{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:46PIXHC7TLE5QBDN2ZSHWR2E3P","short_pith_number":"pith:46PIXHC7","schema_version":"1.0","canonical_sha256":"e79e8b9c5f9ac9d8046dd6647b4744dbdcd3a4ebd42069bac9d3d1e6db4ab7d5","source":{"kind":"arxiv","id":"2303.07815","version":1},"attestation_state":"computed","paper":{"title":"MobileVOS: Real-Time Video Object Segmentation Contrastive Learning meets Knowledge Distillation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Albert Saa-Garriga, Bruno Manganelli, Mehmet Kerim Yucel, Roy Miles","submitted_at":"2023-03-14T11:46:04Z","abstract_excerpt":"This paper tackles the problem of semi-supervised video object segmentation on resource-constrained devices, such as mobile phones. We formulate this problem as a distillation task, whereby we demonstrate that small space-time-memory networks with finite memory can achieve competitive results with state of the art, but at a fraction of the computational cost (32 milliseconds per frame on a Samsung Galaxy S22). Specifically, we provide a theoretically grounded framework that unifies knowledge distillation with supervised contrastive representation learning. These models are able to jointly bene"},"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":"2303.07815","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-03-14T11:46:04Z","cross_cats_sorted":[],"title_canon_sha256":"96046611de919afafb65598ab74427bbb2b231eedd7fbe099efd3042fca69892","abstract_canon_sha256":"da3a1766b4384dbddb75c4fdd42b6784c548f29507a3398ede1ad25d46939dcf"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:51:11.859383Z","signature_b64":"AhpUlx8oNOiQH8pBUkYxQl38GaUgbagabCWsaw+6qfduZuuOJUoETzIZRSbl2ydZH0n64iVJot0lU7kCbXpIBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"e79e8b9c5f9ac9d8046dd6647b4744dbdcd3a4ebd42069bac9d3d1e6db4ab7d5","last_reissued_at":"2026-07-05T05:51:11.858846Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:51:11.858846Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"MobileVOS: Real-Time Video Object Segmentation Contrastive Learning meets Knowledge Distillation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Albert Saa-Garriga, Bruno Manganelli, Mehmet Kerim Yucel, Roy Miles","submitted_at":"2023-03-14T11:46:04Z","abstract_excerpt":"This paper tackles the problem of semi-supervised video object segmentation on resource-constrained devices, such as mobile phones. We formulate this problem as a distillation task, whereby we demonstrate that small space-time-memory networks with finite memory can achieve competitive results with state of the art, but at a fraction of the computational cost (32 milliseconds per frame on a Samsung Galaxy S22). Specifically, we provide a theoretically grounded framework that unifies knowledge distillation with supervised contrastive representation learning. These models are able to jointly bene"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2303.07815","kind":"arxiv","version":1},"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/2303.07815/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":"2303.07815","created_at":"2026-07-05T05:51:11.858921+00:00"},{"alias_kind":"arxiv_version","alias_value":"2303.07815v1","created_at":"2026-07-05T05:51:11.858921+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2303.07815","created_at":"2026-07-05T05:51:11.858921+00:00"},{"alias_kind":"pith_short_12","alias_value":"46PIXHC7TLE5","created_at":"2026-07-05T05:51:11.858921+00:00"},{"alias_kind":"pith_short_16","alias_value":"46PIXHC7TLE5QBDN","created_at":"2026-07-05T05:51:11.858921+00:00"},{"alias_kind":"pith_short_8","alias_value":"46PIXHC7","created_at":"2026-07-05T05:51:11.858921+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2507.15628","citing_title":"A Survey on Efficiency Optimization Techniques for DNN-based Video Analytics: Process Systems, Algorithms, and Applications","ref_index":45,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/46PIXHC7TLE5QBDN2ZSHWR2E3P","json":"https://pith.science/pith/46PIXHC7TLE5QBDN2ZSHWR2E3P.json","graph_json":"https://pith.science/api/pith-number/46PIXHC7TLE5QBDN2ZSHWR2E3P/graph.json","events_json":"https://pith.science/api/pith-number/46PIXHC7TLE5QBDN2ZSHWR2E3P/events.json","paper":"https://pith.science/paper/46PIXHC7"},"agent_actions":{"view_html":"https://pith.science/pith/46PIXHC7TLE5QBDN2ZSHWR2E3P","download_json":"https://pith.science/pith/46PIXHC7TLE5QBDN2ZSHWR2E3P.json","view_paper":"https://pith.science/paper/46PIXHC7","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2303.07815&json=true","fetch_graph":"https://pith.science/api/pith-number/46PIXHC7TLE5QBDN2ZSHWR2E3P/graph.json","fetch_events":"https://pith.science/api/pith-number/46PIXHC7TLE5QBDN2ZSHWR2E3P/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/46PIXHC7TLE5QBDN2ZSHWR2E3P/action/timestamp_anchor","attest_storage":"https://pith.science/pith/46PIXHC7TLE5QBDN2ZSHWR2E3P/action/storage_attestation","attest_author":"https://pith.science/pith/46PIXHC7TLE5QBDN2ZSHWR2E3P/action/author_attestation","sign_citation":"https://pith.science/pith/46PIXHC7TLE5QBDN2ZSHWR2E3P/action/citation_signature","submit_replication":"https://pith.science/pith/46PIXHC7TLE5QBDN2ZSHWR2E3P/action/replication_record"}},"created_at":"2026-07-05T05:51:11.858921+00:00","updated_at":"2026-07-05T05:51:11.858921+00:00"}