{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:JGJMVFHXAL63XITLRUR45R7R7W","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"9090a4d8fc438b71b17f60c32a2f761d5007731714e99bec4dcf1ed4d73bf3cd","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-03-26T17:59:58Z","title_canon_sha256":"a27838af118c97943d66d2008eaf0dd1174381801ee2246ac1e125da087b0314"},"schema_version":"1.0","source":{"id":"2403.17937","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2403.17937","created_at":"2026-07-05T09:12:03Z"},{"alias_kind":"arxiv_version","alias_value":"2403.17937v3","created_at":"2026-07-05T09:12:03Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2403.17937","created_at":"2026-07-05T09:12:03Z"},{"alias_kind":"pith_short_12","alias_value":"JGJMVFHXAL63","created_at":"2026-07-05T09:12:03Z"},{"alias_kind":"pith_short_16","alias_value":"JGJMVFHXAL63XITL","created_at":"2026-07-05T09:12:03Z"},{"alias_kind":"pith_short_8","alias_value":"JGJMVFHX","created_at":"2026-07-05T09:12:03Z"}],"graph_snapshots":[{"event_id":"sha256:efeacce787b687cef3ea1f6197c70e69e4726c275ff5c2453c980367a27e9726","target":"graph","created_at":"2026-07-05T09:12:03Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2403.17937/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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","authors_text":"Abdelrahman Shaker, Fahad Shahbaz Khan, Martin Danelljan, Ming-Hsuan Yang, Salman Khan, Syed Talal Wasim","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-03-26T17:59:58Z","title":"Efficient Video Object Segmentation via Modulated Cross-Attention Memory"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2403.17937","kind":"arxiv","version":3},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:ab91d2d240010f3ebac98f16c38c89681286ca4413e9dbec45ac754cfd7acff7","target":"record","created_at":"2026-07-05T09:12:03Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"9090a4d8fc438b71b17f60c32a2f761d5007731714e99bec4dcf1ed4d73bf3cd","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-03-26T17:59:58Z","title_canon_sha256":"a27838af118c97943d66d2008eaf0dd1174381801ee2246ac1e125da087b0314"},"schema_version":"1.0","source":{"id":"2403.17937","kind":"arxiv","version":3}},"canonical_sha256":"4992ca94f702fdbba26b8d23cec7f1fd8ee1a4bd7f3db89f367e714a362b870f","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"4992ca94f702fdbba26b8d23cec7f1fd8ee1a4bd7f3db89f367e714a362b870f","first_computed_at":"2026-07-05T09:12:03.579872Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:12:03.579872Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"MMh5mN5M7qFN9k9wk9V/VT3naP+SxE9wy7G3/hN+Z1MP1R4XHZ+D02ZYjrMfJ0zggkmN8pSUOl4+ePL3DsnQBg==","signature_status":"signed_v1","signed_at":"2026-07-05T09:12:03.580340Z","signed_message":"canonical_sha256_bytes"},"source_id":"2403.17937","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:ab91d2d240010f3ebac98f16c38c89681286ca4413e9dbec45ac754cfd7acff7","sha256:efeacce787b687cef3ea1f6197c70e69e4726c275ff5c2453c980367a27e9726"],"state_sha256":"703b9c7e67e2482ad56e1384c417e7527b8f6ed73363950180a24c90a36c4fca"}