talal Wasim","submitted_at":"2024-03-26T17:59:58Z","abstract_excerpt":"Recently, transformer-based approaches have shown promising results for semi-supervised video object segmentation. However, these approaches typically struggle on long videos due to increased GPU memory demands, as they frequently expand the memory bank every few frames. We propose a transformer-based approach, named MAVOS, that introduces an optimized and dynamic long-term modulated cross-attention (MCA) memory to model temporal smoothness without requiring frequent memory expansion. The proposed MCA effectively encodes both local and global features at various levels of granularity while eff"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2403.17937","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/2403.17937/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":"2403.17937","created_at":"2026-07-05T09:12:03.579946+00:00"},{"alias_kind":"arxiv_version","alias_value":"2403.17937v3","created_at":"2026-07-05T09:12:03.579946+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2403.17937","created_at":"2026-07-05T09:12:03.579946+00:00"},{"alias_kind":"pith_short_12","alias_value":"JGJMVFHXAL63","created_at":"2026-07-05T09:12:03.579946+00:00"},{"alias_kind":"pith_short_16","alias_value":"JGJMVFHXAL63XITL","created_at":"2026-07-05T09:12:03.579946+00:00"},{"alias_kind":"pith_short_8","alias_value":"JGJMVFHX","created_at":"2026-07-05T09:12:03.579946+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/JGJMVFHXAL63XITLRUR45R7R7W","json":"https://pith.science/pith/JGJMVFHXAL63XITLRUR45R7R7W.json","graph_json":"https://pith.science/api/pith-number/JGJMVFHXAL63XITLRUR45R7R7W/graph.json","events_json":"https://pith.science/api/pith-number/JGJMVFHXAL63XITLRUR45R7R7W/events.json","paper":"https://pith.science/paper/JGJMVFHX"},"agent_actions":{"view_html":"https://pith.science/pith/JGJMVFHXAL63XITLRUR45R7R7W","download_json":"https://pith.science/pith/JGJMVFHXAL63XITLRUR45R7R7W.json","view_paper":"https://pith.science/paper/JGJMVFHX","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2403.17937&json=true","fetch_graph":"https://pith.science/api/pith-number/JGJMVFHXAL63XITLRUR45R7R7W/graph.json","fetch_events":"https://pith.science/api/pith-number/JGJMVFHXAL63XITLRUR45R7R7W/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/JGJMVFHXAL63XITLRUR45R7R7W/action/timestamp_anchor","attest_storage":"https://pith.science/pith/JGJMVFHXAL63XITLRUR45R7R7W/action/storage_attestation","attest_author":"https://pith.science/pith/JGJMVFHXAL63XITLRUR45R7R7W/action/author_attestation","sign_citation":"https://pith.science/pith/JGJMVFHXAL63XITLRUR45R7R7W/action/citation_signature","submit_replication":"https://pith.science/pith/JGJMVFHXAL63XITLRUR45R7R7W/action/replication_record"}},"created_at":"2026-07-05T09:12:03.579946+00:00","updated_at":"2026-07-05T09:12:03.579946+00:00"}