{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2019:6WSZAE5TA4CZIJ5345ZPXY5QE5","short_pith_number":"pith:6WSZAE5T","schema_version":"1.0","canonical_sha256":"f5a59013b307059427bbe772fbe3b027558e9666ffb065dd27780588583af5f2","source":{"kind":"arxiv","id":"1901.06829","version":1},"attestation_state":"computed","paper":{"title":"Read, Watch, and Move: Reinforcement Learning for Temporally Grounding Natural Language Descriptions in Videos","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Dongliang He, Fu Li, Jizhou Huang, Shilei Wen, Xiang Zhao, Xiao Liu","submitted_at":"2019-01-21T09:00:11Z","abstract_excerpt":"The task of video grounding, which temporally localizes a natural language description in a video, plays an important role in understanding videos. Existing studies have adopted strategies of sliding window over the entire video or exhaustively ranking all possible clip-sentence pairs in a pre-segmented video, which inevitably suffer from exhaustively enumerated candidates. To alleviate this problem, we formulate this task as a problem of sequential decision making by learning an agent which regulates the temporal grounding boundaries progressively based on its policy. Specifically, we propose"},"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":"1901.06829","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2019-01-21T09:00:11Z","cross_cats_sorted":[],"title_canon_sha256":"5899b9be485522e7174e24cb6aa8669696626695cee60bc6ae7a389c7ddfdffc","abstract_canon_sha256":"177d22cd0927554db09973845f2c41ac7f9fa0b5687c8f51d56f206cb19f266a"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:55:49.031193Z","signature_b64":"DOap0C0HiyzhiweRQiZI2O1Ddf6IvvC934VdzL+NIjnSY6h1UzGA4jQmN9iZ5PV4Cbo76J28NrPCZMD0Y1s2Cw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"f5a59013b307059427bbe772fbe3b027558e9666ffb065dd27780588583af5f2","last_reissued_at":"2026-05-17T23:55:49.030608Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:55:49.030608Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Read, Watch, and Move: Reinforcement Learning for Temporally Grounding Natural Language Descriptions in Videos","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Dongliang He, Fu Li, Jizhou Huang, Shilei Wen, Xiang Zhao, Xiao Liu","submitted_at":"2019-01-21T09:00:11Z","abstract_excerpt":"The task of video grounding, which temporally localizes a natural language description in a video, plays an important role in understanding videos. Existing studies have adopted strategies of sliding window over the entire video or exhaustively ranking all possible clip-sentence pairs in a pre-segmented video, which inevitably suffer from exhaustively enumerated candidates. To alleviate this problem, we formulate this task as a problem of sequential decision making by learning an agent which regulates the temporal grounding boundaries progressively based on its policy. Specifically, we propose"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1901.06829","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":"1901.06829","created_at":"2026-05-17T23:55:49.030699+00:00"},{"alias_kind":"arxiv_version","alias_value":"1901.06829v1","created_at":"2026-05-17T23:55:49.030699+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1901.06829","created_at":"2026-05-17T23:55:49.030699+00:00"},{"alias_kind":"pith_short_12","alias_value":"6WSZAE5TA4CZ","created_at":"2026-05-18T12:33:10.108867+00:00"},{"alias_kind":"pith_short_16","alias_value":"6WSZAE5TA4CZIJ53","created_at":"2026-05-18T12:33:10.108867+00:00"},{"alias_kind":"pith_short_8","alias_value":"6WSZAE5T","created_at":"2026-05-18T12:33:10.108867+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/6WSZAE5TA4CZIJ5345ZPXY5QE5","json":"https://pith.science/pith/6WSZAE5TA4CZIJ5345ZPXY5QE5.json","graph_json":"https://pith.science/api/pith-number/6WSZAE5TA4CZIJ5345ZPXY5QE5/graph.json","events_json":"https://pith.science/api/pith-number/6WSZAE5TA4CZIJ5345ZPXY5QE5/events.json","paper":"https://pith.science/paper/6WSZAE5T"},"agent_actions":{"view_html":"https://pith.science/pith/6WSZAE5TA4CZIJ5345ZPXY5QE5","download_json":"https://pith.science/pith/6WSZAE5TA4CZIJ5345ZPXY5QE5.json","view_paper":"https://pith.science/paper/6WSZAE5T","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1901.06829&json=true","fetch_graph":"https://pith.science/api/pith-number/6WSZAE5TA4CZIJ5345ZPXY5QE5/graph.json","fetch_events":"https://pith.science/api/pith-number/6WSZAE5TA4CZIJ5345ZPXY5QE5/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/6WSZAE5TA4CZIJ5345ZPXY5QE5/action/timestamp_anchor","attest_storage":"https://pith.science/pith/6WSZAE5TA4CZIJ5345ZPXY5QE5/action/storage_attestation","attest_author":"https://pith.science/pith/6WSZAE5TA4CZIJ5345ZPXY5QE5/action/author_attestation","sign_citation":"https://pith.science/pith/6WSZAE5TA4CZIJ5345ZPXY5QE5/action/citation_signature","submit_replication":"https://pith.science/pith/6WSZAE5TA4CZIJ5345ZPXY5QE5/action/replication_record"}},"created_at":"2026-05-17T23:55:49.030699+00:00","updated_at":"2026-05-17T23:55:49.030699+00:00"}