{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2020:XR7QCPU777GKSWTWHV47QSU7CX","short_pith_number":"pith:XR7QCPU7","schema_version":"1.0","canonical_sha256":"bc7f013e9fffcca95a763d79f84a9f15f6b86f32ad9e109636d7704c8c9ce484","source":{"kind":"arxiv","id":"2001.09308","version":1},"attestation_state":"computed","paper":{"title":"Look Closer to Ground Better: Weakly-Supervised Temporal Grounding of Sentence in Video","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Kwan-Yee K. Wong, Lin Ma, Peng Tang, Wenhan Luo, Zhenfang Chen","submitted_at":"2020-01-25T13:07:43Z","abstract_excerpt":"In this paper, we study the problem of weakly-supervised temporal grounding of sentence in video. Specifically, given an untrimmed video and a query sentence, our goal is to localize a temporal segment in the video that semantically corresponds to the query sentence, with no reliance on any temporal annotation during training. We propose a two-stage model to tackle this problem in a coarse-to-fine manner. In the coarse stage, we first generate a set of fixed-length temporal proposals using multi-scale sliding windows, and match their visual features against the sentence features to identify th"},"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":"2001.09308","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2020-01-25T13:07:43Z","cross_cats_sorted":[],"title_canon_sha256":"0c0a383b312398b50bcf537b61e91201d5d32b21e1ce2cac1bd8ded5a8817c25","abstract_canon_sha256":"4ea35f8fec41ed349b544ccaf61b946a8a12f3394d2a7f6e9027641de4678457"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T00:35:58.205502Z","signature_b64":"vFsvDq1hADc/qPIPlIXUxfOs61R+fvo4mPps0d0gd/pYMML5HXps2j2cMFlis4dBTKsyHqbCxuCqol/hlWI0BQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"bc7f013e9fffcca95a763d79f84a9f15f6b86f32ad9e109636d7704c8c9ce484","last_reissued_at":"2026-07-05T00:35:58.205082Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T00:35:58.205082Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Look Closer to Ground Better: Weakly-Supervised Temporal Grounding of Sentence in Video","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Kwan-Yee K. Wong, Lin Ma, Peng Tang, Wenhan Luo, Zhenfang Chen","submitted_at":"2020-01-25T13:07:43Z","abstract_excerpt":"In this paper, we study the problem of weakly-supervised temporal grounding of sentence in video. Specifically, given an untrimmed video and a query sentence, our goal is to localize a temporal segment in the video that semantically corresponds to the query sentence, with no reliance on any temporal annotation during training. We propose a two-stage model to tackle this problem in a coarse-to-fine manner. In the coarse stage, we first generate a set of fixed-length temporal proposals using multi-scale sliding windows, and match their visual features against the sentence features to identify th"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2001.09308","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/2001.09308/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":"2001.09308","created_at":"2026-07-05T00:35:58.205139+00:00"},{"alias_kind":"arxiv_version","alias_value":"2001.09308v1","created_at":"2026-07-05T00:35:58.205139+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2001.09308","created_at":"2026-07-05T00:35:58.205139+00:00"},{"alias_kind":"pith_short_12","alias_value":"XR7QCPU777GK","created_at":"2026-07-05T00:35:58.205139+00:00"},{"alias_kind":"pith_short_16","alias_value":"XR7QCPU777GKSWTW","created_at":"2026-07-05T00:35:58.205139+00:00"},{"alias_kind":"pith_short_8","alias_value":"XR7QCPU7","created_at":"2026-07-05T00:35:58.205139+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":3,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.14838","citing_title":"Multi-proposal Collaboration and Multi-task Training for Weakly-supervised Video Moment Retrieval","ref_index":25,"is_internal_anchor":false},{"citing_arxiv_id":"2605.26441","citing_title":"Rethinking Weakly-supervised Video Temporal Grounding From a Game Perspective","ref_index":12,"is_internal_anchor":false},{"citing_arxiv_id":"2605.29812","citing_title":"Not All Inputs Are Valid: Towards Open-Set Video Moment Retrieval Using Language","ref_index":9,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/XR7QCPU777GKSWTWHV47QSU7CX","json":"https://pith.science/pith/XR7QCPU777GKSWTWHV47QSU7CX.json","graph_json":"https://pith.science/api/pith-number/XR7QCPU777GKSWTWHV47QSU7CX/graph.json","events_json":"https://pith.science/api/pith-number/XR7QCPU777GKSWTWHV47QSU7CX/events.json","paper":"https://pith.science/paper/XR7QCPU7"},"agent_actions":{"view_html":"https://pith.science/pith/XR7QCPU777GKSWTWHV47QSU7CX","download_json":"https://pith.science/pith/XR7QCPU777GKSWTWHV47QSU7CX.json","view_paper":"https://pith.science/paper/XR7QCPU7","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2001.09308&json=true","fetch_graph":"https://pith.science/api/pith-number/XR7QCPU777GKSWTWHV47QSU7CX/graph.json","fetch_events":"https://pith.science/api/pith-number/XR7QCPU777GKSWTWHV47QSU7CX/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/XR7QCPU777GKSWTWHV47QSU7CX/action/timestamp_anchor","attest_storage":"https://pith.science/pith/XR7QCPU777GKSWTWHV47QSU7CX/action/storage_attestation","attest_author":"https://pith.science/pith/XR7QCPU777GKSWTWHV47QSU7CX/action/author_attestation","sign_citation":"https://pith.science/pith/XR7QCPU777GKSWTWHV47QSU7CX/action/citation_signature","submit_replication":"https://pith.science/pith/XR7QCPU777GKSWTWHV47QSU7CX/action/replication_record"}},"created_at":"2026-07-05T00:35:58.205139+00:00","updated_at":"2026-07-05T00:35:58.205139+00:00"}