{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:5LFBVW5JJMYZGZQEJ2VM7ZZXRL","short_pith_number":"pith:5LFBVW5J","schema_version":"1.0","canonical_sha256":"eaca1adba94b319366044eaacfe7378ae666b28c98eeaca4c1c3c1118d2a5b7c","source":{"kind":"arxiv","id":"2505.12606","version":1},"attestation_state":"computed","paper":{"title":"Diff-MM: Exploring Pre-trained Text-to-Image Generation Model for Unified Multi-modal Object Tracking","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Jinhui Tang, Shiyu Xuan, Zechao Li","submitted_at":"2025-05-19T01:42:13Z","abstract_excerpt":"Multi-modal object tracking integrates auxiliary modalities such as depth, thermal infrared, event flow, and language to provide additional information beyond RGB images, showing great potential in improving tracking stabilization in complex scenarios. Existing methods typically start from an RGB-based tracker and learn to understand auxiliary modalities only from training data. Constrained by the limited multi-modal training data, the performance of these methods is unsatisfactory. To alleviate this limitation, this work proposes a unified multi-modal tracker Diff-MM by exploiting the multi-m"},"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":"2505.12606","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-05-19T01:42:13Z","cross_cats_sorted":[],"title_canon_sha256":"2922ec9cb0ad925725076b28d52af8453f2fa8e2272ecf7e06ac6a51586673c1","abstract_canon_sha256":"3ad55e598db8178a6589975a490529a36dc6f4d9fa1f6715ebbc6455ca60fdc3"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:05:06.823909Z","signature_b64":"qkvln/IKLsFVr2ESJAWdvVGkWSxYfRdIZjDhrep9MoB2S7QuHZcTOKrjqX5tesZ8fpKfK5anj1PDyo0zURDFBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"eaca1adba94b319366044eaacfe7378ae666b28c98eeaca4c1c3c1118d2a5b7c","last_reissued_at":"2026-07-05T11:05:06.823410Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:05:06.823410Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Diff-MM: Exploring Pre-trained Text-to-Image Generation Model for Unified Multi-modal Object Tracking","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Jinhui Tang, Shiyu Xuan, Zechao Li","submitted_at":"2025-05-19T01:42:13Z","abstract_excerpt":"Multi-modal object tracking integrates auxiliary modalities such as depth, thermal infrared, event flow, and language to provide additional information beyond RGB images, showing great potential in improving tracking stabilization in complex scenarios. Existing methods typically start from an RGB-based tracker and learn to understand auxiliary modalities only from training data. Constrained by the limited multi-modal training data, the performance of these methods is unsatisfactory. To alleviate this limitation, this work proposes a unified multi-modal tracker Diff-MM by exploiting the multi-m"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.12606","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/2505.12606/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":"2505.12606","created_at":"2026-07-05T11:05:06.823469+00:00"},{"alias_kind":"arxiv_version","alias_value":"2505.12606v1","created_at":"2026-07-05T11:05:06.823469+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.12606","created_at":"2026-07-05T11:05:06.823469+00:00"},{"alias_kind":"pith_short_12","alias_value":"5LFBVW5JJMYZ","created_at":"2026-07-05T11:05:06.823469+00:00"},{"alias_kind":"pith_short_16","alias_value":"5LFBVW5JJMYZGZQE","created_at":"2026-07-05T11:05:06.823469+00:00"},{"alias_kind":"pith_short_8","alias_value":"5LFBVW5J","created_at":"2026-07-05T11:05:06.823469+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.22138","citing_title":"Efficient Agentic Reasoning Through Self-Regulated Simulative Planning","ref_index":115,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/5LFBVW5JJMYZGZQEJ2VM7ZZXRL","json":"https://pith.science/pith/5LFBVW5JJMYZGZQEJ2VM7ZZXRL.json","graph_json":"https://pith.science/api/pith-number/5LFBVW5JJMYZGZQEJ2VM7ZZXRL/graph.json","events_json":"https://pith.science/api/pith-number/5LFBVW5JJMYZGZQEJ2VM7ZZXRL/events.json","paper":"https://pith.science/paper/5LFBVW5J"},"agent_actions":{"view_html":"https://pith.science/pith/5LFBVW5JJMYZGZQEJ2VM7ZZXRL","download_json":"https://pith.science/pith/5LFBVW5JJMYZGZQEJ2VM7ZZXRL.json","view_paper":"https://pith.science/paper/5LFBVW5J","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2505.12606&json=true","fetch_graph":"https://pith.science/api/pith-number/5LFBVW5JJMYZGZQEJ2VM7ZZXRL/graph.json","fetch_events":"https://pith.science/api/pith-number/5LFBVW5JJMYZGZQEJ2VM7ZZXRL/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/5LFBVW5JJMYZGZQEJ2VM7ZZXRL/action/timestamp_anchor","attest_storage":"https://pith.science/pith/5LFBVW5JJMYZGZQEJ2VM7ZZXRL/action/storage_attestation","attest_author":"https://pith.science/pith/5LFBVW5JJMYZGZQEJ2VM7ZZXRL/action/author_attestation","sign_citation":"https://pith.science/pith/5LFBVW5JJMYZGZQEJ2VM7ZZXRL/action/citation_signature","submit_replication":"https://pith.science/pith/5LFBVW5JJMYZGZQEJ2VM7ZZXRL/action/replication_record"}},"created_at":"2026-07-05T11:05:06.823469+00:00","updated_at":"2026-07-05T11:05:06.823469+00:00"}