{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2018:LZUVBTYJ3JFUKK7U3VX4K4YQJH","short_pith_number":"pith:LZUVBTYJ","schema_version":"1.0","canonical_sha256":"5e6950cf09da4b452bf4dd6fc5731049e7e92000d38b1af7813f57867d6452b0","source":{"kind":"arxiv","id":"1803.01457","version":1},"attestation_state":"computed","paper":{"title":"Less Is More: Picking Informative Frames for Video Captioning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Qingming Huang, Shuhui Wang, Weigang Zhang, Yangyu Chen","submitted_at":"2018-03-05T01:57:49Z","abstract_excerpt":"In video captioning task, the best practice has been achieved by attention-based models which associate salient visual components with sentences in the video. However, existing study follows a common procedure which includes a frame-level appearance modeling and motion modeling on equal interval frame sampling, which may bring about redundant visual information, sensitivity to content noise and unnecessary computation cost.\n  We propose a plug-and-play PickNet to perform informative frame picking in video captioning. Based on a standard Encoder-Decoder framework, we develop a reinforcement-lea"},"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":"1803.01457","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2018-03-05T01:57:49Z","cross_cats_sorted":[],"title_canon_sha256":"301125ce043aa8dd315cdfb5e562aa6f8efd2dc4d37ea83de13f76c56b7a2067","abstract_canon_sha256":"19557015749090fd373ffee7662bf9e6d2b19cff990ae2d02e66f56fc3b7751e"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:22:00.630797Z","signature_b64":"s13df/hZcsy1ckV9QS/DHi9Ir2TnQpJnzUC/EjvcnpVkEIehG473iaYs04Hbmx3iZ8cJVAgLrtvbOOkII9EiAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"5e6950cf09da4b452bf4dd6fc5731049e7e92000d38b1af7813f57867d6452b0","last_reissued_at":"2026-05-18T00:22:00.630356Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:22:00.630356Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Less Is More: Picking Informative Frames for Video Captioning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Qingming Huang, Shuhui Wang, Weigang Zhang, Yangyu Chen","submitted_at":"2018-03-05T01:57:49Z","abstract_excerpt":"In video captioning task, the best practice has been achieved by attention-based models which associate salient visual components with sentences in the video. However, existing study follows a common procedure which includes a frame-level appearance modeling and motion modeling on equal interval frame sampling, which may bring about redundant visual information, sensitivity to content noise and unnecessary computation cost.\n  We propose a plug-and-play PickNet to perform informative frame picking in video captioning. Based on a standard Encoder-Decoder framework, we develop a reinforcement-lea"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1803.01457","kind":"arxiv","version":1},"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":"1803.01457","created_at":"2026-05-18T00:22:00.630425+00:00"},{"alias_kind":"arxiv_version","alias_value":"1803.01457v1","created_at":"2026-05-18T00:22:00.630425+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1803.01457","created_at":"2026-05-18T00:22:00.630425+00:00"},{"alias_kind":"pith_short_12","alias_value":"LZUVBTYJ3JFU","created_at":"2026-05-18T12:32:37.024351+00:00"},{"alias_kind":"pith_short_16","alias_value":"LZUVBTYJ3JFUKK7U","created_at":"2026-05-18T12:32:37.024351+00:00"},{"alias_kind":"pith_short_8","alias_value":"LZUVBTYJ","created_at":"2026-05-18T12:32:37.024351+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/LZUVBTYJ3JFUKK7U3VX4K4YQJH","json":"https://pith.science/pith/LZUVBTYJ3JFUKK7U3VX4K4YQJH.json","graph_json":"https://pith.science/api/pith-number/LZUVBTYJ3JFUKK7U3VX4K4YQJH/graph.json","events_json":"https://pith.science/api/pith-number/LZUVBTYJ3JFUKK7U3VX4K4YQJH/events.json","paper":"https://pith.science/paper/LZUVBTYJ"},"agent_actions":{"view_html":"https://pith.science/pith/LZUVBTYJ3JFUKK7U3VX4K4YQJH","download_json":"https://pith.science/pith/LZUVBTYJ3JFUKK7U3VX4K4YQJH.json","view_paper":"https://pith.science/paper/LZUVBTYJ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1803.01457&json=true","fetch_graph":"https://pith.science/api/pith-number/LZUVBTYJ3JFUKK7U3VX4K4YQJH/graph.json","fetch_events":"https://pith.science/api/pith-number/LZUVBTYJ3JFUKK7U3VX4K4YQJH/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/LZUVBTYJ3JFUKK7U3VX4K4YQJH/action/timestamp_anchor","attest_storage":"https://pith.science/pith/LZUVBTYJ3JFUKK7U3VX4K4YQJH/action/storage_attestation","attest_author":"https://pith.science/pith/LZUVBTYJ3JFUKK7U3VX4K4YQJH/action/author_attestation","sign_citation":"https://pith.science/pith/LZUVBTYJ3JFUKK7U3VX4K4YQJH/action/citation_signature","submit_replication":"https://pith.science/pith/LZUVBTYJ3JFUKK7U3VX4K4YQJH/action/replication_record"}},"created_at":"2026-05-18T00:22:00.630425+00:00","updated_at":"2026-05-18T00:22:00.630425+00:00"}