{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2019:M4WSQS44MXSACYI3LSG32EHFVT","short_pith_number":"pith:M4WSQS44","schema_version":"1.0","canonical_sha256":"672d284b9c65e401611b5c8dbd10e5acfe6dd4f3d3c062ace58dc3ab75aa840e","source":{"kind":"arxiv","id":"1904.09730","version":1},"attestation_state":"computed","paper":{"title":"An Energy and GPU-Computation Efficient Backbone Network for Real-Time Object Detection","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Jongyoul Park, Joong-Won Hwang, Sangrok Lee, Youngwan Lee, Yuseok Bae","submitted_at":"2019-04-22T05:45:57Z","abstract_excerpt":"As DenseNet conserves intermediate features with diverse receptive fields by aggregating them with dense connection, it shows good performance on the object detection task. Although feature reuse enables DenseNet to produce strong features with a small number of model parameters and FLOPs, the detector with DenseNet backbone shows rather slow speed and low energy efficiency. We find the linearly increasing input channel by dense connection leads to heavy memory access cost, which causes computation overhead and more energy consumption. To solve the inefficiency of DenseNet, we propose an energ"},"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":"1904.09730","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2019-04-22T05:45:57Z","cross_cats_sorted":[],"title_canon_sha256":"07b9ba5b366465bfef04e4fe156d84845bc8074025e1e45d80d4730074e479fe","abstract_canon_sha256":"7f45611a4c9c1268b6c630f29867cb7bdc96700242af1adb415b3989ada3f898"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:48:03.511863Z","signature_b64":"HD6rqZIuBI/F/y2Cqh2VbqT13VREt2bqxJU2wbPqON6SsRSpXDoQ8Rw2dfLzv3u3gNpZExcXacu/ww1uxgDJAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"672d284b9c65e401611b5c8dbd10e5acfe6dd4f3d3c062ace58dc3ab75aa840e","last_reissued_at":"2026-05-17T23:48:03.511294Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:48:03.511294Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"An Energy and GPU-Computation Efficient Backbone Network for Real-Time Object Detection","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Jongyoul Park, Joong-Won Hwang, Sangrok Lee, Youngwan Lee, Yuseok Bae","submitted_at":"2019-04-22T05:45:57Z","abstract_excerpt":"As DenseNet conserves intermediate features with diverse receptive fields by aggregating them with dense connection, it shows good performance on the object detection task. Although feature reuse enables DenseNet to produce strong features with a small number of model parameters and FLOPs, the detector with DenseNet backbone shows rather slow speed and low energy efficiency. We find the linearly increasing input channel by dense connection leads to heavy memory access cost, which causes computation overhead and more energy consumption. To solve the inefficiency of DenseNet, we propose an energ"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1904.09730","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":"1904.09730","created_at":"2026-05-17T23:48:03.511413+00:00"},{"alias_kind":"arxiv_version","alias_value":"1904.09730v1","created_at":"2026-05-17T23:48:03.511413+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1904.09730","created_at":"2026-05-17T23:48:03.511413+00:00"},{"alias_kind":"pith_short_12","alias_value":"M4WSQS44MXSA","created_at":"2026-05-18T12:33:21.387695+00:00"},{"alias_kind":"pith_short_16","alias_value":"M4WSQS44MXSACYI3","created_at":"2026-05-18T12:33:21.387695+00:00"},{"alias_kind":"pith_short_8","alias_value":"M4WSQS44","created_at":"2026-05-18T12:33:21.387695+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/M4WSQS44MXSACYI3LSG32EHFVT","json":"https://pith.science/pith/M4WSQS44MXSACYI3LSG32EHFVT.json","graph_json":"https://pith.science/api/pith-number/M4WSQS44MXSACYI3LSG32EHFVT/graph.json","events_json":"https://pith.science/api/pith-number/M4WSQS44MXSACYI3LSG32EHFVT/events.json","paper":"https://pith.science/paper/M4WSQS44"},"agent_actions":{"view_html":"https://pith.science/pith/M4WSQS44MXSACYI3LSG32EHFVT","download_json":"https://pith.science/pith/M4WSQS44MXSACYI3LSG32EHFVT.json","view_paper":"https://pith.science/paper/M4WSQS44","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1904.09730&json=true","fetch_graph":"https://pith.science/api/pith-number/M4WSQS44MXSACYI3LSG32EHFVT/graph.json","fetch_events":"https://pith.science/api/pith-number/M4WSQS44MXSACYI3LSG32EHFVT/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/M4WSQS44MXSACYI3LSG32EHFVT/action/timestamp_anchor","attest_storage":"https://pith.science/pith/M4WSQS44MXSACYI3LSG32EHFVT/action/storage_attestation","attest_author":"https://pith.science/pith/M4WSQS44MXSACYI3LSG32EHFVT/action/author_attestation","sign_citation":"https://pith.science/pith/M4WSQS44MXSACYI3LSG32EHFVT/action/citation_signature","submit_replication":"https://pith.science/pith/M4WSQS44MXSACYI3LSG32EHFVT/action/replication_record"}},"created_at":"2026-05-17T23:48:03.511413+00:00","updated_at":"2026-05-17T23:48:03.511413+00:00"}