{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2017:WOA2JDVRJBRJVA6ZQ3BU3JJ5MB","short_pith_number":"pith:WOA2JDVR","canonical_record":{"source":{"id":"1702.05891","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2017-02-20T08:21:58Z","cross_cats_sorted":[],"title_canon_sha256":"307dd42a56b07831fe208446f421a4bff798ac569dc35ef38e25649688771775","abstract_canon_sha256":"c125ed649830b53f9981ba7cf32928fc3b31b8c0abe33e965283065a725bad3f"},"schema_version":"1.0"},"canonical_sha256":"b381a48eb148629a83d986c34da53d605725fcd6f6d8249a8f5529be0e5a907d","source":{"kind":"arxiv","id":"1702.05891","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1702.05891","created_at":"2026-05-18T00:47:33Z"},{"alias_kind":"arxiv_version","alias_value":"1702.05891v2","created_at":"2026-05-18T00:47:33Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1702.05891","created_at":"2026-05-18T00:47:33Z"},{"alias_kind":"pith_short_12","alias_value":"WOA2JDVRJBRJ","created_at":"2026-05-18T12:31:53Z"},{"alias_kind":"pith_short_16","alias_value":"WOA2JDVRJBRJVA6Z","created_at":"2026-05-18T12:31:53Z"},{"alias_kind":"pith_short_8","alias_value":"WOA2JDVR","created_at":"2026-05-18T12:31:53Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2017:WOA2JDVRJBRJVA6ZQ3BU3JJ5MB","target":"record","payload":{"canonical_record":{"source":{"id":"1702.05891","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2017-02-20T08:21:58Z","cross_cats_sorted":[],"title_canon_sha256":"307dd42a56b07831fe208446f421a4bff798ac569dc35ef38e25649688771775","abstract_canon_sha256":"c125ed649830b53f9981ba7cf32928fc3b31b8c0abe33e965283065a725bad3f"},"schema_version":"1.0"},"canonical_sha256":"b381a48eb148629a83d986c34da53d605725fcd6f6d8249a8f5529be0e5a907d","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:47:33.301093Z","signature_b64":"UY4fhIeIo0A1OSQ5yGV1DSB/IX1kJA3h9O5hEg77TlsVWRVEUuNTw4e/AsVoEEAlL9OYVOx3sPW8LYlvtF4sAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"b381a48eb148629a83d986c34da53d605725fcd6f6d8249a8f5529be0e5a907d","last_reissued_at":"2026-05-18T00:47:33.300496Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:47:33.300496Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1702.05891","source_version":2,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-18T00:47:33Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"f40+4WpJEUGlKIS56SVurH4VAvD+3LYBlkRG/cI28d7xlIWF3tHyqD88fA1giW1ONQz5XNEM8znAhCOsFCWpDA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-03T15:50:26.386806Z"},"content_sha256":"cdbc5698f03aa9259a4495611f045544efed5ac29bec97cb33ea0fe158e3b1b6","schema_version":"1.0","event_id":"sha256:cdbc5698f03aa9259a4495611f045544efed5ac29bec97cb33ea0fe158e3b1b6"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2017:WOA2JDVRJBRJVA6ZQ3BU3JJ5MB","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Learning Spatial Regularization with Image-level Supervisions for Multi-label Image Classification","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Feng Zhu, Hongsheng Li, Nenghai Yu, Wanli Ouyang, Xiaogang Wang","submitted_at":"2017-02-20T08:21:58Z","abstract_excerpt":"Multi-label image classification is a fundamental but challenging task in computer vision. Great progress has been achieved by exploiting semantic relations between labels in recent years. However, conventional approaches are unable to model the underlying spatial relations between labels in multi-label images, because spatial annotations of the labels are generally not provided. In this paper, we propose a unified deep neural network that exploits both semantic and spatial relations between labels with only image-level supervisions. Given a multi-label image, our proposed Spatial Regularizati"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1702.05891","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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-18T00:47:33Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"H3Urh81YC1KxQmBds1iNcdlLTBQwjAmweKFm/vppnU2UyqOCBasvYcBy8mfF/xsdB6E5ohIoJk7KQ8Iriqj1AQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-03T15:50:26.387150Z"},"content_sha256":"e7ba254078648d6cbbf8ac34eac257fe78bb520dffd2bfe5d087ea538f98c425","schema_version":"1.0","event_id":"sha256:e7ba254078648d6cbbf8ac34eac257fe78bb520dffd2bfe5d087ea538f98c425"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/WOA2JDVRJBRJVA6ZQ3BU3JJ5MB/bundle.json","state_url":"https://pith.science/pith/WOA2JDVRJBRJVA6ZQ3BU3JJ5MB/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/WOA2JDVRJBRJVA6ZQ3BU3JJ5MB/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-06-03T15:50:26Z","links":{"resolver":"https://pith.science/pith/WOA2JDVRJBRJVA6ZQ3BU3JJ5MB","bundle":"https://pith.science/pith/WOA2JDVRJBRJVA6ZQ3BU3JJ5MB/bundle.json","state":"https://pith.science/pith/WOA2JDVRJBRJVA6ZQ3BU3JJ5MB/state.json","well_known_bundle":"https://pith.science/.well-known/pith/WOA2JDVRJBRJVA6ZQ3BU3JJ5MB/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2017:WOA2JDVRJBRJVA6ZQ3BU3JJ5MB","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"c125ed649830b53f9981ba7cf32928fc3b31b8c0abe33e965283065a725bad3f","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2017-02-20T08:21:58Z","title_canon_sha256":"307dd42a56b07831fe208446f421a4bff798ac569dc35ef38e25649688771775"},"schema_version":"1.0","source":{"id":"1702.05891","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1702.05891","created_at":"2026-05-18T00:47:33Z"},{"alias_kind":"arxiv_version","alias_value":"1702.05891v2","created_at":"2026-05-18T00:47:33Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1702.05891","created_at":"2026-05-18T00:47:33Z"},{"alias_kind":"pith_short_12","alias_value":"WOA2JDVRJBRJ","created_at":"2026-05-18T12:31:53Z"},{"alias_kind":"pith_short_16","alias_value":"WOA2JDVRJBRJVA6Z","created_at":"2026-05-18T12:31:53Z"},{"alias_kind":"pith_short_8","alias_value":"WOA2JDVR","created_at":"2026-05-18T12:31:53Z"}],"graph_snapshots":[{"event_id":"sha256:e7ba254078648d6cbbf8ac34eac257fe78bb520dffd2bfe5d087ea538f98c425","target":"graph","created_at":"2026-05-18T00:47:33Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"paper":{"abstract_excerpt":"Multi-label image classification is a fundamental but challenging task in computer vision. Great progress has been achieved by exploiting semantic relations between labels in recent years. However, conventional approaches are unable to model the underlying spatial relations between labels in multi-label images, because spatial annotations of the labels are generally not provided. In this paper, we propose a unified deep neural network that exploits both semantic and spatial relations between labels with only image-level supervisions. Given a multi-label image, our proposed Spatial Regularizati","authors_text":"Feng Zhu, Hongsheng Li, Nenghai Yu, Wanli Ouyang, Xiaogang Wang","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2017-02-20T08:21:58Z","title":"Learning Spatial Regularization with Image-level Supervisions for Multi-label Image Classification"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1702.05891","kind":"arxiv","version":2},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:cdbc5698f03aa9259a4495611f045544efed5ac29bec97cb33ea0fe158e3b1b6","target":"record","created_at":"2026-05-18T00:47:33Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"c125ed649830b53f9981ba7cf32928fc3b31b8c0abe33e965283065a725bad3f","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2017-02-20T08:21:58Z","title_canon_sha256":"307dd42a56b07831fe208446f421a4bff798ac569dc35ef38e25649688771775"},"schema_version":"1.0","source":{"id":"1702.05891","kind":"arxiv","version":2}},"canonical_sha256":"b381a48eb148629a83d986c34da53d605725fcd6f6d8249a8f5529be0e5a907d","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"b381a48eb148629a83d986c34da53d605725fcd6f6d8249a8f5529be0e5a907d","first_computed_at":"2026-05-18T00:47:33.300496Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T00:47:33.300496Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"UY4fhIeIo0A1OSQ5yGV1DSB/IX1kJA3h9O5hEg77TlsVWRVEUuNTw4e/AsVoEEAlL9OYVOx3sPW8LYlvtF4sAg==","signature_status":"signed_v1","signed_at":"2026-05-18T00:47:33.301093Z","signed_message":"canonical_sha256_bytes"},"source_id":"1702.05891","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:cdbc5698f03aa9259a4495611f045544efed5ac29bec97cb33ea0fe158e3b1b6","sha256:e7ba254078648d6cbbf8ac34eac257fe78bb520dffd2bfe5d087ea538f98c425"],"state_sha256":"a70274a52fdfd45eb33584b8f979c26950fb3c8ae8f8bfab825c89d86926bb35"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"lqR/vsz+GLctq9czG9f5vQEUmyf/Dc3Y7dxdbBk6H9y77VmhsYKwkl+nPzrRt7yXu/BakbpUFl/xU8cKqoC2CA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-06-03T15:50:26.389085Z","bundle_sha256":"97df7896265ef8554523d32339d4959f682d9d6e4a635862f4d78e39117ad9be"}}