{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2019:GMLX7CKJLHG7C7GSLVPEGHMMRY","short_pith_number":"pith:GMLX7CKJ","schema_version":"1.0","canonical_sha256":"33177f894959cdf17cd25d5e431d8c8e169fc2f9aace5722bdeb09fa6ff10790","source":{"kind":"arxiv","id":"1909.07074","version":1},"attestation_state":"computed","paper":{"title":"Temporally Consistent Depth Prediction with Flow-Guided Memory Units","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Bumsub Ham, Chanho Eom, Hyunjong Park","submitted_at":"2019-09-16T09:10:10Z","abstract_excerpt":"Predicting depth from a monocular video sequence is an important task for autonomous driving. Although it has advanced considerably in the past few years, recent methods based on convolutional neural networks (CNNs) discard temporal coherence in the video sequence and estimate depth independently for each frame, which often leads to undesired inconsistent results over time. To address this problem, we propose to memorize temporal consistency in the video sequence, and leverage it for the task of depth prediction. To this end, we introduce a two-stream CNN with a flow-guided memory module, wher"},"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":"1909.07074","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2019-09-16T09:10:10Z","cross_cats_sorted":[],"title_canon_sha256":"2d230b5b45f4b458007807165a54611626b78323df934ec4289499c48206c6ef","abstract_canon_sha256":"ab639b9faef26293de5a200697c7ad556ee535753e94c0615049b2c9f8c5be7d"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T00:04:53.008142Z","signature_b64":"k7NR7nwdKp0rcld06gcM6/kClaXTSCoWC8SjLtdFrciVAfieAHq5kC3wLFzfyPbcBA8ox42EiZa+hsZyg0QfDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"33177f894959cdf17cd25d5e431d8c8e169fc2f9aace5722bdeb09fa6ff10790","last_reissued_at":"2026-07-05T00:04:53.007785Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T00:04:53.007785Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Temporally Consistent Depth Prediction with Flow-Guided Memory Units","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Bumsub Ham, Chanho Eom, Hyunjong Park","submitted_at":"2019-09-16T09:10:10Z","abstract_excerpt":"Predicting depth from a monocular video sequence is an important task for autonomous driving. Although it has advanced considerably in the past few years, recent methods based on convolutional neural networks (CNNs) discard temporal coherence in the video sequence and estimate depth independently for each frame, which often leads to undesired inconsistent results over time. To address this problem, we propose to memorize temporal consistency in the video sequence, and leverage it for the task of depth prediction. To this end, we introduce a two-stream CNN with a flow-guided memory module, wher"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1909.07074","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":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/1909.07074/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":"1909.07074","created_at":"2026-07-05T00:04:53.007851+00:00"},{"alias_kind":"arxiv_version","alias_value":"1909.07074v1","created_at":"2026-07-05T00:04:53.007851+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1909.07074","created_at":"2026-07-05T00:04:53.007851+00:00"},{"alias_kind":"pith_short_12","alias_value":"GMLX7CKJLHG7","created_at":"2026-07-05T00:04:53.007851+00:00"},{"alias_kind":"pith_short_16","alias_value":"GMLX7CKJLHG7C7GS","created_at":"2026-07-05T00:04:53.007851+00:00"},{"alias_kind":"pith_short_8","alias_value":"GMLX7CKJ","created_at":"2026-07-05T00:04:53.007851+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/GMLX7CKJLHG7C7GSLVPEGHMMRY","json":"https://pith.science/pith/GMLX7CKJLHG7C7GSLVPEGHMMRY.json","graph_json":"https://pith.science/api/pith-number/GMLX7CKJLHG7C7GSLVPEGHMMRY/graph.json","events_json":"https://pith.science/api/pith-number/GMLX7CKJLHG7C7GSLVPEGHMMRY/events.json","paper":"https://pith.science/paper/GMLX7CKJ"},"agent_actions":{"view_html":"https://pith.science/pith/GMLX7CKJLHG7C7GSLVPEGHMMRY","download_json":"https://pith.science/pith/GMLX7CKJLHG7C7GSLVPEGHMMRY.json","view_paper":"https://pith.science/paper/GMLX7CKJ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1909.07074&json=true","fetch_graph":"https://pith.science/api/pith-number/GMLX7CKJLHG7C7GSLVPEGHMMRY/graph.json","fetch_events":"https://pith.science/api/pith-number/GMLX7CKJLHG7C7GSLVPEGHMMRY/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/GMLX7CKJLHG7C7GSLVPEGHMMRY/action/timestamp_anchor","attest_storage":"https://pith.science/pith/GMLX7CKJLHG7C7GSLVPEGHMMRY/action/storage_attestation","attest_author":"https://pith.science/pith/GMLX7CKJLHG7C7GSLVPEGHMMRY/action/author_attestation","sign_citation":"https://pith.science/pith/GMLX7CKJLHG7C7GSLVPEGHMMRY/action/citation_signature","submit_replication":"https://pith.science/pith/GMLX7CKJLHG7C7GSLVPEGHMMRY/action/replication_record"}},"created_at":"2026-07-05T00:04:53.007851+00:00","updated_at":"2026-07-05T00:04:53.007851+00:00"}