{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:3457N2QLN3GRELAIVIXMTPUE75","short_pith_number":"pith:3457N2QL","schema_version":"1.0","canonical_sha256":"df3bf6ea0b6ecd122c08aa2ec9be84ff6b24b214e3c2756c92fe7100c22abb20","source":{"kind":"arxiv","id":"2403.19975","version":1},"attestation_state":"computed","paper":{"title":"Context-Aware Integration of Language and Visual References for Natural Language Tracking","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Jiming Chen, Qi Ye, Shuting He, Wenhan Luo, Yanyan Shao, Yuchao Feng","submitted_at":"2024-03-29T04:58:33Z","abstract_excerpt":"Tracking by natural language specification (TNL) aims to consistently localize a target in a video sequence given a linguistic description in the initial frame. Existing methodologies perform language-based and template-based matching for target reasoning separately and merge the matching results from two sources, which suffer from tracking drift when language and visual templates miss-align with the dynamic target state and ambiguity in the later merging stage. To tackle the issues, we propose a joint multi-modal tracking framework with 1) a prompt modulation module to leverage the complement"},"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":"2403.19975","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-03-29T04:58:33Z","cross_cats_sorted":[],"title_canon_sha256":"e59021b4baf0531d1309f9987175beefea2736a7c00abf3c8804c7585a3f4133","abstract_canon_sha256":"4a8f24f66b75e5b69b6ddeb7cb353df98f5919b36bede70aac863957914798d8"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:02:11.450224Z","signature_b64":"wJZxBq5IHWrmNP2SeIMNT8y98KEa8ZmA4lg2ZEGr9jnGLRNtuMLGcIvVcBdD1HMbpreh6SUL/gvh+QnuTryoDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"df3bf6ea0b6ecd122c08aa2ec9be84ff6b24b214e3c2756c92fe7100c22abb20","last_reissued_at":"2026-07-05T08:02:11.449803Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:02:11.449803Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Context-Aware Integration of Language and Visual References for Natural Language Tracking","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Jiming Chen, Qi Ye, Shuting He, Wenhan Luo, Yanyan Shao, Yuchao Feng","submitted_at":"2024-03-29T04:58:33Z","abstract_excerpt":"Tracking by natural language specification (TNL) aims to consistently localize a target in a video sequence given a linguistic description in the initial frame. Existing methodologies perform language-based and template-based matching for target reasoning separately and merge the matching results from two sources, which suffer from tracking drift when language and visual templates miss-align with the dynamic target state and ambiguity in the later merging stage. To tackle the issues, we propose a joint multi-modal tracking framework with 1) a prompt modulation module to leverage the complement"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2403.19975","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/2403.19975/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":"2403.19975","created_at":"2026-07-05T08:02:11.449865+00:00"},{"alias_kind":"arxiv_version","alias_value":"2403.19975v1","created_at":"2026-07-05T08:02:11.449865+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2403.19975","created_at":"2026-07-05T08:02:11.449865+00:00"},{"alias_kind":"pith_short_12","alias_value":"3457N2QLN3GR","created_at":"2026-07-05T08:02:11.449865+00:00"},{"alias_kind":"pith_short_16","alias_value":"3457N2QLN3GRELAI","created_at":"2026-07-05T08:02:11.449865+00:00"},{"alias_kind":"pith_short_8","alias_value":"3457N2QL","created_at":"2026-07-05T08:02:11.449865+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2412.19648","citing_title":"Enhancing Vision-Language Tracking by Effectively Converting Textual Cues into Visual Cues","ref_index":18,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/3457N2QLN3GRELAIVIXMTPUE75","json":"https://pith.science/pith/3457N2QLN3GRELAIVIXMTPUE75.json","graph_json":"https://pith.science/api/pith-number/3457N2QLN3GRELAIVIXMTPUE75/graph.json","events_json":"https://pith.science/api/pith-number/3457N2QLN3GRELAIVIXMTPUE75/events.json","paper":"https://pith.science/paper/3457N2QL"},"agent_actions":{"view_html":"https://pith.science/pith/3457N2QLN3GRELAIVIXMTPUE75","download_json":"https://pith.science/pith/3457N2QLN3GRELAIVIXMTPUE75.json","view_paper":"https://pith.science/paper/3457N2QL","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2403.19975&json=true","fetch_graph":"https://pith.science/api/pith-number/3457N2QLN3GRELAIVIXMTPUE75/graph.json","fetch_events":"https://pith.science/api/pith-number/3457N2QLN3GRELAIVIXMTPUE75/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/3457N2QLN3GRELAIVIXMTPUE75/action/timestamp_anchor","attest_storage":"https://pith.science/pith/3457N2QLN3GRELAIVIXMTPUE75/action/storage_attestation","attest_author":"https://pith.science/pith/3457N2QLN3GRELAIVIXMTPUE75/action/author_attestation","sign_citation":"https://pith.science/pith/3457N2QLN3GRELAIVIXMTPUE75/action/citation_signature","submit_replication":"https://pith.science/pith/3457N2QLN3GRELAIVIXMTPUE75/action/replication_record"}},"created_at":"2026-07-05T08:02:11.449865+00:00","updated_at":"2026-07-05T08:02:11.449865+00:00"}