{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2020:PU3FGN7OATU56LNFDSKR7IGYPH","short_pith_number":"pith:PU3FGN7O","schema_version":"1.0","canonical_sha256":"7d365337ee04e9df2da51c951fa0d879f4ac958b95a72be29258636996dee2ba","source":{"kind":"arxiv","id":"2006.08247","version":2},"attestation_state":"computed","paper":{"title":"Learn to cycle: Time-consistent feature discovery for action recognition","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Alexandros Stergiou, Ronald Poppe","submitted_at":"2020-06-15T09:36:28Z","abstract_excerpt":"Generalizing over temporal variations is a prerequisite for effective action recognition in videos. Despite significant advances in deep neural networks, it remains a challenge to focus on short-term discriminative motions in relation to the overall performance of an action. We address this challenge by allowing some flexibility in discovering relevant spatio-temporal features. We introduce Squeeze and Recursion Temporal Gates (SRTG), an approach that favors inputs with similar activations with potential temporal variations. We implement this idea with a novel CNN block that uses an LSTM to en"},"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":"2006.08247","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2020-06-15T09:36:28Z","cross_cats_sorted":[],"title_canon_sha256":"8a2b93e7c7c0b17c9c089e84a440a162af5531565ecb03f642a39105461e7f55","abstract_canon_sha256":"424e34f58d02b3ec45814cacb44d774006b40c942e26479d5b1785e1c1bf148e"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T01:53:51.953478Z","signature_b64":"wZ9L0+mI5RpKKNntkWjrUAvGoSD8h+Eka0i2jsoStzRsQmIQpvy4TKcVM83P6Qd94RPqm9qWXd91Ya1Q8IHMAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"7d365337ee04e9df2da51c951fa0d879f4ac958b95a72be29258636996dee2ba","last_reissued_at":"2026-07-05T01:53:51.953079Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T01:53:51.953079Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Learn to cycle: Time-consistent feature discovery for action recognition","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Alexandros Stergiou, Ronald Poppe","submitted_at":"2020-06-15T09:36:28Z","abstract_excerpt":"Generalizing over temporal variations is a prerequisite for effective action recognition in videos. Despite significant advances in deep neural networks, it remains a challenge to focus on short-term discriminative motions in relation to the overall performance of an action. We address this challenge by allowing some flexibility in discovering relevant spatio-temporal features. We introduce Squeeze and Recursion Temporal Gates (SRTG), an approach that favors inputs with similar activations with potential temporal variations. We implement this idea with a novel CNN block that uses an LSTM to en"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2006.08247","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/2006.08247/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":"2006.08247","created_at":"2026-07-05T01:53:51.953139+00:00"},{"alias_kind":"arxiv_version","alias_value":"2006.08247v2","created_at":"2026-07-05T01:53:51.953139+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2006.08247","created_at":"2026-07-05T01:53:51.953139+00:00"},{"alias_kind":"pith_short_12","alias_value":"PU3FGN7OATU5","created_at":"2026-07-05T01:53:51.953139+00:00"},{"alias_kind":"pith_short_16","alias_value":"PU3FGN7OATU56LNF","created_at":"2026-07-05T01:53:51.953139+00:00"},{"alias_kind":"pith_short_8","alias_value":"PU3FGN7O","created_at":"2026-07-05T01:53:51.953139+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/PU3FGN7OATU56LNFDSKR7IGYPH","json":"https://pith.science/pith/PU3FGN7OATU56LNFDSKR7IGYPH.json","graph_json":"https://pith.science/api/pith-number/PU3FGN7OATU56LNFDSKR7IGYPH/graph.json","events_json":"https://pith.science/api/pith-number/PU3FGN7OATU56LNFDSKR7IGYPH/events.json","paper":"https://pith.science/paper/PU3FGN7O"},"agent_actions":{"view_html":"https://pith.science/pith/PU3FGN7OATU56LNFDSKR7IGYPH","download_json":"https://pith.science/pith/PU3FGN7OATU56LNFDSKR7IGYPH.json","view_paper":"https://pith.science/paper/PU3FGN7O","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2006.08247&json=true","fetch_graph":"https://pith.science/api/pith-number/PU3FGN7OATU56LNFDSKR7IGYPH/graph.json","fetch_events":"https://pith.science/api/pith-number/PU3FGN7OATU56LNFDSKR7IGYPH/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/PU3FGN7OATU56LNFDSKR7IGYPH/action/timestamp_anchor","attest_storage":"https://pith.science/pith/PU3FGN7OATU56LNFDSKR7IGYPH/action/storage_attestation","attest_author":"https://pith.science/pith/PU3FGN7OATU56LNFDSKR7IGYPH/action/author_attestation","sign_citation":"https://pith.science/pith/PU3FGN7OATU56LNFDSKR7IGYPH/action/citation_signature","submit_replication":"https://pith.science/pith/PU3FGN7OATU56LNFDSKR7IGYPH/action/replication_record"}},"created_at":"2026-07-05T01:53:51.953139+00:00","updated_at":"2026-07-05T01:53:51.953139+00:00"}