{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2019:26VAQ7I46XMBRI2TX6DU2A5EFX","short_pith_number":"pith:26VAQ7I4","schema_version":"1.0","canonical_sha256":"d7aa087d1cf5d818a353bf874d03a42dfe3c551eb31a771fecb64c4d010aeffb","source":{"kind":"arxiv","id":"1907.13369","version":2},"attestation_state":"computed","paper":{"title":"Multi-Agent Reinforcement Learning Based Frame Sampling for Effective Untrimmed Video Recognition","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Dongliang He, Shifeng Chen, Shilei Wen, Wenhao Wu, Xiao Tan","submitted_at":"2019-07-31T08:51:31Z","abstract_excerpt":"Video Recognition has drawn great research interest and great progress has been made. A suitable frame sampling strategy can improve the accuracy and efficiency of recognition. However, mainstream solutions generally adopt hand-crafted frame sampling strategies for recognition. It could degrade the performance, especially in untrimmed videos, due to the variation of frame-level saliency. To this end, we concentrate on improving untrimmed video classification via developing a learning-based frame sampling strategy. We intuitively formulate the frame sampling procedure as multiple parallel Marko"},"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":"1907.13369","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2019-07-31T08:51:31Z","cross_cats_sorted":[],"title_canon_sha256":"77308437130cee3cc2e492ed08c0288ccd3a80bbb6ed8ec69cdda002cfdd079c","abstract_canon_sha256":"7043583bb4a2e4a579b5133f361b22dad40f6b116ecd702b59034f3e67ba4d0a"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-04T23:51:06.065656Z","signature_b64":"XBTNyMtB1p26P4mc7QqR7DKAkyHA+MMa3PyQ7AXO0EP6iaGJaeepDtVG3WLio75DgKMlCc8AOnU6kuNHq2ORAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"d7aa087d1cf5d818a353bf874d03a42dfe3c551eb31a771fecb64c4d010aeffb","last_reissued_at":"2026-07-04T23:51:06.065237Z","signature_status":"signed_v1","first_computed_at":"2026-07-04T23:51:06.065237Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Multi-Agent Reinforcement Learning Based Frame Sampling for Effective Untrimmed Video Recognition","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Dongliang He, Shifeng Chen, Shilei Wen, Wenhao Wu, Xiao Tan","submitted_at":"2019-07-31T08:51:31Z","abstract_excerpt":"Video Recognition has drawn great research interest and great progress has been made. A suitable frame sampling strategy can improve the accuracy and efficiency of recognition. However, mainstream solutions generally adopt hand-crafted frame sampling strategies for recognition. It could degrade the performance, especially in untrimmed videos, due to the variation of frame-level saliency. To this end, we concentrate on improving untrimmed video classification via developing a learning-based frame sampling strategy. We intuitively formulate the frame sampling procedure as multiple parallel Marko"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1907.13369","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/1907.13369/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":"1907.13369","created_at":"2026-07-04T23:51:06.065292+00:00"},{"alias_kind":"arxiv_version","alias_value":"1907.13369v2","created_at":"2026-07-04T23:51:06.065292+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1907.13369","created_at":"2026-07-04T23:51:06.065292+00:00"},{"alias_kind":"pith_short_12","alias_value":"26VAQ7I46XMB","created_at":"2026-07-04T23:51:06.065292+00:00"},{"alias_kind":"pith_short_16","alias_value":"26VAQ7I46XMBRI2T","created_at":"2026-07-04T23:51:06.065292+00:00"},{"alias_kind":"pith_short_8","alias_value":"26VAQ7I4","created_at":"2026-07-04T23:51:06.065292+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/26VAQ7I46XMBRI2TX6DU2A5EFX","json":"https://pith.science/pith/26VAQ7I46XMBRI2TX6DU2A5EFX.json","graph_json":"https://pith.science/api/pith-number/26VAQ7I46XMBRI2TX6DU2A5EFX/graph.json","events_json":"https://pith.science/api/pith-number/26VAQ7I46XMBRI2TX6DU2A5EFX/events.json","paper":"https://pith.science/paper/26VAQ7I4"},"agent_actions":{"view_html":"https://pith.science/pith/26VAQ7I46XMBRI2TX6DU2A5EFX","download_json":"https://pith.science/pith/26VAQ7I46XMBRI2TX6DU2A5EFX.json","view_paper":"https://pith.science/paper/26VAQ7I4","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1907.13369&json=true","fetch_graph":"https://pith.science/api/pith-number/26VAQ7I46XMBRI2TX6DU2A5EFX/graph.json","fetch_events":"https://pith.science/api/pith-number/26VAQ7I46XMBRI2TX6DU2A5EFX/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/26VAQ7I46XMBRI2TX6DU2A5EFX/action/timestamp_anchor","attest_storage":"https://pith.science/pith/26VAQ7I46XMBRI2TX6DU2A5EFX/action/storage_attestation","attest_author":"https://pith.science/pith/26VAQ7I46XMBRI2TX6DU2A5EFX/action/author_attestation","sign_citation":"https://pith.science/pith/26VAQ7I46XMBRI2TX6DU2A5EFX/action/citation_signature","submit_replication":"https://pith.science/pith/26VAQ7I46XMBRI2TX6DU2A5EFX/action/replication_record"}},"created_at":"2026-07-04T23:51:06.065292+00:00","updated_at":"2026-07-04T23:51:06.065292+00:00"}