{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:54V4MPRRBJPI7DRBLARLF7XOAX","short_pith_number":"pith:54V4MPRR","schema_version":"1.0","canonical_sha256":"ef2bc63e310a5e8f8e215822b2feee05facd01c6b9a2496be32a08e72bf72625","source":{"kind":"arxiv","id":"2109.05779","version":2},"attestation_state":"computed","paper":{"title":"Deep Joint Source-Channel Coding for Multi-Task Network","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CV","authors_text":"Jiahui Li, Mengyang Wang, Mengyao Ma, Xiaopeng Fan, Zhicong Zhang","submitted_at":"2021-09-13T08:58:02Z","abstract_excerpt":"Multi-task learning (MTL) is an efficient way to improve the performance of related tasks by sharing knowledge. However, most existing MTL networks run on a single end and are not suitable for collaborative intelligence (CI) scenarios. In this work, we propose an MTL network with a deep joint source-channel coding (JSCC) framework, which allows operating under CI scenarios. We first propose a feature fusion based MTL network (FFMNet) for joint object detection and semantic segmentation. Compared with other MTL networks, FFMNet gets higher performance with fewer parameters. Then FFMNet is split"},"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":"2109.05779","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2021-09-13T08:58:02Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"c4d29770343721e9faccd86203eac0202c742ffef2f1de7907ad6428aaf95a95","abstract_canon_sha256":"eb0e9a67bc25501e28e72e37d6adc070b17f5eff8545385295a515836171693e"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T03:28:25.378475Z","signature_b64":"ltxiddX2TVMdsVbSiNxkUN6V7pIESMN+QRvNVnzST3PJeFGhlxm4q+GiMUpz6euZBArPJ+n8zryeYkEzYP5NBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"ef2bc63e310a5e8f8e215822b2feee05facd01c6b9a2496be32a08e72bf72625","last_reissued_at":"2026-07-05T03:28:25.378063Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T03:28:25.378063Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Deep Joint Source-Channel Coding for Multi-Task Network","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CV","authors_text":"Jiahui Li, Mengyang Wang, Mengyao Ma, Xiaopeng Fan, Zhicong Zhang","submitted_at":"2021-09-13T08:58:02Z","abstract_excerpt":"Multi-task learning (MTL) is an efficient way to improve the performance of related tasks by sharing knowledge. However, most existing MTL networks run on a single end and are not suitable for collaborative intelligence (CI) scenarios. In this work, we propose an MTL network with a deep joint source-channel coding (JSCC) framework, which allows operating under CI scenarios. We first propose a feature fusion based MTL network (FFMNet) for joint object detection and semantic segmentation. Compared with other MTL networks, FFMNet gets higher performance with fewer parameters. Then FFMNet is split"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2109.05779","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/2109.05779/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":"2109.05779","created_at":"2026-07-05T03:28:25.378128+00:00"},{"alias_kind":"arxiv_version","alias_value":"2109.05779v2","created_at":"2026-07-05T03:28:25.378128+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2109.05779","created_at":"2026-07-05T03:28:25.378128+00:00"},{"alias_kind":"pith_short_12","alias_value":"54V4MPRRBJPI","created_at":"2026-07-05T03:28:25.378128+00:00"},{"alias_kind":"pith_short_16","alias_value":"54V4MPRRBJPI7DRB","created_at":"2026-07-05T03:28:25.378128+00:00"},{"alias_kind":"pith_short_8","alias_value":"54V4MPRR","created_at":"2026-07-05T03:28:25.378128+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/54V4MPRRBJPI7DRBLARLF7XOAX","json":"https://pith.science/pith/54V4MPRRBJPI7DRBLARLF7XOAX.json","graph_json":"https://pith.science/api/pith-number/54V4MPRRBJPI7DRBLARLF7XOAX/graph.json","events_json":"https://pith.science/api/pith-number/54V4MPRRBJPI7DRBLARLF7XOAX/events.json","paper":"https://pith.science/paper/54V4MPRR"},"agent_actions":{"view_html":"https://pith.science/pith/54V4MPRRBJPI7DRBLARLF7XOAX","download_json":"https://pith.science/pith/54V4MPRRBJPI7DRBLARLF7XOAX.json","view_paper":"https://pith.science/paper/54V4MPRR","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2109.05779&json=true","fetch_graph":"https://pith.science/api/pith-number/54V4MPRRBJPI7DRBLARLF7XOAX/graph.json","fetch_events":"https://pith.science/api/pith-number/54V4MPRRBJPI7DRBLARLF7XOAX/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/54V4MPRRBJPI7DRBLARLF7XOAX/action/timestamp_anchor","attest_storage":"https://pith.science/pith/54V4MPRRBJPI7DRBLARLF7XOAX/action/storage_attestation","attest_author":"https://pith.science/pith/54V4MPRRBJPI7DRBLARLF7XOAX/action/author_attestation","sign_citation":"https://pith.science/pith/54V4MPRRBJPI7DRBLARLF7XOAX/action/citation_signature","submit_replication":"https://pith.science/pith/54V4MPRRBJPI7DRBLARLF7XOAX/action/replication_record"}},"created_at":"2026-07-05T03:28:25.378128+00:00","updated_at":"2026-07-05T03:28:25.378128+00:00"}