{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:N2QFVWVTDHURQSMDOFV24XZOQL","short_pith_number":"pith:N2QFVWVT","schema_version":"1.0","canonical_sha256":"6ea05adab319e9184983716bae5f2e82d91234bd1bf4ad56eb8215bfb5c73ea0","source":{"kind":"arxiv","id":"2201.08949","version":2},"attestation_state":"computed","paper":{"title":"Temporal Aggregation for Adaptive RGBT Tracking","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Tianyang Xu, Xiao-Jun Wu, Zhangyong Tang","submitted_at":"2022-01-22T02:31:56Z","abstract_excerpt":"Visual object tracking with RGB and thermal infrared (TIR) spectra available, shorted in RGBT tracking, is a novel and challenging research topic which draws increasing attention nowadays. In this paper, we propose an RGBT tracker which takes spatio-temporal clues into account for robust appearance model learning, and simultaneously, constructs an adaptive fusion sub-network for cross-modal interactions. Unlike most existing RGBT trackers that implement object tracking tasks with only spatial information included, temporal information is further considered in this method. Specifically, differe"},"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":"2201.08949","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2022-01-22T02:31:56Z","cross_cats_sorted":[],"title_canon_sha256":"5fe592df6d718289e86ceddaf9ad42205aeff78e17066f027365e7cd0000e1d6","abstract_canon_sha256":"d5e093109f11b80515493c9a8d649f8372d7479eb1de0f14ca9ba92d2d25bc39"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T03:52:34.809025Z","signature_b64":"ohLnJ5oxogQsBUWVvs9+o3GhxC1t+QQGOtDKU2T7Y80cDa51ZNCly5zmlMhigeUsongVu7q8wg4OMBLD/iM9BA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"6ea05adab319e9184983716bae5f2e82d91234bd1bf4ad56eb8215bfb5c73ea0","last_reissued_at":"2026-07-05T03:52:34.808629Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T03:52:34.808629Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Temporal Aggregation for Adaptive RGBT Tracking","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Tianyang Xu, Xiao-Jun Wu, Zhangyong Tang","submitted_at":"2022-01-22T02:31:56Z","abstract_excerpt":"Visual object tracking with RGB and thermal infrared (TIR) spectra available, shorted in RGBT tracking, is a novel and challenging research topic which draws increasing attention nowadays. In this paper, we propose an RGBT tracker which takes spatio-temporal clues into account for robust appearance model learning, and simultaneously, constructs an adaptive fusion sub-network for cross-modal interactions. Unlike most existing RGBT trackers that implement object tracking tasks with only spatial information included, temporal information is further considered in this method. Specifically, differe"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2201.08949","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/2201.08949/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":"2201.08949","created_at":"2026-07-05T03:52:34.808676+00:00"},{"alias_kind":"arxiv_version","alias_value":"2201.08949v2","created_at":"2026-07-05T03:52:34.808676+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2201.08949","created_at":"2026-07-05T03:52:34.808676+00:00"},{"alias_kind":"pith_short_12","alias_value":"N2QFVWVTDHUR","created_at":"2026-07-05T03:52:34.808676+00:00"},{"alias_kind":"pith_short_16","alias_value":"N2QFVWVTDHURQSMD","created_at":"2026-07-05T03:52:34.808676+00:00"},{"alias_kind":"pith_short_8","alias_value":"N2QFVWVT","created_at":"2026-07-05T03:52:34.808676+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2412.15691","citing_title":"Exploiting Multimodal Spatial-temporal Patterns for Video Object Tracking","ref_index":36,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/N2QFVWVTDHURQSMDOFV24XZOQL","json":"https://pith.science/pith/N2QFVWVTDHURQSMDOFV24XZOQL.json","graph_json":"https://pith.science/api/pith-number/N2QFVWVTDHURQSMDOFV24XZOQL/graph.json","events_json":"https://pith.science/api/pith-number/N2QFVWVTDHURQSMDOFV24XZOQL/events.json","paper":"https://pith.science/paper/N2QFVWVT"},"agent_actions":{"view_html":"https://pith.science/pith/N2QFVWVTDHURQSMDOFV24XZOQL","download_json":"https://pith.science/pith/N2QFVWVTDHURQSMDOFV24XZOQL.json","view_paper":"https://pith.science/paper/N2QFVWVT","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2201.08949&json=true","fetch_graph":"https://pith.science/api/pith-number/N2QFVWVTDHURQSMDOFV24XZOQL/graph.json","fetch_events":"https://pith.science/api/pith-number/N2QFVWVTDHURQSMDOFV24XZOQL/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/N2QFVWVTDHURQSMDOFV24XZOQL/action/timestamp_anchor","attest_storage":"https://pith.science/pith/N2QFVWVTDHURQSMDOFV24XZOQL/action/storage_attestation","attest_author":"https://pith.science/pith/N2QFVWVTDHURQSMDOFV24XZOQL/action/author_attestation","sign_citation":"https://pith.science/pith/N2QFVWVTDHURQSMDOFV24XZOQL/action/citation_signature","submit_replication":"https://pith.science/pith/N2QFVWVTDHURQSMDOFV24XZOQL/action/replication_record"}},"created_at":"2026-07-05T03:52:34.808676+00:00","updated_at":"2026-07-05T03:52:34.808676+00:00"}