{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:XYO5WM2WBMSTOMD7KXE3G4LLBU","short_pith_number":"pith:XYO5WM2W","schema_version":"1.0","canonical_sha256":"be1ddb33560b2537307f55c9b3716b0d0a2ded0c156d5e3cab8eb15ff5e337e0","source":{"kind":"arxiv","id":"2111.13386","version":1},"attestation_state":"computed","paper":{"title":"POEM: 1-bit Point-wise Operations based on Expectation-Maximization for Efficient Point Cloud Processing","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Baochang Zhang, Guodong Guo, Junhe Zhao, Sheng Xu, Yanjing Li","submitted_at":"2021-11-26T09:45:01Z","abstract_excerpt":"Real-time point cloud processing is fundamental for lots of computer vision tasks, while still challenged by the computational problem on resource-limited edge devices. To address this issue, we implement XNOR-Net-based binary neural networks (BNNs) for an efficient point cloud processing, but its performance is severely suffered due to two main drawbacks, Gaussian-distributed weights and non-learnable scale factor. In this paper, we introduce point-wise operations based on Expectation-Maximization (POEM) into BNNs for efficient point cloud processing. The EM algorithm can efficiently constrai"},"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":"2111.13386","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2021-11-26T09:45:01Z","cross_cats_sorted":[],"title_canon_sha256":"4f30643547c8d60e4c38ef3d40479cca60423f507a7a05eafdb769a7c3ad31ac","abstract_canon_sha256":"54653bf0f2e54e55f9112f38153a96d274c974266c8e161aebba325418d36de5"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T03:35:20.839951Z","signature_b64":"AF6evLWE99dGL//ts9LIBVrscFyJiRXBnfebWMb0A+VvKRGOpwTEw2kQ9sFjQZefg0hOjQESRfUL+PkHUsj/Aw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"be1ddb33560b2537307f55c9b3716b0d0a2ded0c156d5e3cab8eb15ff5e337e0","last_reissued_at":"2026-07-05T03:35:20.839492Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T03:35:20.839492Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"POEM: 1-bit Point-wise Operations based on Expectation-Maximization for Efficient Point Cloud Processing","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Baochang Zhang, Guodong Guo, Junhe Zhao, Sheng Xu, Yanjing Li","submitted_at":"2021-11-26T09:45:01Z","abstract_excerpt":"Real-time point cloud processing is fundamental for lots of computer vision tasks, while still challenged by the computational problem on resource-limited edge devices. To address this issue, we implement XNOR-Net-based binary neural networks (BNNs) for an efficient point cloud processing, but its performance is severely suffered due to two main drawbacks, Gaussian-distributed weights and non-learnable scale factor. In this paper, we introduce point-wise operations based on Expectation-Maximization (POEM) into BNNs for efficient point cloud processing. The EM algorithm can efficiently constrai"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2111.13386","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/2111.13386/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":"2111.13386","created_at":"2026-07-05T03:35:20.839550+00:00"},{"alias_kind":"arxiv_version","alias_value":"2111.13386v1","created_at":"2026-07-05T03:35:20.839550+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2111.13386","created_at":"2026-07-05T03:35:20.839550+00:00"},{"alias_kind":"pith_short_12","alias_value":"XYO5WM2WBMST","created_at":"2026-07-05T03:35:20.839550+00:00"},{"alias_kind":"pith_short_16","alias_value":"XYO5WM2WBMSTOMD7","created_at":"2026-07-05T03:35:20.839550+00:00"},{"alias_kind":"pith_short_8","alias_value":"XYO5WM2W","created_at":"2026-07-05T03:35:20.839550+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2507.04456","citing_title":"BiVM: Accurate Binarized Neural Network for Efficient Video Matting","ref_index":96,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/XYO5WM2WBMSTOMD7KXE3G4LLBU","json":"https://pith.science/pith/XYO5WM2WBMSTOMD7KXE3G4LLBU.json","graph_json":"https://pith.science/api/pith-number/XYO5WM2WBMSTOMD7KXE3G4LLBU/graph.json","events_json":"https://pith.science/api/pith-number/XYO5WM2WBMSTOMD7KXE3G4LLBU/events.json","paper":"https://pith.science/paper/XYO5WM2W"},"agent_actions":{"view_html":"https://pith.science/pith/XYO5WM2WBMSTOMD7KXE3G4LLBU","download_json":"https://pith.science/pith/XYO5WM2WBMSTOMD7KXE3G4LLBU.json","view_paper":"https://pith.science/paper/XYO5WM2W","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2111.13386&json=true","fetch_graph":"https://pith.science/api/pith-number/XYO5WM2WBMSTOMD7KXE3G4LLBU/graph.json","fetch_events":"https://pith.science/api/pith-number/XYO5WM2WBMSTOMD7KXE3G4LLBU/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/XYO5WM2WBMSTOMD7KXE3G4LLBU/action/timestamp_anchor","attest_storage":"https://pith.science/pith/XYO5WM2WBMSTOMD7KXE3G4LLBU/action/storage_attestation","attest_author":"https://pith.science/pith/XYO5WM2WBMSTOMD7KXE3G4LLBU/action/author_attestation","sign_citation":"https://pith.science/pith/XYO5WM2WBMSTOMD7KXE3G4LLBU/action/citation_signature","submit_replication":"https://pith.science/pith/XYO5WM2WBMSTOMD7KXE3G4LLBU/action/replication_record"}},"created_at":"2026-07-05T03:35:20.839550+00:00","updated_at":"2026-07-05T03:35:20.839550+00:00"}