{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2017:GT2373KASNFEG5Y6ZIJ57IG2NW","short_pith_number":"pith:GT2373KA","schema_version":"1.0","canonical_sha256":"34f5bfed40934a43771eca13dfa0da6d88cd391cd4c9b591e6d07527b63a296a","source":{"kind":"arxiv","id":"1801.01080","version":1},"attestation_state":"computed","paper":{"title":"Cooperative Training of Deep Aggregation Networks for RGB-D Action Recognition","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Jun Wan, Philip Ogunbona, Pichao Wang, Wanqing Li, Xinwang Liu","submitted_at":"2017-12-05T07:33:20Z","abstract_excerpt":"A novel deep neural network training paradigm that exploits the conjoint information in multiple heterogeneous sources is proposed. Specifically, in a RGB-D based action recognition task, it cooperatively trains a single convolutional neural network (named c-ConvNet) on both RGB visual features and depth features, and deeply aggregates the two kinds of features for action recognition. Differently from the conventional ConvNet that learns the deep separable features for homogeneous modality-based classification with only one softmax loss function, the c-ConvNet enhances the discriminative power"},"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":"1801.01080","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2017-12-05T07:33:20Z","cross_cats_sorted":[],"title_canon_sha256":"615dd9f160a0f53bf472981ca692d9f09735fd91732b33c91c5db16cd9c1b326","abstract_canon_sha256":"edd1acca6424ca26b24ae1fdefe1f4fe408c5497ff369b137b3875f5434af0ab"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:26:47.886626Z","signature_b64":"x8cXMs9z4Lv0A+TK04Y9wxS55xT91r3/2LgNSRhyAQ2nLhbT5cajuKEW+nAzh48dRw+5TdUnDoLj79tJq2EaCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"34f5bfed40934a43771eca13dfa0da6d88cd391cd4c9b591e6d07527b63a296a","last_reissued_at":"2026-05-18T00:26:47.885958Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:26:47.885958Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Cooperative Training of Deep Aggregation Networks for RGB-D Action Recognition","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Jun Wan, Philip Ogunbona, Pichao Wang, Wanqing Li, Xinwang Liu","submitted_at":"2017-12-05T07:33:20Z","abstract_excerpt":"A novel deep neural network training paradigm that exploits the conjoint information in multiple heterogeneous sources is proposed. Specifically, in a RGB-D based action recognition task, it cooperatively trains a single convolutional neural network (named c-ConvNet) on both RGB visual features and depth features, and deeply aggregates the two kinds of features for action recognition. Differently from the conventional ConvNet that learns the deep separable features for homogeneous modality-based classification with only one softmax loss function, the c-ConvNet enhances the discriminative power"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1801.01080","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":"1801.01080","created_at":"2026-05-18T00:26:47.886059+00:00"},{"alias_kind":"arxiv_version","alias_value":"1801.01080v1","created_at":"2026-05-18T00:26:47.886059+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1801.01080","created_at":"2026-05-18T00:26:47.886059+00:00"},{"alias_kind":"pith_short_12","alias_value":"GT2373KASNFE","created_at":"2026-05-18T12:31:18.294218+00:00"},{"alias_kind":"pith_short_16","alias_value":"GT2373KASNFEG5Y6","created_at":"2026-05-18T12:31:18.294218+00:00"},{"alias_kind":"pith_short_8","alias_value":"GT2373KA","created_at":"2026-05-18T12:31:18.294218+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/GT2373KASNFEG5Y6ZIJ57IG2NW","json":"https://pith.science/pith/GT2373KASNFEG5Y6ZIJ57IG2NW.json","graph_json":"https://pith.science/api/pith-number/GT2373KASNFEG5Y6ZIJ57IG2NW/graph.json","events_json":"https://pith.science/api/pith-number/GT2373KASNFEG5Y6ZIJ57IG2NW/events.json","paper":"https://pith.science/paper/GT2373KA"},"agent_actions":{"view_html":"https://pith.science/pith/GT2373KASNFEG5Y6ZIJ57IG2NW","download_json":"https://pith.science/pith/GT2373KASNFEG5Y6ZIJ57IG2NW.json","view_paper":"https://pith.science/paper/GT2373KA","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1801.01080&json=true","fetch_graph":"https://pith.science/api/pith-number/GT2373KASNFEG5Y6ZIJ57IG2NW/graph.json","fetch_events":"https://pith.science/api/pith-number/GT2373KASNFEG5Y6ZIJ57IG2NW/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/GT2373KASNFEG5Y6ZIJ57IG2NW/action/timestamp_anchor","attest_storage":"https://pith.science/pith/GT2373KASNFEG5Y6ZIJ57IG2NW/action/storage_attestation","attest_author":"https://pith.science/pith/GT2373KASNFEG5Y6ZIJ57IG2NW/action/author_attestation","sign_citation":"https://pith.science/pith/GT2373KASNFEG5Y6ZIJ57IG2NW/action/citation_signature","submit_replication":"https://pith.science/pith/GT2373KASNFEG5Y6ZIJ57IG2NW/action/replication_record"}},"created_at":"2026-05-18T00:26:47.886059+00:00","updated_at":"2026-05-18T00:26:47.886059+00:00"}