{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2015:ZCXMRLKDXUPLZO5RDBMFYCJPTP","short_pith_number":"pith:ZCXMRLKD","schema_version":"1.0","canonical_sha256":"c8aec8ad43bd1ebcbbb118585c092f9be152f31be10a2855c135e4abb7d85794","source":{"kind":"arxiv","id":"1504.04792","version":2},"attestation_state":"computed","paper":{"title":"Visual Recognition Using Directional Distribution Distance","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Bin-Bin Gao, Guoqing Liu, Jianxin Wu","submitted_at":"2015-04-19T04:55:59Z","abstract_excerpt":"In computer vision, an entity such as an image or video is often represented as a set of instance vectors, which can be SIFT, motion, or deep learning feature vectors extracted from different parts of that entity. Thus, it is essential to design efficient and effective methods to compare two sets of instance vectors. Existing methods such as FV, VLAD or Super Vectors have achieved excellent results. However, this paper shows that these methods are designed based on a generative perspective, and a discriminative method can be more effective in categorizing images or videos. The proposed D3 (dis"},"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":"1504.04792","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2015-04-19T04:55:59Z","cross_cats_sorted":[],"title_canon_sha256":"c96a87aa8b8f7674edd9711ec00cc46a5c7d602167b731c04d711d438be5c4d4","abstract_canon_sha256":"e14c433d2b26ed5c1dd894e4149d511616995e6564912c3d92e7a727725fbedc"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T01:16:09.843408Z","signature_b64":"SxdbTALHWagSzzYs+5Wo0TnRlwslaDVTX9WQ8sNahwNdFePyVe7bUDQpC+5q4jblYzHkEujFPY/NecIqTD12AQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"c8aec8ad43bd1ebcbbb118585c092f9be152f31be10a2855c135e4abb7d85794","last_reissued_at":"2026-05-18T01:16:09.842784Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T01:16:09.842784Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Visual Recognition Using Directional Distribution Distance","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Bin-Bin Gao, Guoqing Liu, Jianxin Wu","submitted_at":"2015-04-19T04:55:59Z","abstract_excerpt":"In computer vision, an entity such as an image or video is often represented as a set of instance vectors, which can be SIFT, motion, or deep learning feature vectors extracted from different parts of that entity. Thus, it is essential to design efficient and effective methods to compare two sets of instance vectors. Existing methods such as FV, VLAD or Super Vectors have achieved excellent results. However, this paper shows that these methods are designed based on a generative perspective, and a discriminative method can be more effective in categorizing images or videos. The proposed D3 (dis"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1504.04792","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":""},"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":"1504.04792","created_at":"2026-05-18T01:16:09.842862+00:00"},{"alias_kind":"arxiv_version","alias_value":"1504.04792v2","created_at":"2026-05-18T01:16:09.842862+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1504.04792","created_at":"2026-05-18T01:16:09.842862+00:00"},{"alias_kind":"pith_short_12","alias_value":"ZCXMRLKDXUPL","created_at":"2026-05-18T12:29:52.810259+00:00"},{"alias_kind":"pith_short_16","alias_value":"ZCXMRLKDXUPLZO5R","created_at":"2026-05-18T12:29:52.810259+00:00"},{"alias_kind":"pith_short_8","alias_value":"ZCXMRLKD","created_at":"2026-05-18T12:29:52.810259+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/ZCXMRLKDXUPLZO5RDBMFYCJPTP","json":"https://pith.science/pith/ZCXMRLKDXUPLZO5RDBMFYCJPTP.json","graph_json":"https://pith.science/api/pith-number/ZCXMRLKDXUPLZO5RDBMFYCJPTP/graph.json","events_json":"https://pith.science/api/pith-number/ZCXMRLKDXUPLZO5RDBMFYCJPTP/events.json","paper":"https://pith.science/paper/ZCXMRLKD"},"agent_actions":{"view_html":"https://pith.science/pith/ZCXMRLKDXUPLZO5RDBMFYCJPTP","download_json":"https://pith.science/pith/ZCXMRLKDXUPLZO5RDBMFYCJPTP.json","view_paper":"https://pith.science/paper/ZCXMRLKD","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1504.04792&json=true","fetch_graph":"https://pith.science/api/pith-number/ZCXMRLKDXUPLZO5RDBMFYCJPTP/graph.json","fetch_events":"https://pith.science/api/pith-number/ZCXMRLKDXUPLZO5RDBMFYCJPTP/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/ZCXMRLKDXUPLZO5RDBMFYCJPTP/action/timestamp_anchor","attest_storage":"https://pith.science/pith/ZCXMRLKDXUPLZO5RDBMFYCJPTP/action/storage_attestation","attest_author":"https://pith.science/pith/ZCXMRLKDXUPLZO5RDBMFYCJPTP/action/author_attestation","sign_citation":"https://pith.science/pith/ZCXMRLKDXUPLZO5RDBMFYCJPTP/action/citation_signature","submit_replication":"https://pith.science/pith/ZCXMRLKDXUPLZO5RDBMFYCJPTP/action/replication_record"}},"created_at":"2026-05-18T01:16:09.842862+00:00","updated_at":"2026-05-18T01:16:09.842862+00:00"}