{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:ZIK6EJKUXJL2XUE35RMX2CP4RW","short_pith_number":"pith:ZIK6EJKU","schema_version":"1.0","canonical_sha256":"ca15e22554ba57abd09bec597d09fc8d9d2fcb0b9d030cd54bee98525d2a5e53","source":{"kind":"arxiv","id":"2205.03776","version":1},"attestation_state":"computed","paper":{"title":"SparseTT: Visual Tracking with Sparse Transformers","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Qingjie Liu, Wenrui Cai, Yunhong Wang, Zehua Fu, Zhihong Fu","submitted_at":"2022-05-08T04:00:28Z","abstract_excerpt":"Transformers have been successfully applied to the visual tracking task and significantly promote tracking performance. The self-attention mechanism designed to model long-range dependencies is the key to the success of Transformers. However, self-attention lacks focusing on the most relevant information in the search regions, making it easy to be distracted by background. In this paper, we relieve this issue with a sparse attention mechanism by focusing the most relevant information in the search regions, which enables a much accurate tracking. Furthermore, we introduce a double-head predicto"},"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":"2205.03776","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2022-05-08T04:00:28Z","cross_cats_sorted":[],"title_canon_sha256":"b886f06918e5989a7ec6cd9b18997d814beea8df35f70bb7ddbe9af27b64ba02","abstract_canon_sha256":"2c40dd7ba588ec4f1793c0341e07f8a4322f3916cda756773ee9530c260f3cb7"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T04:21:18.430228Z","signature_b64":"8WVQp6muzgTS7mCmh5ZpwDrMyi4C5iT1rvwv1evRKO8xwx3A6CUvxOnmEWUN5lvi6K05bgnRCwQPITt+GeG8AQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"ca15e22554ba57abd09bec597d09fc8d9d2fcb0b9d030cd54bee98525d2a5e53","last_reissued_at":"2026-07-05T04:21:18.429814Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T04:21:18.429814Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"SparseTT: Visual Tracking with Sparse Transformers","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Qingjie Liu, Wenrui Cai, Yunhong Wang, Zehua Fu, Zhihong Fu","submitted_at":"2022-05-08T04:00:28Z","abstract_excerpt":"Transformers have been successfully applied to the visual tracking task and significantly promote tracking performance. The self-attention mechanism designed to model long-range dependencies is the key to the success of Transformers. However, self-attention lacks focusing on the most relevant information in the search regions, making it easy to be distracted by background. In this paper, we relieve this issue with a sparse attention mechanism by focusing the most relevant information in the search regions, which enables a much accurate tracking. Furthermore, we introduce a double-head predicto"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2205.03776","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/2205.03776/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":"2205.03776","created_at":"2026-07-05T04:21:18.429875+00:00"},{"alias_kind":"arxiv_version","alias_value":"2205.03776v1","created_at":"2026-07-05T04:21:18.429875+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2205.03776","created_at":"2026-07-05T04:21:18.429875+00:00"},{"alias_kind":"pith_short_12","alias_value":"ZIK6EJKUXJL2","created_at":"2026-07-05T04:21:18.429875+00:00"},{"alias_kind":"pith_short_16","alias_value":"ZIK6EJKUXJL2XUE3","created_at":"2026-07-05T04:21:18.429875+00:00"},{"alias_kind":"pith_short_8","alias_value":"ZIK6EJKU","created_at":"2026-07-05T04:21:18.429875+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2506.11040","citing_title":"Large Language models for Time Series Analysis: Techniques, Applications, and Challenges","ref_index":110,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/ZIK6EJKUXJL2XUE35RMX2CP4RW","json":"https://pith.science/pith/ZIK6EJKUXJL2XUE35RMX2CP4RW.json","graph_json":"https://pith.science/api/pith-number/ZIK6EJKUXJL2XUE35RMX2CP4RW/graph.json","events_json":"https://pith.science/api/pith-number/ZIK6EJKUXJL2XUE35RMX2CP4RW/events.json","paper":"https://pith.science/paper/ZIK6EJKU"},"agent_actions":{"view_html":"https://pith.science/pith/ZIK6EJKUXJL2XUE35RMX2CP4RW","download_json":"https://pith.science/pith/ZIK6EJKUXJL2XUE35RMX2CP4RW.json","view_paper":"https://pith.science/paper/ZIK6EJKU","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2205.03776&json=true","fetch_graph":"https://pith.science/api/pith-number/ZIK6EJKUXJL2XUE35RMX2CP4RW/graph.json","fetch_events":"https://pith.science/api/pith-number/ZIK6EJKUXJL2XUE35RMX2CP4RW/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/ZIK6EJKUXJL2XUE35RMX2CP4RW/action/timestamp_anchor","attest_storage":"https://pith.science/pith/ZIK6EJKUXJL2XUE35RMX2CP4RW/action/storage_attestation","attest_author":"https://pith.science/pith/ZIK6EJKUXJL2XUE35RMX2CP4RW/action/author_attestation","sign_citation":"https://pith.science/pith/ZIK6EJKUXJL2XUE35RMX2CP4RW/action/citation_signature","submit_replication":"https://pith.science/pith/ZIK6EJKUXJL2XUE35RMX2CP4RW/action/replication_record"}},"created_at":"2026-07-05T04:21:18.429875+00:00","updated_at":"2026-07-05T04:21:18.429875+00:00"}