{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2019:UXYXU3ZLIN5SXZ3XIGAD2AUWTC","short_pith_number":"pith:UXYXU3ZL","schema_version":"1.0","canonical_sha256":"a5f17a6f2b437b2be77741803d029698b45abb15da4e38987bd83f5b79029d9a","source":{"kind":"arxiv","id":"1903.01864","version":2},"attestation_state":"computed","paper":{"title":"Frustum ConvNet: Sliding Frustums to Aggregate Local Point-Wise Features for Amodal 3D Object Detection","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Kui Jia, Zhixin Wang","submitted_at":"2019-03-05T14:46:58Z","abstract_excerpt":"In this work, we propose a novel method termed \\emph{Frustum ConvNet (F-ConvNet)} for amodal 3D object detection from point clouds. Given 2D region proposals in an RGB image, our method first generates a sequence of frustums for each region proposal, and uses the obtained frustums to group local points. F-ConvNet aggregates point-wise features as frustum-level feature vectors, and arrays these feature vectors as a feature map for use of its subsequent component of fully convolutional network (FCN), which spatially fuses frustum-level features and supports an end-to-end and continuous estimatio"},"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":"1903.01864","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2019-03-05T14:46:58Z","cross_cats_sorted":[],"title_canon_sha256":"70cc0cb85b132dbfa00274f755c8bfd716e3a7694d1bc1987afa9372b61c714f","abstract_canon_sha256":"c67d1033cf4f14b6a381c0c2691b11d0140071346e15c3d5f5d9b3f4eff08fcc"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-04T23:56:35.595701Z","signature_b64":"UPh/Dfo9ZoG5G4jyc9gFIRQ9OBYxWBAtiOdVAo/GMjeiMRWQBhTtAFN1O1k/QUQaEKQSQbhsY9TijsdvJ4hvBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"a5f17a6f2b437b2be77741803d029698b45abb15da4e38987bd83f5b79029d9a","last_reissued_at":"2026-07-04T23:56:35.595212Z","signature_status":"signed_v1","first_computed_at":"2026-07-04T23:56:35.595212Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Frustum ConvNet: Sliding Frustums to Aggregate Local Point-Wise Features for Amodal 3D Object Detection","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Kui Jia, Zhixin Wang","submitted_at":"2019-03-05T14:46:58Z","abstract_excerpt":"In this work, we propose a novel method termed \\emph{Frustum ConvNet (F-ConvNet)} for amodal 3D object detection from point clouds. Given 2D region proposals in an RGB image, our method first generates a sequence of frustums for each region proposal, and uses the obtained frustums to group local points. F-ConvNet aggregates point-wise features as frustum-level feature vectors, and arrays these feature vectors as a feature map for use of its subsequent component of fully convolutional network (FCN), which spatially fuses frustum-level features and supports an end-to-end and continuous estimatio"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1903.01864","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/1903.01864/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":"1903.01864","created_at":"2026-07-04T23:56:35.595265+00:00"},{"alias_kind":"arxiv_version","alias_value":"1903.01864v2","created_at":"2026-07-04T23:56:35.595265+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1903.01864","created_at":"2026-07-04T23:56:35.595265+00:00"},{"alias_kind":"pith_short_12","alias_value":"UXYXU3ZLIN5S","created_at":"2026-07-04T23:56:35.595265+00:00"},{"alias_kind":"pith_short_16","alias_value":"UXYXU3ZLIN5SXZ3X","created_at":"2026-07-04T23:56:35.595265+00:00"},{"alias_kind":"pith_short_8","alias_value":"UXYXU3ZL","created_at":"2026-07-04T23:56:35.595265+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2412.08096","citing_title":"THUD++: Large-Scale Dynamic Indoor Scene Dataset and Benchmark for Mobile Robots","ref_index":39,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/UXYXU3ZLIN5SXZ3XIGAD2AUWTC","json":"https://pith.science/pith/UXYXU3ZLIN5SXZ3XIGAD2AUWTC.json","graph_json":"https://pith.science/api/pith-number/UXYXU3ZLIN5SXZ3XIGAD2AUWTC/graph.json","events_json":"https://pith.science/api/pith-number/UXYXU3ZLIN5SXZ3XIGAD2AUWTC/events.json","paper":"https://pith.science/paper/UXYXU3ZL"},"agent_actions":{"view_html":"https://pith.science/pith/UXYXU3ZLIN5SXZ3XIGAD2AUWTC","download_json":"https://pith.science/pith/UXYXU3ZLIN5SXZ3XIGAD2AUWTC.json","view_paper":"https://pith.science/paper/UXYXU3ZL","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1903.01864&json=true","fetch_graph":"https://pith.science/api/pith-number/UXYXU3ZLIN5SXZ3XIGAD2AUWTC/graph.json","fetch_events":"https://pith.science/api/pith-number/UXYXU3ZLIN5SXZ3XIGAD2AUWTC/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/UXYXU3ZLIN5SXZ3XIGAD2AUWTC/action/timestamp_anchor","attest_storage":"https://pith.science/pith/UXYXU3ZLIN5SXZ3XIGAD2AUWTC/action/storage_attestation","attest_author":"https://pith.science/pith/UXYXU3ZLIN5SXZ3XIGAD2AUWTC/action/author_attestation","sign_citation":"https://pith.science/pith/UXYXU3ZLIN5SXZ3XIGAD2AUWTC/action/citation_signature","submit_replication":"https://pith.science/pith/UXYXU3ZLIN5SXZ3XIGAD2AUWTC/action/replication_record"}},"created_at":"2026-07-04T23:56:35.595265+00:00","updated_at":"2026-07-04T23:56:35.595265+00:00"}