{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:54DPLFVTL76JUARB2EPXFMIMKS","short_pith_number":"pith:54DPLFVT","schema_version":"1.0","canonical_sha256":"ef06f596b35ffc9a0221d11f72b10c54a1ffaa1890297adb7d461a49160962d9","source":{"kind":"arxiv","id":"2403.05231","version":2},"attestation_state":"computed","paper":{"title":"Tracking Meets LoRA: Faster Training, Larger Model, Stronger Performance","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Haibin Ling, Heng Fan, Liting Lin, Yaowei Wang, Yong Xu, Zhipeng Zhang","submitted_at":"2024-03-08T11:41:48Z","abstract_excerpt":"Motivated by the Parameter-Efficient Fine-Tuning (PEFT) in large language models, we propose LoRAT, a method that unveils the power of large ViT model for tracking within laboratory-level resources. The essence of our work lies in adapting LoRA, a technique that fine-tunes a small subset of model parameters without adding inference latency, to the domain of visual tracking. However, unique challenges and potential domain gaps make this transfer not as easy as the first intuition. Firstly, a transformer-based tracker constructs unshared position embedding for template and search image. This pos"},"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":"2403.05231","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-03-08T11:41:48Z","cross_cats_sorted":[],"title_canon_sha256":"6d8a533dbff739bb925aac9fe4bbd49a9613697d004bbe89bdd587ef387abbf2","abstract_canon_sha256":"fd89b9213856ac41db8985fe7cf901cf65b0d39e4066edb40a9d06c302feb11d"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:48:41.813540Z","signature_b64":"UCYm1s8xRaiME6yWIP4+qIqg+oQmL3+lk1Ax1ilVmAGqqvOEOP4XhhuQkIKR/Mhx3DiMHnypkdZxildGdcs5CA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"ef06f596b35ffc9a0221d11f72b10c54a1ffaa1890297adb7d461a49160962d9","last_reissued_at":"2026-07-05T08:48:41.813080Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:48:41.813080Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Tracking Meets LoRA: Faster Training, Larger Model, Stronger Performance","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Haibin Ling, Heng Fan, Liting Lin, Yaowei Wang, Yong Xu, Zhipeng Zhang","submitted_at":"2024-03-08T11:41:48Z","abstract_excerpt":"Motivated by the Parameter-Efficient Fine-Tuning (PEFT) in large language models, we propose LoRAT, a method that unveils the power of large ViT model for tracking within laboratory-level resources. The essence of our work lies in adapting LoRA, a technique that fine-tunes a small subset of model parameters without adding inference latency, to the domain of visual tracking. However, unique challenges and potential domain gaps make this transfer not as easy as the first intuition. Firstly, a transformer-based tracker constructs unshared position embedding for template and search image. This pos"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2403.05231","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/2403.05231/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":"2403.05231","created_at":"2026-07-05T08:48:41.813135+00:00"},{"alias_kind":"arxiv_version","alias_value":"2403.05231v2","created_at":"2026-07-05T08:48:41.813135+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2403.05231","created_at":"2026-07-05T08:48:41.813135+00:00"},{"alias_kind":"pith_short_12","alias_value":"54DPLFVTL76J","created_at":"2026-07-05T08:48:41.813135+00:00"},{"alias_kind":"pith_short_16","alias_value":"54DPLFVTL76JUARB","created_at":"2026-07-05T08:48:41.813135+00:00"},{"alias_kind":"pith_short_8","alias_value":"54DPLFVT","created_at":"2026-07-05T08:48:41.813135+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/54DPLFVTL76JUARB2EPXFMIMKS","json":"https://pith.science/pith/54DPLFVTL76JUARB2EPXFMIMKS.json","graph_json":"https://pith.science/api/pith-number/54DPLFVTL76JUARB2EPXFMIMKS/graph.json","events_json":"https://pith.science/api/pith-number/54DPLFVTL76JUARB2EPXFMIMKS/events.json","paper":"https://pith.science/paper/54DPLFVT"},"agent_actions":{"view_html":"https://pith.science/pith/54DPLFVTL76JUARB2EPXFMIMKS","download_json":"https://pith.science/pith/54DPLFVTL76JUARB2EPXFMIMKS.json","view_paper":"https://pith.science/paper/54DPLFVT","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2403.05231&json=true","fetch_graph":"https://pith.science/api/pith-number/54DPLFVTL76JUARB2EPXFMIMKS/graph.json","fetch_events":"https://pith.science/api/pith-number/54DPLFVTL76JUARB2EPXFMIMKS/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/54DPLFVTL76JUARB2EPXFMIMKS/action/timestamp_anchor","attest_storage":"https://pith.science/pith/54DPLFVTL76JUARB2EPXFMIMKS/action/storage_attestation","attest_author":"https://pith.science/pith/54DPLFVTL76JUARB2EPXFMIMKS/action/author_attestation","sign_citation":"https://pith.science/pith/54DPLFVTL76JUARB2EPXFMIMKS/action/citation_signature","submit_replication":"https://pith.science/pith/54DPLFVTL76JUARB2EPXFMIMKS/action/replication_record"}},"created_at":"2026-07-05T08:48:41.813135+00:00","updated_at":"2026-07-05T08:48:41.813135+00:00"}