{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:7ECETK2DV2KFNPKBOCBD6K6QNT","short_pith_number":"pith:7ECETK2D","schema_version":"1.0","canonical_sha256":"f90449ab43ae9456bd4170823f2bd06cd403a3ab64e98561059ee101ffae04ea","source":{"kind":"arxiv","id":"2401.03142","version":1},"attestation_state":"computed","paper":{"title":"Explicit Visual Prompts for Visual Object Tracking","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Bineng Zhong, Liangtao Shi, Ning Li, Qihua Liang, Shengping Zhang, Xianxian Li","submitted_at":"2024-01-06T07:12:07Z","abstract_excerpt":"How to effectively exploit spatio-temporal information is crucial to capture target appearance changes in visual tracking. However, most deep learning-based trackers mainly focus on designing a complicated appearance model or template updating strategy, while lacking the exploitation of context between consecutive frames and thus entailing the \\textit{when-and-how-to-update} dilemma. To address these issues, we propose a novel explicit visual prompts framework for visual tracking, dubbed \\textbf{EVPTrack}. Specifically, we utilize spatio-temporal tokens to propagate information between consecu"},"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":"2401.03142","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-01-06T07:12:07Z","cross_cats_sorted":[],"title_canon_sha256":"6909126621a117b888236b77d269e94c93d5fba86ee8efb1d235cdaa707d3820","abstract_canon_sha256":"e7fa7912a6a70fd242710cafb1090e932f81cdebba0cc94f089e49dac7d35ebc"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:31:03.073331Z","signature_b64":"Qg0qfUcYOmWMKoHoGAN1uhypLfOWsDfV6vh/bUQoPc0BIMbVmMBCdpHvww+bM+7oLKb7rutr2QcumCcGyyjzDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"f90449ab43ae9456bd4170823f2bd06cd403a3ab64e98561059ee101ffae04ea","last_reissued_at":"2026-07-05T07:31:03.072835Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:31:03.072835Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Explicit Visual Prompts for Visual Object Tracking","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Bineng Zhong, Liangtao Shi, Ning Li, Qihua Liang, Shengping Zhang, Xianxian Li","submitted_at":"2024-01-06T07:12:07Z","abstract_excerpt":"How to effectively exploit spatio-temporal information is crucial to capture target appearance changes in visual tracking. However, most deep learning-based trackers mainly focus on designing a complicated appearance model or template updating strategy, while lacking the exploitation of context between consecutive frames and thus entailing the \\textit{when-and-how-to-update} dilemma. To address these issues, we propose a novel explicit visual prompts framework for visual tracking, dubbed \\textbf{EVPTrack}. Specifically, we utilize spatio-temporal tokens to propagate information between consecu"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2401.03142","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/2401.03142/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":"2401.03142","created_at":"2026-07-05T07:31:03.072892+00:00"},{"alias_kind":"arxiv_version","alias_value":"2401.03142v1","created_at":"2026-07-05T07:31:03.072892+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2401.03142","created_at":"2026-07-05T07:31:03.072892+00:00"},{"alias_kind":"pith_short_12","alias_value":"7ECETK2DV2KF","created_at":"2026-07-05T07:31:03.072892+00:00"},{"alias_kind":"pith_short_16","alias_value":"7ECETK2DV2KFNPKB","created_at":"2026-07-05T07:31:03.072892+00:00"},{"alias_kind":"pith_short_8","alias_value":"7ECETK2D","created_at":"2026-07-05T07:31:03.072892+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2505.19434","citing_title":"CSTrack: Enhancing RGB-X Tracking via Compact Spatiotemporal Features","ref_index":2019,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/7ECETK2DV2KFNPKBOCBD6K6QNT","json":"https://pith.science/pith/7ECETK2DV2KFNPKBOCBD6K6QNT.json","graph_json":"https://pith.science/api/pith-number/7ECETK2DV2KFNPKBOCBD6K6QNT/graph.json","events_json":"https://pith.science/api/pith-number/7ECETK2DV2KFNPKBOCBD6K6QNT/events.json","paper":"https://pith.science/paper/7ECETK2D"},"agent_actions":{"view_html":"https://pith.science/pith/7ECETK2DV2KFNPKBOCBD6K6QNT","download_json":"https://pith.science/pith/7ECETK2DV2KFNPKBOCBD6K6QNT.json","view_paper":"https://pith.science/paper/7ECETK2D","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2401.03142&json=true","fetch_graph":"https://pith.science/api/pith-number/7ECETK2DV2KFNPKBOCBD6K6QNT/graph.json","fetch_events":"https://pith.science/api/pith-number/7ECETK2DV2KFNPKBOCBD6K6QNT/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/7ECETK2DV2KFNPKBOCBD6K6QNT/action/timestamp_anchor","attest_storage":"https://pith.science/pith/7ECETK2DV2KFNPKBOCBD6K6QNT/action/storage_attestation","attest_author":"https://pith.science/pith/7ECETK2DV2KFNPKBOCBD6K6QNT/action/author_attestation","sign_citation":"https://pith.science/pith/7ECETK2DV2KFNPKBOCBD6K6QNT/action/citation_signature","submit_replication":"https://pith.science/pith/7ECETK2DV2KFNPKBOCBD6K6QNT/action/replication_record"}},"created_at":"2026-07-05T07:31:03.072892+00:00","updated_at":"2026-07-05T07:31:03.072892+00:00"}