{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:YZIV6MLPUFXS4ARXA2TB7N24B6","short_pith_number":"pith:YZIV6MLP","schema_version":"1.0","canonical_sha256":"c6515f316fa16f2e023706a61fb75c0fbabd8b13257c1cde2ae28eda0f119f43","source":{"kind":"arxiv","id":"2201.02526","version":1},"attestation_state":"computed","paper":{"title":"Learning Target-aware Representation for Visual Tracking via Informative Interactions","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Bing Li, Heng Fan, Liping Jing, Mingzhe Guo, Weiming Hu, Yilin Lyu, Zhipeng Zhang","submitted_at":"2022-01-07T16:22:27Z","abstract_excerpt":"We introduce a novel backbone architecture to improve target-perception ability of feature representation for tracking. Specifically, having observed that de facto frameworks perform feature matching simply using the outputs from backbone for target localization, there is no direct feedback from the matching module to the backbone network, especially the shallow layers. More concretely, only the matching module can directly access the target information (in the reference frame), while the representation learning of candidate frame is blind to the reference target. As a consequence, the accumul"},"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":"2201.02526","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2022-01-07T16:22:27Z","cross_cats_sorted":[],"title_canon_sha256":"70482807d4df37330e5c00be0d813d54d9e5c11bc04bb29b7fdd232359d03655","abstract_canon_sha256":"733a0b3652fc9cadd3ed3e6e41895737acb6645ec8c4e67f38696afc46c91cbd"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T03:46:41.920560Z","signature_b64":"M6ltb5EOtRYjczg81yMDft29c5id225ATObSlOYZ2v87r1YLsKG3gbl0IPzLN887X7WRBIJlsNNCtcSm9sLkAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"c6515f316fa16f2e023706a61fb75c0fbabd8b13257c1cde2ae28eda0f119f43","last_reissued_at":"2026-07-05T03:46:41.920177Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T03:46:41.920177Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Learning Target-aware Representation for Visual Tracking via Informative Interactions","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Bing Li, Heng Fan, Liping Jing, Mingzhe Guo, Weiming Hu, Yilin Lyu, Zhipeng Zhang","submitted_at":"2022-01-07T16:22:27Z","abstract_excerpt":"We introduce a novel backbone architecture to improve target-perception ability of feature representation for tracking. Specifically, having observed that de facto frameworks perform feature matching simply using the outputs from backbone for target localization, there is no direct feedback from the matching module to the backbone network, especially the shallow layers. More concretely, only the matching module can directly access the target information (in the reference frame), while the representation learning of candidate frame is blind to the reference target. As a consequence, the accumul"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2201.02526","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/2201.02526/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":"2201.02526","created_at":"2026-07-05T03:46:41.920241+00:00"},{"alias_kind":"arxiv_version","alias_value":"2201.02526v1","created_at":"2026-07-05T03:46:41.920241+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2201.02526","created_at":"2026-07-05T03:46:41.920241+00:00"},{"alias_kind":"pith_short_12","alias_value":"YZIV6MLPUFXS","created_at":"2026-07-05T03:46:41.920241+00:00"},{"alias_kind":"pith_short_16","alias_value":"YZIV6MLPUFXS4ARX","created_at":"2026-07-05T03:46:41.920241+00:00"},{"alias_kind":"pith_short_8","alias_value":"YZIV6MLP","created_at":"2026-07-05T03:46:41.920241+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2412.09991","citing_title":"Visual Object Tracking across Diverse Data Modalities: A Review","ref_index":78,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/YZIV6MLPUFXS4ARXA2TB7N24B6","json":"https://pith.science/pith/YZIV6MLPUFXS4ARXA2TB7N24B6.json","graph_json":"https://pith.science/api/pith-number/YZIV6MLPUFXS4ARXA2TB7N24B6/graph.json","events_json":"https://pith.science/api/pith-number/YZIV6MLPUFXS4ARXA2TB7N24B6/events.json","paper":"https://pith.science/paper/YZIV6MLP"},"agent_actions":{"view_html":"https://pith.science/pith/YZIV6MLPUFXS4ARXA2TB7N24B6","download_json":"https://pith.science/pith/YZIV6MLPUFXS4ARXA2TB7N24B6.json","view_paper":"https://pith.science/paper/YZIV6MLP","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2201.02526&json=true","fetch_graph":"https://pith.science/api/pith-number/YZIV6MLPUFXS4ARXA2TB7N24B6/graph.json","fetch_events":"https://pith.science/api/pith-number/YZIV6MLPUFXS4ARXA2TB7N24B6/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/YZIV6MLPUFXS4ARXA2TB7N24B6/action/timestamp_anchor","attest_storage":"https://pith.science/pith/YZIV6MLPUFXS4ARXA2TB7N24B6/action/storage_attestation","attest_author":"https://pith.science/pith/YZIV6MLPUFXS4ARXA2TB7N24B6/action/author_attestation","sign_citation":"https://pith.science/pith/YZIV6MLPUFXS4ARXA2TB7N24B6/action/citation_signature","submit_replication":"https://pith.science/pith/YZIV6MLPUFXS4ARXA2TB7N24B6/action/replication_record"}},"created_at":"2026-07-05T03:46:41.920241+00:00","updated_at":"2026-07-05T03:46:41.920241+00:00"}