{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2019:MYG2CR3KXJ55OHF7RUVO5CF6VX","short_pith_number":"pith:MYG2CR3K","schema_version":"1.0","canonical_sha256":"660da1476aba7bd71cbf8d2aee88beadef07e6e51658f24d0f094d708f9ae40f","source":{"kind":"arxiv","id":"1906.07912","version":2},"attestation_state":"computed","paper":{"title":"ViP: Virtual Pooling for Accelerating CNN-based Image Classification and Object Detection","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Diana Marculescu, Jiyuan Zhang, Ruizhou Ding, Zhuo Chen","submitted_at":"2019-06-19T04:44:54Z","abstract_excerpt":"In recent years, Convolutional Neural Networks (CNNs) have shown superior capability in visual learning tasks. While accuracy-wise CNNs provide unprecedented performance, they are also known to be computationally intensive and energy demanding for modern computer systems. In this paper, we propose Virtual Pooling (ViP), a model-level approach to improve speed and energy consumption of CNN-based image classification and object detection tasks, with a provable error bound. We show the efficacy of ViP through experiments on four CNN models, three representative datasets, both desktop and mobile p"},"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":"1906.07912","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2019-06-19T04:44:54Z","cross_cats_sorted":[],"title_canon_sha256":"b593616e66e084be6dc513665c6a2e35de170ca24564232bc377ca14b98e3e1c","abstract_canon_sha256":"036a9b3b9da8ec74fee5dc38fc5345a16739e8e623d3f9423df3ff868dae901a"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T00:42:31.534793Z","signature_b64":"m7CPytAvrc8/y0wF+JJ4GRzDVRklonqdQ8UWVvbNlq5W+O+xb7Jo6Ll9HHFKmI4YrdkGnRGoqbRmFqmi9h72DA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"660da1476aba7bd71cbf8d2aee88beadef07e6e51658f24d0f094d708f9ae40f","last_reissued_at":"2026-07-05T00:42:31.534248Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T00:42:31.534248Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"ViP: Virtual Pooling for Accelerating CNN-based Image Classification and Object Detection","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Diana Marculescu, Jiyuan Zhang, Ruizhou Ding, Zhuo Chen","submitted_at":"2019-06-19T04:44:54Z","abstract_excerpt":"In recent years, Convolutional Neural Networks (CNNs) have shown superior capability in visual learning tasks. While accuracy-wise CNNs provide unprecedented performance, they are also known to be computationally intensive and energy demanding for modern computer systems. In this paper, we propose Virtual Pooling (ViP), a model-level approach to improve speed and energy consumption of CNN-based image classification and object detection tasks, with a provable error bound. We show the efficacy of ViP through experiments on four CNN models, three representative datasets, both desktop and mobile p"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1906.07912","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/1906.07912/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":"1906.07912","created_at":"2026-07-05T00:42:31.534307+00:00"},{"alias_kind":"arxiv_version","alias_value":"1906.07912v2","created_at":"2026-07-05T00:42:31.534307+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1906.07912","created_at":"2026-07-05T00:42:31.534307+00:00"},{"alias_kind":"pith_short_12","alias_value":"MYG2CR3KXJ55","created_at":"2026-07-05T00:42:31.534307+00:00"},{"alias_kind":"pith_short_16","alias_value":"MYG2CR3KXJ55OHF7","created_at":"2026-07-05T00:42:31.534307+00:00"},{"alias_kind":"pith_short_8","alias_value":"MYG2CR3K","created_at":"2026-07-05T00:42:31.534307+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2504.13102","citing_title":"A Multi-task Learning Balanced Attention Convolutional Neural Network Model for Few-shot Underwater Acoustic Target Recognition","ref_index":7,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/MYG2CR3KXJ55OHF7RUVO5CF6VX","json":"https://pith.science/pith/MYG2CR3KXJ55OHF7RUVO5CF6VX.json","graph_json":"https://pith.science/api/pith-number/MYG2CR3KXJ55OHF7RUVO5CF6VX/graph.json","events_json":"https://pith.science/api/pith-number/MYG2CR3KXJ55OHF7RUVO5CF6VX/events.json","paper":"https://pith.science/paper/MYG2CR3K"},"agent_actions":{"view_html":"https://pith.science/pith/MYG2CR3KXJ55OHF7RUVO5CF6VX","download_json":"https://pith.science/pith/MYG2CR3KXJ55OHF7RUVO5CF6VX.json","view_paper":"https://pith.science/paper/MYG2CR3K","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1906.07912&json=true","fetch_graph":"https://pith.science/api/pith-number/MYG2CR3KXJ55OHF7RUVO5CF6VX/graph.json","fetch_events":"https://pith.science/api/pith-number/MYG2CR3KXJ55OHF7RUVO5CF6VX/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/MYG2CR3KXJ55OHF7RUVO5CF6VX/action/timestamp_anchor","attest_storage":"https://pith.science/pith/MYG2CR3KXJ55OHF7RUVO5CF6VX/action/storage_attestation","attest_author":"https://pith.science/pith/MYG2CR3KXJ55OHF7RUVO5CF6VX/action/author_attestation","sign_citation":"https://pith.science/pith/MYG2CR3KXJ55OHF7RUVO5CF6VX/action/citation_signature","submit_replication":"https://pith.science/pith/MYG2CR3KXJ55OHF7RUVO5CF6VX/action/replication_record"}},"created_at":"2026-07-05T00:42:31.534307+00:00","updated_at":"2026-07-05T00:42:31.534307+00:00"}