{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2018:JUYZ4CXS4F7T3FHCWAMJ4FHRV5","short_pith_number":"pith:JUYZ4CXS","schema_version":"1.0","canonical_sha256":"4d319e0af2e17f3d94e2b0189e14f1af615012adc1f218c1f5d88a0dd19a24d9","source":{"kind":"arxiv","id":"1807.02800","version":2},"attestation_state":"computed","paper":{"title":"Spatio-Temporal Instance Learning: Action Tubes from Class Supervision","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Cees G. M. Snoek, Pascal Mettes","submitted_at":"2018-07-08T11:12:51Z","abstract_excerpt":"The goal of this work is spatio-temporal action localization in videos, using only the supervision from video-level class labels. The state-of-the-art casts this weakly-supervised action localization regime as a Multiple Instance Learning problem, where instances are a priori computed spatio-temporal proposals. Rather than disconnecting the spatio-temporal learning from the training, we propose Spatio-Temporal Instance Learning, which enables action localization directly from box proposals in video frames. We outline the assumptions of our model and propose a max-margin objective and optimizat"},"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":"1807.02800","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2018-07-08T11:12:51Z","cross_cats_sorted":[],"title_canon_sha256":"74c238925a0c0e6cbde76da739f29bd2a78f47ae77f5a62e1d6298566df6ca40","abstract_canon_sha256":"e33d58d8576f01be68f89dd87945f881e4757d62dbf01194c53b2c43380595af"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:00:08.356165Z","signature_b64":"shh1MJB1sz2aN9GcsuENnAHPV+VRQVsZTauqy+0KTke5lQczeTYjxwAzed+x7bZe80wk4J+KcFapgMiHpyo2AQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"4d319e0af2e17f3d94e2b0189e14f1af615012adc1f218c1f5d88a0dd19a24d9","last_reissued_at":"2026-05-18T00:00:08.355713Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:00:08.355713Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Spatio-Temporal Instance Learning: Action Tubes from Class Supervision","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Cees G. M. Snoek, Pascal Mettes","submitted_at":"2018-07-08T11:12:51Z","abstract_excerpt":"The goal of this work is spatio-temporal action localization in videos, using only the supervision from video-level class labels. The state-of-the-art casts this weakly-supervised action localization regime as a Multiple Instance Learning problem, where instances are a priori computed spatio-temporal proposals. Rather than disconnecting the spatio-temporal learning from the training, we propose Spatio-Temporal Instance Learning, which enables action localization directly from box proposals in video frames. We outline the assumptions of our model and propose a max-margin objective and optimizat"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1807.02800","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":"1807.02800","created_at":"2026-05-18T00:00:08.355775+00:00"},{"alias_kind":"arxiv_version","alias_value":"1807.02800v2","created_at":"2026-05-18T00:00:08.355775+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1807.02800","created_at":"2026-05-18T00:00:08.355775+00:00"},{"alias_kind":"pith_short_12","alias_value":"JUYZ4CXS4F7T","created_at":"2026-05-18T12:32:31.084164+00:00"},{"alias_kind":"pith_short_16","alias_value":"JUYZ4CXS4F7T3FHC","created_at":"2026-05-18T12:32:31.084164+00:00"},{"alias_kind":"pith_short_8","alias_value":"JUYZ4CXS","created_at":"2026-05-18T12:32:31.084164+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/JUYZ4CXS4F7T3FHCWAMJ4FHRV5","json":"https://pith.science/pith/JUYZ4CXS4F7T3FHCWAMJ4FHRV5.json","graph_json":"https://pith.science/api/pith-number/JUYZ4CXS4F7T3FHCWAMJ4FHRV5/graph.json","events_json":"https://pith.science/api/pith-number/JUYZ4CXS4F7T3FHCWAMJ4FHRV5/events.json","paper":"https://pith.science/paper/JUYZ4CXS"},"agent_actions":{"view_html":"https://pith.science/pith/JUYZ4CXS4F7T3FHCWAMJ4FHRV5","download_json":"https://pith.science/pith/JUYZ4CXS4F7T3FHCWAMJ4FHRV5.json","view_paper":"https://pith.science/paper/JUYZ4CXS","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1807.02800&json=true","fetch_graph":"https://pith.science/api/pith-number/JUYZ4CXS4F7T3FHCWAMJ4FHRV5/graph.json","fetch_events":"https://pith.science/api/pith-number/JUYZ4CXS4F7T3FHCWAMJ4FHRV5/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/JUYZ4CXS4F7T3FHCWAMJ4FHRV5/action/timestamp_anchor","attest_storage":"https://pith.science/pith/JUYZ4CXS4F7T3FHCWAMJ4FHRV5/action/storage_attestation","attest_author":"https://pith.science/pith/JUYZ4CXS4F7T3FHCWAMJ4FHRV5/action/author_attestation","sign_citation":"https://pith.science/pith/JUYZ4CXS4F7T3FHCWAMJ4FHRV5/action/citation_signature","submit_replication":"https://pith.science/pith/JUYZ4CXS4F7T3FHCWAMJ4FHRV5/action/replication_record"}},"created_at":"2026-05-18T00:00:08.355775+00:00","updated_at":"2026-05-18T00:00:08.355775+00:00"}