{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:XC4TUHVVYHRLGKNSXUMSPNNIGQ","short_pith_number":"pith:XC4TUHVV","schema_version":"1.0","canonical_sha256":"b8b93a1eb5c1e2b329b2bd1927b5a8340b195ffe6cf0936d49580672fddeec2a","source":{"kind":"arxiv","id":"2308.05140","version":1},"attestation_state":"computed","paper":{"title":"Robust Object Modeling for Visual Tracking","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Gangshan Wu, Jie Liu, Jie Tang, Yidong Cai","submitted_at":"2023-08-09T15:32:03Z","abstract_excerpt":"Object modeling has become a core part of recent tracking frameworks. Current popular tackers use Transformer attention to extract the template feature separately or interactively with the search region. However, separate template learning lacks communication between the template and search regions, which brings difficulty in extracting discriminative target-oriented features. On the other hand, interactive template learning produces hybrid template features, which may introduce potential distractors to the template via the cluttered search regions. To enjoy the merits of both methods, we prop"},"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":"2308.05140","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-08-09T15:32:03Z","cross_cats_sorted":[],"title_canon_sha256":"77648efb4c901095b8aafde3761a7eb53ddde669e56e4d7a1e5f4ac745cb3411","abstract_canon_sha256":"6bb8f8e86917e3a59f2803994654fe3eee1cd5a00c1632d186366543673eacb7"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:39:56.254863Z","signature_b64":"RmovQdEb2mcmaP3zh0G1mBvTX7GXRBYICO/Do2d/5lckOcfugx1iTrqhYeUSzGavMlJQJVT3n+QjauXxPV4iDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"b8b93a1eb5c1e2b329b2bd1927b5a8340b195ffe6cf0936d49580672fddeec2a","last_reissued_at":"2026-07-05T06:39:56.254451Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:39:56.254451Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Robust Object Modeling for Visual Tracking","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Gangshan Wu, Jie Liu, Jie Tang, Yidong Cai","submitted_at":"2023-08-09T15:32:03Z","abstract_excerpt":"Object modeling has become a core part of recent tracking frameworks. Current popular tackers use Transformer attention to extract the template feature separately or interactively with the search region. However, separate template learning lacks communication between the template and search regions, which brings difficulty in extracting discriminative target-oriented features. On the other hand, interactive template learning produces hybrid template features, which may introduce potential distractors to the template via the cluttered search regions. To enjoy the merits of both methods, we prop"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2308.05140","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/2308.05140/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":"2308.05140","created_at":"2026-07-05T06:39:56.254512+00:00"},{"alias_kind":"arxiv_version","alias_value":"2308.05140v1","created_at":"2026-07-05T06:39:56.254512+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2308.05140","created_at":"2026-07-05T06:39:56.254512+00:00"},{"alias_kind":"pith_short_12","alias_value":"XC4TUHVVYHRL","created_at":"2026-07-05T06:39:56.254512+00:00"},{"alias_kind":"pith_short_16","alias_value":"XC4TUHVVYHRLGKNS","created_at":"2026-07-05T06:39:56.254512+00:00"},{"alias_kind":"pith_short_8","alias_value":"XC4TUHVV","created_at":"2026-07-05T06:39:56.254512+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2412.13611","citing_title":"Robust Tracking via Mamba-based Context-aware Token Learning","ref_index":4,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/XC4TUHVVYHRLGKNSXUMSPNNIGQ","json":"https://pith.science/pith/XC4TUHVVYHRLGKNSXUMSPNNIGQ.json","graph_json":"https://pith.science/api/pith-number/XC4TUHVVYHRLGKNSXUMSPNNIGQ/graph.json","events_json":"https://pith.science/api/pith-number/XC4TUHVVYHRLGKNSXUMSPNNIGQ/events.json","paper":"https://pith.science/paper/XC4TUHVV"},"agent_actions":{"view_html":"https://pith.science/pith/XC4TUHVVYHRLGKNSXUMSPNNIGQ","download_json":"https://pith.science/pith/XC4TUHVVYHRLGKNSXUMSPNNIGQ.json","view_paper":"https://pith.science/paper/XC4TUHVV","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2308.05140&json=true","fetch_graph":"https://pith.science/api/pith-number/XC4TUHVVYHRLGKNSXUMSPNNIGQ/graph.json","fetch_events":"https://pith.science/api/pith-number/XC4TUHVVYHRLGKNSXUMSPNNIGQ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/XC4TUHVVYHRLGKNSXUMSPNNIGQ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/XC4TUHVVYHRLGKNSXUMSPNNIGQ/action/storage_attestation","attest_author":"https://pith.science/pith/XC4TUHVVYHRLGKNSXUMSPNNIGQ/action/author_attestation","sign_citation":"https://pith.science/pith/XC4TUHVVYHRLGKNSXUMSPNNIGQ/action/citation_signature","submit_replication":"https://pith.science/pith/XC4TUHVVYHRLGKNSXUMSPNNIGQ/action/replication_record"}},"created_at":"2026-07-05T06:39:56.254512+00:00","updated_at":"2026-07-05T06:39:56.254512+00:00"}