{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:4POUT6BDXZG2X2ZSAKPL4ZANE6","short_pith_number":"pith:4POUT6BD","schema_version":"1.0","canonical_sha256":"e3dd49f823be4dabeb32029ebe640d2786b5cfaeac1481c1f247718c87ce3237","source":{"kind":"arxiv","id":"2312.17448","version":1},"attestation_state":"computed","paper":{"title":"Tracking with Human-Intent Reasoning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Bin Luo, Chenyang Li, Huchuan Lu, Jiawen Zhu, Jun-Yan He, Xuansong Xie, Yifeng Geng, Zhi-Qi Cheng","submitted_at":"2023-12-29T03:22:18Z","abstract_excerpt":"Advances in perception modeling have significantly improved the performance of object tracking. However, the current methods for specifying the target object in the initial frame are either by 1) using a box or mask template, or by 2) providing an explicit language description. These manners are cumbersome and do not allow the tracker to have self-reasoning ability. Therefore, this work proposes a new tracking task -- Instruction Tracking, which involves providing implicit tracking instructions that require the trackers to perform tracking automatically in video frames. To achieve this, we inv"},"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":"2312.17448","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-12-29T03:22:18Z","cross_cats_sorted":[],"title_canon_sha256":"64dace7e3110aeca026ed5e21114134b59545aac8110711a0279c85b34831f03","abstract_canon_sha256":"e6c8f67c4b0797437da14be1012638bfd6571f8d0408f8faa245070a7583c1e1"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:28:52.080705Z","signature_b64":"1MwL2mf4oqLA5PMMy17YeRTMVe/uVrtxPRBRmN1MvXceABRTv/fgXvERh5veQRh5xCdoeP233B9ZA8TdYBy0Cg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"e3dd49f823be4dabeb32029ebe640d2786b5cfaeac1481c1f247718c87ce3237","last_reissued_at":"2026-07-05T07:28:52.080236Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:28:52.080236Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Tracking with Human-Intent Reasoning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Bin Luo, Chenyang Li, Huchuan Lu, Jiawen Zhu, Jun-Yan He, Xuansong Xie, Yifeng Geng, Zhi-Qi Cheng","submitted_at":"2023-12-29T03:22:18Z","abstract_excerpt":"Advances in perception modeling have significantly improved the performance of object tracking. However, the current methods for specifying the target object in the initial frame are either by 1) using a box or mask template, or by 2) providing an explicit language description. These manners are cumbersome and do not allow the tracker to have self-reasoning ability. Therefore, this work proposes a new tracking task -- Instruction Tracking, which involves providing implicit tracking instructions that require the trackers to perform tracking automatically in video frames. To achieve this, we inv"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2312.17448","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/2312.17448/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":"2312.17448","created_at":"2026-07-05T07:28:52.080299+00:00"},{"alias_kind":"arxiv_version","alias_value":"2312.17448v1","created_at":"2026-07-05T07:28:52.080299+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2312.17448","created_at":"2026-07-05T07:28:52.080299+00:00"},{"alias_kind":"pith_short_12","alias_value":"4POUT6BDXZG2","created_at":"2026-07-05T07:28:52.080299+00:00"},{"alias_kind":"pith_short_16","alias_value":"4POUT6BDXZG2X2ZS","created_at":"2026-07-05T07:28:52.080299+00:00"},{"alias_kind":"pith_short_8","alias_value":"4POUT6BD","created_at":"2026-07-05T07:28:52.080299+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":7,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.25585","citing_title":"FeVOS: Foresight Expression Video Object Segmentation","ref_index":49,"is_internal_anchor":false},{"citing_arxiv_id":"2606.26196","citing_title":"From Structure to Synergy: A Survey of Vision-Language Perception Paradigm Evolution in Multimodal Large Language Models","ref_index":88,"is_internal_anchor":false},{"citing_arxiv_id":"2606.26994","citing_title":"Event-Aware Instructed Assistant for Referring Video Segmentation","ref_index":63,"is_internal_anchor":false},{"citing_arxiv_id":"2605.20110","citing_title":"SetCon: Towards Open-Ended Referring Segmentation via Set-Level Concept Prediction","ref_index":73,"is_internal_anchor":false},{"citing_arxiv_id":"2604.11411","citing_title":"Online Reasoning Video Object Segmentation","ref_index":57,"is_internal_anchor":false},{"citing_arxiv_id":"2605.07334","citing_title":"RCoT-Seg: Reinforced Chain-of-Thought for Video Reasoning and Segmentation","ref_index":35,"is_internal_anchor":false},{"citing_arxiv_id":"2605.07064","citing_title":"Learning to Track Instance from Single Nature Language Description","ref_index":65,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/4POUT6BDXZG2X2ZSAKPL4ZANE6","json":"https://pith.science/pith/4POUT6BDXZG2X2ZSAKPL4ZANE6.json","graph_json":"https://pith.science/api/pith-number/4POUT6BDXZG2X2ZSAKPL4ZANE6/graph.json","events_json":"https://pith.science/api/pith-number/4POUT6BDXZG2X2ZSAKPL4ZANE6/events.json","paper":"https://pith.science/paper/4POUT6BD"},"agent_actions":{"view_html":"https://pith.science/pith/4POUT6BDXZG2X2ZSAKPL4ZANE6","download_json":"https://pith.science/pith/4POUT6BDXZG2X2ZSAKPL4ZANE6.json","view_paper":"https://pith.science/paper/4POUT6BD","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2312.17448&json=true","fetch_graph":"https://pith.science/api/pith-number/4POUT6BDXZG2X2ZSAKPL4ZANE6/graph.json","fetch_events":"https://pith.science/api/pith-number/4POUT6BDXZG2X2ZSAKPL4ZANE6/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/4POUT6BDXZG2X2ZSAKPL4ZANE6/action/timestamp_anchor","attest_storage":"https://pith.science/pith/4POUT6BDXZG2X2ZSAKPL4ZANE6/action/storage_attestation","attest_author":"https://pith.science/pith/4POUT6BDXZG2X2ZSAKPL4ZANE6/action/author_attestation","sign_citation":"https://pith.science/pith/4POUT6BDXZG2X2ZSAKPL4ZANE6/action/citation_signature","submit_replication":"https://pith.science/pith/4POUT6BDXZG2X2ZSAKPL4ZANE6/action/replication_record"}},"created_at":"2026-07-05T07:28:52.080299+00:00","updated_at":"2026-07-05T07:28:52.080299+00:00"}