{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:4AXMIBXROOVGJ6SOAZKK4LDSB6","short_pith_number":"pith:4AXMIBXR","schema_version":"1.0","canonical_sha256":"e02ec406f173aa64fa4e0654ae2c720faa0e9ae1a4300c334441339c7e0f5e5a","source":{"kind":"arxiv","id":"2411.17576","version":2},"attestation_state":"computed","paper":{"title":"A Distractor-Aware Memory for Visual Object Tracking with SAM2","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Alan Lukezic, Jovana Videnovic, Matej Kristan","submitted_at":"2024-11-26T16:41:09Z","abstract_excerpt":"Memory-based trackers are video object segmentation methods that form the target model by concatenating recently tracked frames into a memory buffer and localize the target by attending the current image to the buffered frames. While already achieving top performance on many benchmarks, it was the recent release of SAM2 that placed memory-based trackers into focus of the visual object tracking community. Nevertheless, modern trackers still struggle in the presence of distractors. We argue that a more sophisticated memory model is required, and propose a new distractor-aware memory model for SA"},"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":"2411.17576","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-11-26T16:41:09Z","cross_cats_sorted":[],"title_canon_sha256":"ebb8ac3202f91bf0ea7cfe6baeeb4f4353abf2e215a1cf189e820e99a99f1ce9","abstract_canon_sha256":"175ebef56c8afa534cd5e35c8801f97554b09a051507de8f8aa3ef102253e054"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:44:17.008996Z","signature_b64":"1rQ/4uv9fU6CD8tOykaZHtIXwkBNGw9ZzgVFiw4QLifJ2/0Dq9xJDcctqWTRhZDBPndPTffirHSQCDN4nuFWBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"e02ec406f173aa64fa4e0654ae2c720faa0e9ae1a4300c334441339c7e0f5e5a","last_reissued_at":"2026-07-05T09:44:17.008401Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:44:17.008401Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"A Distractor-Aware Memory for Visual Object Tracking with SAM2","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Alan Lukezic, Jovana Videnovic, Matej Kristan","submitted_at":"2024-11-26T16:41:09Z","abstract_excerpt":"Memory-based trackers are video object segmentation methods that form the target model by concatenating recently tracked frames into a memory buffer and localize the target by attending the current image to the buffered frames. While already achieving top performance on many benchmarks, it was the recent release of SAM2 that placed memory-based trackers into focus of the visual object tracking community. Nevertheless, modern trackers still struggle in the presence of distractors. We argue that a more sophisticated memory model is required, and propose a new distractor-aware memory model for SA"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2411.17576","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/2411.17576/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":"2411.17576","created_at":"2026-07-05T09:44:17.008469+00:00"},{"alias_kind":"arxiv_version","alias_value":"2411.17576v2","created_at":"2026-07-05T09:44:17.008469+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2411.17576","created_at":"2026-07-05T09:44:17.008469+00:00"},{"alias_kind":"pith_short_12","alias_value":"4AXMIBXROOVG","created_at":"2026-07-05T09:44:17.008469+00:00"},{"alias_kind":"pith_short_16","alias_value":"4AXMIBXROOVGJ6SO","created_at":"2026-07-05T09:44:17.008469+00:00"},{"alias_kind":"pith_short_8","alias_value":"4AXMIBXR","created_at":"2026-07-05T09:44:17.008469+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2510.18822","citing_title":"SAM 2++: Tracking Anything at Any Granularity","ref_index":52,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/4AXMIBXROOVGJ6SOAZKK4LDSB6","json":"https://pith.science/pith/4AXMIBXROOVGJ6SOAZKK4LDSB6.json","graph_json":"https://pith.science/api/pith-number/4AXMIBXROOVGJ6SOAZKK4LDSB6/graph.json","events_json":"https://pith.science/api/pith-number/4AXMIBXROOVGJ6SOAZKK4LDSB6/events.json","paper":"https://pith.science/paper/4AXMIBXR"},"agent_actions":{"view_html":"https://pith.science/pith/4AXMIBXROOVGJ6SOAZKK4LDSB6","download_json":"https://pith.science/pith/4AXMIBXROOVGJ6SOAZKK4LDSB6.json","view_paper":"https://pith.science/paper/4AXMIBXR","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2411.17576&json=true","fetch_graph":"https://pith.science/api/pith-number/4AXMIBXROOVGJ6SOAZKK4LDSB6/graph.json","fetch_events":"https://pith.science/api/pith-number/4AXMIBXROOVGJ6SOAZKK4LDSB6/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/4AXMIBXROOVGJ6SOAZKK4LDSB6/action/timestamp_anchor","attest_storage":"https://pith.science/pith/4AXMIBXROOVGJ6SOAZKK4LDSB6/action/storage_attestation","attest_author":"https://pith.science/pith/4AXMIBXROOVGJ6SOAZKK4LDSB6/action/author_attestation","sign_citation":"https://pith.science/pith/4AXMIBXROOVGJ6SOAZKK4LDSB6/action/citation_signature","submit_replication":"https://pith.science/pith/4AXMIBXROOVGJ6SOAZKK4LDSB6/action/replication_record"}},"created_at":"2026-07-05T09:44:17.008469+00:00","updated_at":"2026-07-05T09:44:17.008469+00:00"}