{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:X2KOM7SMZSHUW6P5YIU77PE6IU","short_pith_number":"pith:X2KOM7SM","schema_version":"1.0","canonical_sha256":"be94e67e4ccc8f4b79fdc229ffbc9e451358f71ca95e9d20851592b5af2134ea","source":{"kind":"arxiv","id":"2211.13470","version":1},"attestation_state":"computed","paper":{"title":"Efficient Zero-shot Visual Search via Target and Context-aware Transformer","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.CV","authors_text":"Erwan David, Gabriel Kreiman, Melissa Vo, Mengmi Zhang, Xuezhe Ren, Zhiwei Ding","submitted_at":"2022-11-24T08:27:47Z","abstract_excerpt":"Visual search is a ubiquitous challenge in natural vision, including daily tasks such as finding a friend in a crowd or searching for a car in a parking lot. Human rely heavily on relevant target features to perform goal-directed visual search. Meanwhile, context is of critical importance for locating a target object in complex scenes as it helps narrow down the search area and makes the search process more efficient. However, few works have combined both target and context information in visual search computational models. Here we propose a zero-shot deep learning architecture, TCT (Target an"},"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":"2211.13470","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2022-11-24T08:27:47Z","cross_cats_sorted":["cs.AI","cs.LG"],"title_canon_sha256":"c35daa6a5db70eb5715f5de65d7d51cfbe751de927914c936ed3c9d1a0bccc96","abstract_canon_sha256":"11419c072ab2e3f5edf754113bfe1fcc76a7d87f8decef8a43e64262109bf0a6"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:19:22.629163Z","signature_b64":"cilgZ9co06+E3VfUaBEgtWheDFfcfauG8+4yGbkxRvJbaGjII7PX9zyh0+eWhbFTZwMDq4zQhKv3Nxz7QgpODw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"be94e67e4ccc8f4b79fdc229ffbc9e451358f71ca95e9d20851592b5af2134ea","last_reissued_at":"2026-07-05T05:19:22.628763Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:19:22.628763Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Efficient Zero-shot Visual Search via Target and Context-aware Transformer","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.CV","authors_text":"Erwan David, Gabriel Kreiman, Melissa Vo, Mengmi Zhang, Xuezhe Ren, Zhiwei Ding","submitted_at":"2022-11-24T08:27:47Z","abstract_excerpt":"Visual search is a ubiquitous challenge in natural vision, including daily tasks such as finding a friend in a crowd or searching for a car in a parking lot. Human rely heavily on relevant target features to perform goal-directed visual search. Meanwhile, context is of critical importance for locating a target object in complex scenes as it helps narrow down the search area and makes the search process more efficient. However, few works have combined both target and context information in visual search computational models. Here we propose a zero-shot deep learning architecture, TCT (Target an"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2211.13470","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/2211.13470/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":"2211.13470","created_at":"2026-07-05T05:19:22.628820+00:00"},{"alias_kind":"arxiv_version","alias_value":"2211.13470v1","created_at":"2026-07-05T05:19:22.628820+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2211.13470","created_at":"2026-07-05T05:19:22.628820+00:00"},{"alias_kind":"pith_short_12","alias_value":"X2KOM7SMZSHU","created_at":"2026-07-05T05:19:22.628820+00:00"},{"alias_kind":"pith_short_16","alias_value":"X2KOM7SMZSHUW6P5","created_at":"2026-07-05T05:19:22.628820+00:00"},{"alias_kind":"pith_short_8","alias_value":"X2KOM7SM","created_at":"2026-07-05T05:19:22.628820+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2411.09176","citing_title":"Gazing at Rewards: Eye Movements as a Lens into Human and AI Decision-Making in Hybrid Visual Foraging","ref_index":31,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/X2KOM7SMZSHUW6P5YIU77PE6IU","json":"https://pith.science/pith/X2KOM7SMZSHUW6P5YIU77PE6IU.json","graph_json":"https://pith.science/api/pith-number/X2KOM7SMZSHUW6P5YIU77PE6IU/graph.json","events_json":"https://pith.science/api/pith-number/X2KOM7SMZSHUW6P5YIU77PE6IU/events.json","paper":"https://pith.science/paper/X2KOM7SM"},"agent_actions":{"view_html":"https://pith.science/pith/X2KOM7SMZSHUW6P5YIU77PE6IU","download_json":"https://pith.science/pith/X2KOM7SMZSHUW6P5YIU77PE6IU.json","view_paper":"https://pith.science/paper/X2KOM7SM","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2211.13470&json=true","fetch_graph":"https://pith.science/api/pith-number/X2KOM7SMZSHUW6P5YIU77PE6IU/graph.json","fetch_events":"https://pith.science/api/pith-number/X2KOM7SMZSHUW6P5YIU77PE6IU/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/X2KOM7SMZSHUW6P5YIU77PE6IU/action/timestamp_anchor","attest_storage":"https://pith.science/pith/X2KOM7SMZSHUW6P5YIU77PE6IU/action/storage_attestation","attest_author":"https://pith.science/pith/X2KOM7SMZSHUW6P5YIU77PE6IU/action/author_attestation","sign_citation":"https://pith.science/pith/X2KOM7SMZSHUW6P5YIU77PE6IU/action/citation_signature","submit_replication":"https://pith.science/pith/X2KOM7SMZSHUW6P5YIU77PE6IU/action/replication_record"}},"created_at":"2026-07-05T05:19:22.628820+00:00","updated_at":"2026-07-05T05:19:22.628820+00:00"}