{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2016:JCGJS6TTO7ZSP345QRF3QT4XX3","short_pith_number":"pith:JCGJS6TT","schema_version":"1.0","canonical_sha256":"488c997a7377f327ef9d844bb84f97bedfb11f6ec1aa7985118915fc286115cd","source":{"kind":"arxiv","id":"1612.02699","version":3},"attestation_state":"computed","paper":{"title":"Deep Supervision with Shape Concepts for Occlusion-Aware 3D Object Parsing","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Chi Li, Gregory D. Hager, Manmohan Chandraker, M. Zeeshan Zia, Quoc-Huy Tran, Xiang Yu","submitted_at":"2016-12-08T15:33:19Z","abstract_excerpt":"Monocular 3D object parsing is highly desirable in various scenarios including occlusion reasoning and holistic scene interpretation. We present a deep convolutional neural network (CNN) architecture to localize semantic parts in 2D image and 3D space while inferring their visibility states, given a single RGB image. Our key insight is to exploit domain knowledge to regularize the network by deeply supervising its hidden layers, in order to sequentially infer intermediate concepts associated with the final task. To acquire training data in desired quantities with ground truth 3D shape and rele"},"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":"1612.02699","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2016-12-08T15:33:19Z","cross_cats_sorted":[],"title_canon_sha256":"6532a663df6e2fead324ceeb3c6a4452166b4e1332b4a09207c7ac4944831d47","abstract_canon_sha256":"4a49c10db34faba9b459ae618b57e7710ea8c0ca0b49d99b47b936b283f1f769"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:46:02.335939Z","signature_b64":"Dlsc8HuLN/TR3d7DeDrSS4tan71LHFY6gL4udtAXjf+RIRjBvZp10erxMRb07IBXT9DXFdTyuIg72eWn66VnDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"488c997a7377f327ef9d844bb84f97bedfb11f6ec1aa7985118915fc286115cd","last_reissued_at":"2026-05-18T00:46:02.335212Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:46:02.335212Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Deep Supervision with Shape Concepts for Occlusion-Aware 3D Object Parsing","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Chi Li, Gregory D. Hager, Manmohan Chandraker, M. Zeeshan Zia, Quoc-Huy Tran, Xiang Yu","submitted_at":"2016-12-08T15:33:19Z","abstract_excerpt":"Monocular 3D object parsing is highly desirable in various scenarios including occlusion reasoning and holistic scene interpretation. We present a deep convolutional neural network (CNN) architecture to localize semantic parts in 2D image and 3D space while inferring their visibility states, given a single RGB image. Our key insight is to exploit domain knowledge to regularize the network by deeply supervising its hidden layers, in order to sequentially infer intermediate concepts associated with the final task. To acquire training data in desired quantities with ground truth 3D shape and rele"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1612.02699","kind":"arxiv","version":3},"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":"1612.02699","created_at":"2026-05-18T00:46:02.335303+00:00"},{"alias_kind":"arxiv_version","alias_value":"1612.02699v3","created_at":"2026-05-18T00:46:02.335303+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1612.02699","created_at":"2026-05-18T00:46:02.335303+00:00"},{"alias_kind":"pith_short_12","alias_value":"JCGJS6TTO7ZS","created_at":"2026-05-18T12:30:25.849896+00:00"},{"alias_kind":"pith_short_16","alias_value":"JCGJS6TTO7ZSP345","created_at":"2026-05-18T12:30:25.849896+00:00"},{"alias_kind":"pith_short_8","alias_value":"JCGJS6TT","created_at":"2026-05-18T12:30:25.849896+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"1907.11879","citing_title":"Multi-task Self-Supervised Learning for Human Activity Detection","ref_index":35,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/JCGJS6TTO7ZSP345QRF3QT4XX3","json":"https://pith.science/pith/JCGJS6TTO7ZSP345QRF3QT4XX3.json","graph_json":"https://pith.science/api/pith-number/JCGJS6TTO7ZSP345QRF3QT4XX3/graph.json","events_json":"https://pith.science/api/pith-number/JCGJS6TTO7ZSP345QRF3QT4XX3/events.json","paper":"https://pith.science/paper/JCGJS6TT"},"agent_actions":{"view_html":"https://pith.science/pith/JCGJS6TTO7ZSP345QRF3QT4XX3","download_json":"https://pith.science/pith/JCGJS6TTO7ZSP345QRF3QT4XX3.json","view_paper":"https://pith.science/paper/JCGJS6TT","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1612.02699&json=true","fetch_graph":"https://pith.science/api/pith-number/JCGJS6TTO7ZSP345QRF3QT4XX3/graph.json","fetch_events":"https://pith.science/api/pith-number/JCGJS6TTO7ZSP345QRF3QT4XX3/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/JCGJS6TTO7ZSP345QRF3QT4XX3/action/timestamp_anchor","attest_storage":"https://pith.science/pith/JCGJS6TTO7ZSP345QRF3QT4XX3/action/storage_attestation","attest_author":"https://pith.science/pith/JCGJS6TTO7ZSP345QRF3QT4XX3/action/author_attestation","sign_citation":"https://pith.science/pith/JCGJS6TTO7ZSP345QRF3QT4XX3/action/citation_signature","submit_replication":"https://pith.science/pith/JCGJS6TTO7ZSP345QRF3QT4XX3/action/replication_record"}},"created_at":"2026-05-18T00:46:02.335303+00:00","updated_at":"2026-05-18T00:46:02.335303+00:00"}