{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2018:EH3BWHLBVAWXQRTQXXP3NGAH3G","short_pith_number":"pith:EH3BWHLB","schema_version":"1.0","canonical_sha256":"21f61b1d61a82d784670bddfb69807d9a2a0a1e2781a674ae59b94787b732308","source":{"kind":"arxiv","id":"1808.06698","version":1},"attestation_state":"computed","paper":{"title":"VERAM: View-Enhanced Recurrent Attention Model for 3D Shape Classification","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.GR"],"primary_cat":"cs.CV","authors_text":"Kai Xu, Lintao Zheng, Songle Chen, Yan Zhang, ZhiXin Sun","submitted_at":"2018-08-20T21:08:02Z","abstract_excerpt":"Multi-view deep neural network is perhaps the most successful approach in 3D shape classification. However, the fusion of multi-view features based on max or average pooling lacks a view selection mechanism, limiting its application in, e.g., multi-view active object recognition by a robot. This paper presents VERAM, a recurrent attention model capable of actively selecting a sequence of views for highly accurate 3D shape classification. VERAM addresses an important issue commonly found in existing attention-based models, i.e., the unbalanced training of the subnetworks corresponding to next v"},"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":"1808.06698","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2018-08-20T21:08:02Z","cross_cats_sorted":["cs.GR"],"title_canon_sha256":"21f5ccbd28a47d0f538f55e9b93ce8cce28b533caaf233245062499a52b36576","abstract_canon_sha256":"fdff6dc41cd03738bad5e44458438ac021296fd90cef87c5dace717f19626da7"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:07:39.352908Z","signature_b64":"esDn8ML9RK8VguUv49L/o536OQRYioPuCsk4xVLN8eWKEodKhIA3vyVszgb2lgeO1314lTxQ4ee6KCDKR12wAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"21f61b1d61a82d784670bddfb69807d9a2a0a1e2781a674ae59b94787b732308","last_reissued_at":"2026-05-18T00:07:39.352188Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:07:39.352188Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"VERAM: View-Enhanced Recurrent Attention Model for 3D Shape Classification","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.GR"],"primary_cat":"cs.CV","authors_text":"Kai Xu, Lintao Zheng, Songle Chen, Yan Zhang, ZhiXin Sun","submitted_at":"2018-08-20T21:08:02Z","abstract_excerpt":"Multi-view deep neural network is perhaps the most successful approach in 3D shape classification. However, the fusion of multi-view features based on max or average pooling lacks a view selection mechanism, limiting its application in, e.g., multi-view active object recognition by a robot. This paper presents VERAM, a recurrent attention model capable of actively selecting a sequence of views for highly accurate 3D shape classification. VERAM addresses an important issue commonly found in existing attention-based models, i.e., the unbalanced training of the subnetworks corresponding to next v"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1808.06698","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":""},"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":"1808.06698","created_at":"2026-05-18T00:07:39.352292+00:00"},{"alias_kind":"arxiv_version","alias_value":"1808.06698v1","created_at":"2026-05-18T00:07:39.352292+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1808.06698","created_at":"2026-05-18T00:07:39.352292+00:00"},{"alias_kind":"pith_short_12","alias_value":"EH3BWHLBVAWX","created_at":"2026-05-18T12:32:22.470017+00:00"},{"alias_kind":"pith_short_16","alias_value":"EH3BWHLBVAWXQRTQ","created_at":"2026-05-18T12:32:22.470017+00:00"},{"alias_kind":"pith_short_8","alias_value":"EH3BWHLB","created_at":"2026-05-18T12:32:22.470017+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/EH3BWHLBVAWXQRTQXXP3NGAH3G","json":"https://pith.science/pith/EH3BWHLBVAWXQRTQXXP3NGAH3G.json","graph_json":"https://pith.science/api/pith-number/EH3BWHLBVAWXQRTQXXP3NGAH3G/graph.json","events_json":"https://pith.science/api/pith-number/EH3BWHLBVAWXQRTQXXP3NGAH3G/events.json","paper":"https://pith.science/paper/EH3BWHLB"},"agent_actions":{"view_html":"https://pith.science/pith/EH3BWHLBVAWXQRTQXXP3NGAH3G","download_json":"https://pith.science/pith/EH3BWHLBVAWXQRTQXXP3NGAH3G.json","view_paper":"https://pith.science/paper/EH3BWHLB","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1808.06698&json=true","fetch_graph":"https://pith.science/api/pith-number/EH3BWHLBVAWXQRTQXXP3NGAH3G/graph.json","fetch_events":"https://pith.science/api/pith-number/EH3BWHLBVAWXQRTQXXP3NGAH3G/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/EH3BWHLBVAWXQRTQXXP3NGAH3G/action/timestamp_anchor","attest_storage":"https://pith.science/pith/EH3BWHLBVAWXQRTQXXP3NGAH3G/action/storage_attestation","attest_author":"https://pith.science/pith/EH3BWHLBVAWXQRTQXXP3NGAH3G/action/author_attestation","sign_citation":"https://pith.science/pith/EH3BWHLBVAWXQRTQXXP3NGAH3G/action/citation_signature","submit_replication":"https://pith.science/pith/EH3BWHLBVAWXQRTQXXP3NGAH3G/action/replication_record"}},"created_at":"2026-05-18T00:07:39.352292+00:00","updated_at":"2026-05-18T00:07:39.352292+00:00"}