{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:7NROMR2TAA4OOLNVNNA7QPICND","short_pith_number":"pith:7NROMR2T","schema_version":"1.0","canonical_sha256":"fb62e647530038e72db56b41f83d0268f67808c8dbccc2b578e8d6a95f4dd731","source":{"kind":"arxiv","id":"2109.06398","version":1},"attestation_state":"computed","paper":{"title":"Adaptive Proposal Generation Network for Temporal Sentence Localization in Videos","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CL"],"primary_cat":"cs.CV","authors_text":"Daizong Liu, Jianfeng Dong, Pan Zhou, Xiaoye Qu","submitted_at":"2021-09-14T02:02:36Z","abstract_excerpt":"We address the problem of temporal sentence localization in videos (TSLV). Traditional methods follow a top-down framework which localizes the target segment with pre-defined segment proposals. Although they have achieved decent performance, the proposals are handcrafted and redundant. Recently, bottom-up framework attracts increasing attention due to its superior efficiency. It directly predicts the probabilities for each frame as a boundary. However, the performance of bottom-up model is inferior to the top-down counterpart as it fails to exploit the segment-level interaction. In this paper,"},"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":"2109.06398","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2021-09-14T02:02:36Z","cross_cats_sorted":["cs.CL"],"title_canon_sha256":"4aa30526589a379c46459c534b021f1ef8a165d8ae9a24153bffed50196ee6d0","abstract_canon_sha256":"096bd930b61862265966be8ac17e055a219c7f413a5255d3162fbb6bf481d99f"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T03:13:53.934064Z","signature_b64":"YbFYDTtKBkEVxFxYPcpgXwQ2w5sIWXgLknASKuBFaeUvdolP6tVI8CPe7ds8o+x8XyRRT4dbCXmTdel2H272Dw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"fb62e647530038e72db56b41f83d0268f67808c8dbccc2b578e8d6a95f4dd731","last_reissued_at":"2026-07-05T03:13:53.933604Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T03:13:53.933604Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Adaptive Proposal Generation Network for Temporal Sentence Localization in Videos","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CL"],"primary_cat":"cs.CV","authors_text":"Daizong Liu, Jianfeng Dong, Pan Zhou, Xiaoye Qu","submitted_at":"2021-09-14T02:02:36Z","abstract_excerpt":"We address the problem of temporal sentence localization in videos (TSLV). Traditional methods follow a top-down framework which localizes the target segment with pre-defined segment proposals. Although they have achieved decent performance, the proposals are handcrafted and redundant. Recently, bottom-up framework attracts increasing attention due to its superior efficiency. It directly predicts the probabilities for each frame as a boundary. However, the performance of bottom-up model is inferior to the top-down counterpart as it fails to exploit the segment-level interaction. In this paper,"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2109.06398","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":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2109.06398/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":"2109.06398","created_at":"2026-07-05T03:13:53.933660+00:00"},{"alias_kind":"arxiv_version","alias_value":"2109.06398v1","created_at":"2026-07-05T03:13:53.933660+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2109.06398","created_at":"2026-07-05T03:13:53.933660+00:00"},{"alias_kind":"pith_short_12","alias_value":"7NROMR2TAA4O","created_at":"2026-07-05T03:13:53.933660+00:00"},{"alias_kind":"pith_short_16","alias_value":"7NROMR2TAA4OOLNV","created_at":"2026-07-05T03:13:53.933660+00:00"},{"alias_kind":"pith_short_8","alias_value":"7NROMR2T","created_at":"2026-07-05T03:13:53.933660+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.30742","citing_title":"Annotations Are Not All You Need: A Cross-modal Knowledge Transfer Network for Unsupervised Temporal Sentence Grounding","ref_index":4,"is_internal_anchor":false},{"citing_arxiv_id":"2412.07157","citing_title":"Multi-Scale Contrastive Learning for Video Temporal Grounding","ref_index":34,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/7NROMR2TAA4OOLNVNNA7QPICND","json":"https://pith.science/pith/7NROMR2TAA4OOLNVNNA7QPICND.json","graph_json":"https://pith.science/api/pith-number/7NROMR2TAA4OOLNVNNA7QPICND/graph.json","events_json":"https://pith.science/api/pith-number/7NROMR2TAA4OOLNVNNA7QPICND/events.json","paper":"https://pith.science/paper/7NROMR2T"},"agent_actions":{"view_html":"https://pith.science/pith/7NROMR2TAA4OOLNVNNA7QPICND","download_json":"https://pith.science/pith/7NROMR2TAA4OOLNVNNA7QPICND.json","view_paper":"https://pith.science/paper/7NROMR2T","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2109.06398&json=true","fetch_graph":"https://pith.science/api/pith-number/7NROMR2TAA4OOLNVNNA7QPICND/graph.json","fetch_events":"https://pith.science/api/pith-number/7NROMR2TAA4OOLNVNNA7QPICND/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/7NROMR2TAA4OOLNVNNA7QPICND/action/timestamp_anchor","attest_storage":"https://pith.science/pith/7NROMR2TAA4OOLNVNNA7QPICND/action/storage_attestation","attest_author":"https://pith.science/pith/7NROMR2TAA4OOLNVNNA7QPICND/action/author_attestation","sign_citation":"https://pith.science/pith/7NROMR2TAA4OOLNVNNA7QPICND/action/citation_signature","submit_replication":"https://pith.science/pith/7NROMR2TAA4OOLNVNNA7QPICND/action/replication_record"}},"created_at":"2026-07-05T03:13:53.933660+00:00","updated_at":"2026-07-05T03:13:53.933660+00:00"}