{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2019:HJIBEKPTGTRFZ5M3CA4NLKJGYV","short_pith_number":"pith:HJIBEKPT","schema_version":"1.0","canonical_sha256":"3a501229f334e25cf59b1038d5a926c571094a48545eb8805682d9b862a11f46","source":{"kind":"arxiv","id":"1904.05673","version":1},"attestation_state":"computed","paper":{"title":"YUVMultiNet: Real-time YUV multi-task CNN for autonomous driving","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CV","authors_text":"Mani Kumar Surisetti, Pullarao Maddu, Said El-Hachimi, Saranya Kandan, Thomas Boulay","submitted_at":"2019-04-11T13:08:05Z","abstract_excerpt":"In this paper, we propose a multi-task convolutional neural network (CNN) architecture optimized for a low power automotive grade SoC. We introduce a network based on a unified architecture where the encoder is shared among the two tasks namely detection and segmentation. The pro-posed network runs at 25FPS for 1280x800 resolution. We briefly discuss the methods used to optimize the network architecture such as using native YUV image directly, optimization of layers & feature maps and applying quantization. We also focus on memory bandwidth in our design as convolutions are data intensives and"},"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":"1904.05673","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2019-04-11T13:08:05Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"e0c68d18106ee9ec2e5c9f659c5dcdc278a1c743d72fc7e96c66560918dd9e9f","abstract_canon_sha256":"41090310767dd7f4000a1f06e10414ea20fca419ea5880fd6fc1425c216bb418"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:48:48.774580Z","signature_b64":"iHH+K0EXSZTnXLijdDtd3o8hlTuKD68EesHhnBJIO9SaKys0PWzqZl+eh48FkSAyQlz5TwljU4Sw0I/WMZUmCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"3a501229f334e25cf59b1038d5a926c571094a48545eb8805682d9b862a11f46","last_reissued_at":"2026-05-17T23:48:48.774140Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:48:48.774140Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"YUVMultiNet: Real-time YUV multi-task CNN for autonomous driving","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CV","authors_text":"Mani Kumar Surisetti, Pullarao Maddu, Said El-Hachimi, Saranya Kandan, Thomas Boulay","submitted_at":"2019-04-11T13:08:05Z","abstract_excerpt":"In this paper, we propose a multi-task convolutional neural network (CNN) architecture optimized for a low power automotive grade SoC. We introduce a network based on a unified architecture where the encoder is shared among the two tasks namely detection and segmentation. The pro-posed network runs at 25FPS for 1280x800 resolution. We briefly discuss the methods used to optimize the network architecture such as using native YUV image directly, optimization of layers & feature maps and applying quantization. We also focus on memory bandwidth in our design as convolutions are data intensives and"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1904.05673","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":"1904.05673","created_at":"2026-05-17T23:48:48.774201+00:00"},{"alias_kind":"arxiv_version","alias_value":"1904.05673v1","created_at":"2026-05-17T23:48:48.774201+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1904.05673","created_at":"2026-05-17T23:48:48.774201+00:00"},{"alias_kind":"pith_short_12","alias_value":"HJIBEKPTGTRF","created_at":"2026-05-18T12:33:18.533446+00:00"},{"alias_kind":"pith_short_16","alias_value":"HJIBEKPTGTRFZ5M3","created_at":"2026-05-18T12:33:18.533446+00:00"},{"alias_kind":"pith_short_8","alias_value":"HJIBEKPT","created_at":"2026-05-18T12:33:18.533446+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/HJIBEKPTGTRFZ5M3CA4NLKJGYV","json":"https://pith.science/pith/HJIBEKPTGTRFZ5M3CA4NLKJGYV.json","graph_json":"https://pith.science/api/pith-number/HJIBEKPTGTRFZ5M3CA4NLKJGYV/graph.json","events_json":"https://pith.science/api/pith-number/HJIBEKPTGTRFZ5M3CA4NLKJGYV/events.json","paper":"https://pith.science/paper/HJIBEKPT"},"agent_actions":{"view_html":"https://pith.science/pith/HJIBEKPTGTRFZ5M3CA4NLKJGYV","download_json":"https://pith.science/pith/HJIBEKPTGTRFZ5M3CA4NLKJGYV.json","view_paper":"https://pith.science/paper/HJIBEKPT","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1904.05673&json=true","fetch_graph":"https://pith.science/api/pith-number/HJIBEKPTGTRFZ5M3CA4NLKJGYV/graph.json","fetch_events":"https://pith.science/api/pith-number/HJIBEKPTGTRFZ5M3CA4NLKJGYV/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/HJIBEKPTGTRFZ5M3CA4NLKJGYV/action/timestamp_anchor","attest_storage":"https://pith.science/pith/HJIBEKPTGTRFZ5M3CA4NLKJGYV/action/storage_attestation","attest_author":"https://pith.science/pith/HJIBEKPTGTRFZ5M3CA4NLKJGYV/action/author_attestation","sign_citation":"https://pith.science/pith/HJIBEKPTGTRFZ5M3CA4NLKJGYV/action/citation_signature","submit_replication":"https://pith.science/pith/HJIBEKPTGTRFZ5M3CA4NLKJGYV/action/replication_record"}},"created_at":"2026-05-17T23:48:48.774201+00:00","updated_at":"2026-05-17T23:48:48.774201+00:00"}