{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2017:QRTK22ALLOFAXJCNJK55UONQD4","short_pith_number":"pith:QRTK22AL","schema_version":"1.0","canonical_sha256":"8466ad680b5b8a0ba44d4abbda39b01f3ae6022f2764009226eec6d58b73f905","source":{"kind":"arxiv","id":"1709.01220","version":2},"attestation_state":"computed","paper":{"title":"Multi-Modal Multi-Scale Deep Learning for Large-Scale Image Annotation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Ji-Rong Wen, Shih-Fu Chang, Tao Xiang, Yulei Niu, Zhiwu Lu","submitted_at":"2017-09-05T02:50:45Z","abstract_excerpt":"Image annotation aims to annotate a given image with a variable number of class labels corresponding to diverse visual concepts. In this paper, we address two main issues in large-scale image annotation: 1) how to learn a rich feature representation suitable for predicting a diverse set of visual concepts ranging from object, scene to abstract concept; 2) how to annotate an image with the optimal number of class labels. To address the first issue, we propose a novel multi-scale deep model for extracting rich and discriminative features capable of representing a wide range of visual concepts. S"},"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":"1709.01220","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2017-09-05T02:50:45Z","cross_cats_sorted":[],"title_canon_sha256":"df3db4123e90eaf5a3dbaf4af8d9313edcd2765aa8ccc24fc1544eadec2dd8b9","abstract_canon_sha256":"90547f9babb5e66cbc16aa40e9a99fcb12ea67aa4e831e9bf88b1d3585f18501"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:02:49.780941Z","signature_b64":"bUhDU1Vg85lQH3Z/RZMwHrG/SMLuS9tJuASpDb2ae+dc86Ef1C241wFd8D5szzbos+jzxoWHZSyCJ424ZGNuBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"8466ad680b5b8a0ba44d4abbda39b01f3ae6022f2764009226eec6d58b73f905","last_reissued_at":"2026-05-18T00:02:49.780465Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:02:49.780465Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Multi-Modal Multi-Scale Deep Learning for Large-Scale Image Annotation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Ji-Rong Wen, Shih-Fu Chang, Tao Xiang, Yulei Niu, Zhiwu Lu","submitted_at":"2017-09-05T02:50:45Z","abstract_excerpt":"Image annotation aims to annotate a given image with a variable number of class labels corresponding to diverse visual concepts. In this paper, we address two main issues in large-scale image annotation: 1) how to learn a rich feature representation suitable for predicting a diverse set of visual concepts ranging from object, scene to abstract concept; 2) how to annotate an image with the optimal number of class labels. To address the first issue, we propose a novel multi-scale deep model for extracting rich and discriminative features capable of representing a wide range of visual concepts. S"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1709.01220","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":""},"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":"1709.01220","created_at":"2026-05-18T00:02:49.780546+00:00"},{"alias_kind":"arxiv_version","alias_value":"1709.01220v2","created_at":"2026-05-18T00:02:49.780546+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1709.01220","created_at":"2026-05-18T00:02:49.780546+00:00"},{"alias_kind":"pith_short_12","alias_value":"QRTK22ALLOFA","created_at":"2026-05-18T12:31:39.905425+00:00"},{"alias_kind":"pith_short_16","alias_value":"QRTK22ALLOFAXJCN","created_at":"2026-05-18T12:31:39.905425+00:00"},{"alias_kind":"pith_short_8","alias_value":"QRTK22AL","created_at":"2026-05-18T12:31:39.905425+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/QRTK22ALLOFAXJCNJK55UONQD4","json":"https://pith.science/pith/QRTK22ALLOFAXJCNJK55UONQD4.json","graph_json":"https://pith.science/api/pith-number/QRTK22ALLOFAXJCNJK55UONQD4/graph.json","events_json":"https://pith.science/api/pith-number/QRTK22ALLOFAXJCNJK55UONQD4/events.json","paper":"https://pith.science/paper/QRTK22AL"},"agent_actions":{"view_html":"https://pith.science/pith/QRTK22ALLOFAXJCNJK55UONQD4","download_json":"https://pith.science/pith/QRTK22ALLOFAXJCNJK55UONQD4.json","view_paper":"https://pith.science/paper/QRTK22AL","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1709.01220&json=true","fetch_graph":"https://pith.science/api/pith-number/QRTK22ALLOFAXJCNJK55UONQD4/graph.json","fetch_events":"https://pith.science/api/pith-number/QRTK22ALLOFAXJCNJK55UONQD4/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/QRTK22ALLOFAXJCNJK55UONQD4/action/timestamp_anchor","attest_storage":"https://pith.science/pith/QRTK22ALLOFAXJCNJK55UONQD4/action/storage_attestation","attest_author":"https://pith.science/pith/QRTK22ALLOFAXJCNJK55UONQD4/action/author_attestation","sign_citation":"https://pith.science/pith/QRTK22ALLOFAXJCNJK55UONQD4/action/citation_signature","submit_replication":"https://pith.science/pith/QRTK22ALLOFAXJCNJK55UONQD4/action/replication_record"}},"created_at":"2026-05-18T00:02:49.780546+00:00","updated_at":"2026-05-18T00:02:49.780546+00:00"}