{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:JM6R7N3JBMDCM2GP2KYJGFUE2U","short_pith_number":"pith:JM6R7N3J","schema_version":"1.0","canonical_sha256":"4b3d1fb7690b062668cfd2b0931684d508fe384ea03594d0d7f6e041c64c4cfc","source":{"kind":"arxiv","id":"2408.01688","version":2},"attestation_state":"computed","paper":{"title":"SiamMo: Siamese Motion-Centric 3D Object Tracking","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Hongjie Gu, Jing Zhang, Yingqi Deng, Yuxiang Yang, Zhekang Dong","submitted_at":"2024-08-03T07:02:01Z","abstract_excerpt":"Current 3D single object tracking methods primarily rely on the Siamese matching-based paradigm, which struggles with textureless and incomplete LiDAR point clouds. Conversely, the motion-centric paradigm avoids appearance matching, thus overcoming these issues. However, its complex multi-stage pipeline and the limited temporal modeling capability of a single-stream architecture constrain its potential. In this paper, we introduce SiamMo, a novel and simple Siamese motion-centric tracking approach. Unlike the traditional single-stream architecture, we employ Siamese feature extraction for moti"},"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":"2408.01688","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-08-03T07:02:01Z","cross_cats_sorted":[],"title_canon_sha256":"744f0b24fd01a4ae8824a39cd6b461d2dbe3a954b64ff249d8f746ed14ea762b","abstract_canon_sha256":"08dba996125b800da0ee5e86809b04296fbc2882dacfccc6ec010977a0a07c2e"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:04:38.578102Z","signature_b64":"pikMK8YQOohVpjz4te0TfDx+nw8ST3XqsHKL335/PysXQVCQKmk1fWjEOB/bFHa0PpQu+RK+8cpdTIsxQ2KTCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"4b3d1fb7690b062668cfd2b0931684d508fe384ea03594d0d7f6e041c64c4cfc","last_reissued_at":"2026-07-05T09:04:38.577720Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:04:38.577720Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"SiamMo: Siamese Motion-Centric 3D Object Tracking","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Hongjie Gu, Jing Zhang, Yingqi Deng, Yuxiang Yang, Zhekang Dong","submitted_at":"2024-08-03T07:02:01Z","abstract_excerpt":"Current 3D single object tracking methods primarily rely on the Siamese matching-based paradigm, which struggles with textureless and incomplete LiDAR point clouds. Conversely, the motion-centric paradigm avoids appearance matching, thus overcoming these issues. However, its complex multi-stage pipeline and the limited temporal modeling capability of a single-stream architecture constrain its potential. In this paper, we introduce SiamMo, a novel and simple Siamese motion-centric tracking approach. Unlike the traditional single-stream architecture, we employ Siamese feature extraction for moti"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2408.01688","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/2408.01688/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":"2408.01688","created_at":"2026-07-05T09:04:38.577777+00:00"},{"alias_kind":"arxiv_version","alias_value":"2408.01688v2","created_at":"2026-07-05T09:04:38.577777+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2408.01688","created_at":"2026-07-05T09:04:38.577777+00:00"},{"alias_kind":"pith_short_12","alias_value":"JM6R7N3JBMDC","created_at":"2026-07-05T09:04:38.577777+00:00"},{"alias_kind":"pith_short_16","alias_value":"JM6R7N3JBMDCM2GP","created_at":"2026-07-05T09:04:38.577777+00:00"},{"alias_kind":"pith_short_8","alias_value":"JM6R7N3J","created_at":"2026-07-05T09:04:38.577777+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2507.19908","citing_title":"TrackAny3D: Transferring Pretrained 3D Models for Category-unified 3D Point Cloud Tracking","ref_index":52,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/JM6R7N3JBMDCM2GP2KYJGFUE2U","json":"https://pith.science/pith/JM6R7N3JBMDCM2GP2KYJGFUE2U.json","graph_json":"https://pith.science/api/pith-number/JM6R7N3JBMDCM2GP2KYJGFUE2U/graph.json","events_json":"https://pith.science/api/pith-number/JM6R7N3JBMDCM2GP2KYJGFUE2U/events.json","paper":"https://pith.science/paper/JM6R7N3J"},"agent_actions":{"view_html":"https://pith.science/pith/JM6R7N3JBMDCM2GP2KYJGFUE2U","download_json":"https://pith.science/pith/JM6R7N3JBMDCM2GP2KYJGFUE2U.json","view_paper":"https://pith.science/paper/JM6R7N3J","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2408.01688&json=true","fetch_graph":"https://pith.science/api/pith-number/JM6R7N3JBMDCM2GP2KYJGFUE2U/graph.json","fetch_events":"https://pith.science/api/pith-number/JM6R7N3JBMDCM2GP2KYJGFUE2U/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/JM6R7N3JBMDCM2GP2KYJGFUE2U/action/timestamp_anchor","attest_storage":"https://pith.science/pith/JM6R7N3JBMDCM2GP2KYJGFUE2U/action/storage_attestation","attest_author":"https://pith.science/pith/JM6R7N3JBMDCM2GP2KYJGFUE2U/action/author_attestation","sign_citation":"https://pith.science/pith/JM6R7N3JBMDCM2GP2KYJGFUE2U/action/citation_signature","submit_replication":"https://pith.science/pith/JM6R7N3JBMDCM2GP2KYJGFUE2U/action/replication_record"}},"created_at":"2026-07-05T09:04:38.577777+00:00","updated_at":"2026-07-05T09:04:38.577777+00:00"}