{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2016:W3O47GALUUQA2SYMGV7XJAEYL7","short_pith_number":"pith:W3O47GAL","schema_version":"1.0","canonical_sha256":"b6ddcf980ba5200d4b0c357f7480985ff782ceaf58a9ba910f0b58f757743136","source":{"kind":"arxiv","id":"1605.08140","version":3},"attestation_state":"computed","paper":{"title":"Learning Latent Sub-events in Activity Videos Using Temporal Attention Filters","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"AJ Piergiovanni, Chenyou Fan, Michael S. Ryoo","submitted_at":"2016-05-26T04:02:01Z","abstract_excerpt":"In this paper, we newly introduce the concept of temporal attention filters, and describe how they can be used for human activity recognition from videos. Many high-level activities are often composed of multiple temporal parts (e.g., sub-events) with different duration/speed, and our objective is to make the model explicitly learn such temporal structure using multiple attention filters and benefit from them. Our temporal filters are designed to be fully differentiable, allowing end-of-end training of the temporal filters together with the underlying frame-based or segment-based convolutional"},"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":"1605.08140","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2016-05-26T04:02:01Z","cross_cats_sorted":[],"title_canon_sha256":"c9f600456b6cc7c860831316f2d32426cfd3df51a462787e60816cad648cb1f6","abstract_canon_sha256":"b0816edb2f2189c29012b16b0073f1f639cbc4ecaff030bd1dfdc37e1cc0b36b"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:54:03.192535Z","signature_b64":"e4ov4xBw04Fvufm/zJhXYHD89tspisbSR6WsnpZzvXlz2KHgyA18kJhyiARKpQidhdre3CtJJVVEtVBxmukyAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"b6ddcf980ba5200d4b0c357f7480985ff782ceaf58a9ba910f0b58f757743136","last_reissued_at":"2026-05-18T00:54:03.192112Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:54:03.192112Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Learning Latent Sub-events in Activity Videos Using Temporal Attention Filters","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"AJ Piergiovanni, Chenyou Fan, Michael S. Ryoo","submitted_at":"2016-05-26T04:02:01Z","abstract_excerpt":"In this paper, we newly introduce the concept of temporal attention filters, and describe how they can be used for human activity recognition from videos. Many high-level activities are often composed of multiple temporal parts (e.g., sub-events) with different duration/speed, and our objective is to make the model explicitly learn such temporal structure using multiple attention filters and benefit from them. Our temporal filters are designed to be fully differentiable, allowing end-of-end training of the temporal filters together with the underlying frame-based or segment-based convolutional"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1605.08140","kind":"arxiv","version":3},"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":"1605.08140","created_at":"2026-05-18T00:54:03.192168+00:00"},{"alias_kind":"arxiv_version","alias_value":"1605.08140v3","created_at":"2026-05-18T00:54:03.192168+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1605.08140","created_at":"2026-05-18T00:54:03.192168+00:00"},{"alias_kind":"pith_short_12","alias_value":"W3O47GALUUQA","created_at":"2026-05-18T12:30:48.956258+00:00"},{"alias_kind":"pith_short_16","alias_value":"W3O47GALUUQA2SYM","created_at":"2026-05-18T12:30:48.956258+00:00"},{"alias_kind":"pith_short_8","alias_value":"W3O47GAL","created_at":"2026-05-18T12:30:48.956258+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/W3O47GALUUQA2SYMGV7XJAEYL7","json":"https://pith.science/pith/W3O47GALUUQA2SYMGV7XJAEYL7.json","graph_json":"https://pith.science/api/pith-number/W3O47GALUUQA2SYMGV7XJAEYL7/graph.json","events_json":"https://pith.science/api/pith-number/W3O47GALUUQA2SYMGV7XJAEYL7/events.json","paper":"https://pith.science/paper/W3O47GAL"},"agent_actions":{"view_html":"https://pith.science/pith/W3O47GALUUQA2SYMGV7XJAEYL7","download_json":"https://pith.science/pith/W3O47GALUUQA2SYMGV7XJAEYL7.json","view_paper":"https://pith.science/paper/W3O47GAL","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1605.08140&json=true","fetch_graph":"https://pith.science/api/pith-number/W3O47GALUUQA2SYMGV7XJAEYL7/graph.json","fetch_events":"https://pith.science/api/pith-number/W3O47GALUUQA2SYMGV7XJAEYL7/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/W3O47GALUUQA2SYMGV7XJAEYL7/action/timestamp_anchor","attest_storage":"https://pith.science/pith/W3O47GALUUQA2SYMGV7XJAEYL7/action/storage_attestation","attest_author":"https://pith.science/pith/W3O47GALUUQA2SYMGV7XJAEYL7/action/author_attestation","sign_citation":"https://pith.science/pith/W3O47GALUUQA2SYMGV7XJAEYL7/action/citation_signature","submit_replication":"https://pith.science/pith/W3O47GALUUQA2SYMGV7XJAEYL7/action/replication_record"}},"created_at":"2026-05-18T00:54:03.192168+00:00","updated_at":"2026-05-18T00:54:03.192168+00:00"}