{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:PF4NXVGEG364ENVUWICUEJYME3","short_pith_number":"pith:PF4NXVGE","schema_version":"1.0","canonical_sha256":"7978dbd4c436fdc236b4b20542270c26d75bef1d685abc1abf9a8035d078f192","source":{"kind":"arxiv","id":"2405.17773","version":2},"attestation_state":"computed","paper":{"title":"XTrack: Multimodal Training Boosts RGB-X Video Object Trackers","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Chao Ma, Danda Pani Paudel, Eduard Zamfi, Guolei Sun, Luc Van Gool, Radu Timofte, Yuedong Tan, Yuqian Fu, Zhuyun Zhou, Zongwei Wu","submitted_at":"2024-05-28T03:00:58Z","abstract_excerpt":"Multimodal sensing has proven valuable for visual tracking, as different sensor types offer unique strengths in handling one specific challenging scene where object appearance varies. While a generalist model capable of leveraging all modalities would be ideal, development is hindered by data sparsity, typically in practice, only one modality is available at a time. Therefore, it is crucial to ensure and achieve that knowledge gained from multimodal sensing -- such as identifying relevant features and regions -- is effectively shared, even when certain modalities are unavailable at inference. "},"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":"2405.17773","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-05-28T03:00:58Z","cross_cats_sorted":[],"title_canon_sha256":"0ba55276ffbede9b70c08e1934c7e9362fb25d83a036d7300479f40141d61513","abstract_canon_sha256":"c0104f9c364e18ccbfc2de65af4eb8fefadefca1c5d6373e6fb20bc37ec28a59"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:41:37.423924Z","signature_b64":"602x5TICo/kouIZN5ItvCGCtegJdR62/30YL6HUa1XC9d70o2D69e6LBfYF7xF+ik2iKa2KimsRAAsHAB0S0BQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"7978dbd4c436fdc236b4b20542270c26d75bef1d685abc1abf9a8035d078f192","last_reissued_at":"2026-07-05T09:41:37.423488Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:41:37.423488Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"XTrack: Multimodal Training Boosts RGB-X Video Object Trackers","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Chao Ma, Danda Pani Paudel, Eduard Zamfi, Guolei Sun, Luc Van Gool, Radu Timofte, Yuedong Tan, Yuqian Fu, Zhuyun Zhou, Zongwei Wu","submitted_at":"2024-05-28T03:00:58Z","abstract_excerpt":"Multimodal sensing has proven valuable for visual tracking, as different sensor types offer unique strengths in handling one specific challenging scene where object appearance varies. While a generalist model capable of leveraging all modalities would be ideal, development is hindered by data sparsity, typically in practice, only one modality is available at a time. Therefore, it is crucial to ensure and achieve that knowledge gained from multimodal sensing -- such as identifying relevant features and regions -- is effectively shared, even when certain modalities are unavailable at inference. "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2405.17773","kind":"arxiv","version":2},"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/2405.17773/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":"2405.17773","created_at":"2026-07-05T09:41:37.423544+00:00"},{"alias_kind":"arxiv_version","alias_value":"2405.17773v2","created_at":"2026-07-05T09:41:37.423544+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2405.17773","created_at":"2026-07-05T09:41:37.423544+00:00"},{"alias_kind":"pith_short_12","alias_value":"PF4NXVGEG364","created_at":"2026-07-05T09:41:37.423544+00:00"},{"alias_kind":"pith_short_16","alias_value":"PF4NXVGEG364ENVU","created_at":"2026-07-05T09:41:37.423544+00:00"},{"alias_kind":"pith_short_8","alias_value":"PF4NXVGE","created_at":"2026-07-05T09:41:37.423544+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.03716","citing_title":"Unified Multimodal Visual Tracking with Dual Mixture-of-Experts","ref_index":7,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/PF4NXVGEG364ENVUWICUEJYME3","json":"https://pith.science/pith/PF4NXVGEG364ENVUWICUEJYME3.json","graph_json":"https://pith.science/api/pith-number/PF4NXVGEG364ENVUWICUEJYME3/graph.json","events_json":"https://pith.science/api/pith-number/PF4NXVGEG364ENVUWICUEJYME3/events.json","paper":"https://pith.science/paper/PF4NXVGE"},"agent_actions":{"view_html":"https://pith.science/pith/PF4NXVGEG364ENVUWICUEJYME3","download_json":"https://pith.science/pith/PF4NXVGEG364ENVUWICUEJYME3.json","view_paper":"https://pith.science/paper/PF4NXVGE","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2405.17773&json=true","fetch_graph":"https://pith.science/api/pith-number/PF4NXVGEG364ENVUWICUEJYME3/graph.json","fetch_events":"https://pith.science/api/pith-number/PF4NXVGEG364ENVUWICUEJYME3/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/PF4NXVGEG364ENVUWICUEJYME3/action/timestamp_anchor","attest_storage":"https://pith.science/pith/PF4NXVGEG364ENVUWICUEJYME3/action/storage_attestation","attest_author":"https://pith.science/pith/PF4NXVGEG364ENVUWICUEJYME3/action/author_attestation","sign_citation":"https://pith.science/pith/PF4NXVGEG364ENVUWICUEJYME3/action/citation_signature","submit_replication":"https://pith.science/pith/PF4NXVGEG364ENVUWICUEJYME3/action/replication_record"}},"created_at":"2026-07-05T09:41:37.423544+00:00","updated_at":"2026-07-05T09:41:37.423544+00:00"}