{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:557OFCM45FQYBLZYH2MRDA6JEC","short_pith_number":"pith:557OFCM4","schema_version":"1.0","canonical_sha256":"ef7ee2899ce96180af383e991183c920921ffae2de65898c3bec64a427f90f60","source":{"kind":"arxiv","id":"2209.10918","version":2},"attestation_state":"computed","paper":{"title":"CONE: An Efficient COarse-to-fiNE Alignment Framework for Long Video Temporal Grounding","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CL","cs.IR"],"primary_cat":"cs.CV","authors_text":"Chong-Wah Ngo, Difei Gao, Kun Yan, Lei Ji, Nan Duan, Wanjun Zhong, Wing-Kwong Chan, Zheng Shou, Zhijian Hou","submitted_at":"2022-09-22T10:58:42Z","abstract_excerpt":"This paper tackles an emerging and challenging problem of long video temporal grounding~(VTG) that localizes video moments related to a natural language (NL) query. Compared with short videos, long videos are also highly demanded but less explored, which brings new challenges in higher inference computation cost and weaker multi-modal alignment. To address these challenges, we propose CONE, an efficient COarse-to-fiNE alignment framework. CONE is a plug-and-play framework on top of existing VTG models to handle long videos through a sliding window mechanism. Specifically, CONE (1) introduces a"},"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":"2209.10918","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2022-09-22T10:58:42Z","cross_cats_sorted":["cs.CL","cs.IR"],"title_canon_sha256":"d413b66225de1b916a4502acbbd558e7c541743cc380ccd5f341cbdc8240df50","abstract_canon_sha256":"2c1d622c345444110347f4bc42b119e38ae138d38ab9279c38eacf3c72329a69"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:15:43.096808Z","signature_b64":"izfJdbX2HFIfJ9PETibDZN2rmifIpdVyVXoDqjk2rmrUL0KyEHZ9sbYOx5wghAHKti50aV1tJWyEFYTP/FvLAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"ef7ee2899ce96180af383e991183c920921ffae2de65898c3bec64a427f90f60","last_reissued_at":"2026-07-05T06:15:43.096241Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:15:43.096241Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"CONE: An Efficient COarse-to-fiNE Alignment Framework for Long Video Temporal Grounding","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CL","cs.IR"],"primary_cat":"cs.CV","authors_text":"Chong-Wah Ngo, Difei Gao, Kun Yan, Lei Ji, Nan Duan, Wanjun Zhong, Wing-Kwong Chan, Zheng Shou, Zhijian Hou","submitted_at":"2022-09-22T10:58:42Z","abstract_excerpt":"This paper tackles an emerging and challenging problem of long video temporal grounding~(VTG) that localizes video moments related to a natural language (NL) query. Compared with short videos, long videos are also highly demanded but less explored, which brings new challenges in higher inference computation cost and weaker multi-modal alignment. To address these challenges, we propose CONE, an efficient COarse-to-fiNE alignment framework. CONE is a plug-and-play framework on top of existing VTG models to handle long videos through a sliding window mechanism. Specifically, CONE (1) introduces a"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2209.10918","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/2209.10918/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":"2209.10918","created_at":"2026-07-05T06:15:43.096310+00:00"},{"alias_kind":"arxiv_version","alias_value":"2209.10918v2","created_at":"2026-07-05T06:15:43.096310+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2209.10918","created_at":"2026-07-05T06:15:43.096310+00:00"},{"alias_kind":"pith_short_12","alias_value":"557OFCM45FQY","created_at":"2026-07-05T06:15:43.096310+00:00"},{"alias_kind":"pith_short_16","alias_value":"557OFCM45FQYBLZY","created_at":"2026-07-05T06:15:43.096310+00:00"},{"alias_kind":"pith_short_8","alias_value":"557OFCM4","created_at":"2026-07-05T06:15:43.096310+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":4,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.09248","citing_title":"Temporal-Aware Reasoning Optimization for Video Temporal Grounding","ref_index":11,"is_internal_anchor":false},{"citing_arxiv_id":"2412.07157","citing_title":"Multi-Scale Contrastive Learning for Video Temporal Grounding","ref_index":20,"is_internal_anchor":false},{"citing_arxiv_id":"2604.25276","citing_title":"OmniVTG: A Large-Scale Dataset and Training Paradigm for Open-World Video Temporal Grounding","ref_index":10,"is_internal_anchor":false},{"citing_arxiv_id":"2604.08522","citing_title":"UniversalVTG: A Universal and Lightweight Foundation Model for Video Temporal Grounding","ref_index":19,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/557OFCM45FQYBLZYH2MRDA6JEC","json":"https://pith.science/pith/557OFCM45FQYBLZYH2MRDA6JEC.json","graph_json":"https://pith.science/api/pith-number/557OFCM45FQYBLZYH2MRDA6JEC/graph.json","events_json":"https://pith.science/api/pith-number/557OFCM45FQYBLZYH2MRDA6JEC/events.json","paper":"https://pith.science/paper/557OFCM4"},"agent_actions":{"view_html":"https://pith.science/pith/557OFCM45FQYBLZYH2MRDA6JEC","download_json":"https://pith.science/pith/557OFCM45FQYBLZYH2MRDA6JEC.json","view_paper":"https://pith.science/paper/557OFCM4","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2209.10918&json=true","fetch_graph":"https://pith.science/api/pith-number/557OFCM45FQYBLZYH2MRDA6JEC/graph.json","fetch_events":"https://pith.science/api/pith-number/557OFCM45FQYBLZYH2MRDA6JEC/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/557OFCM45FQYBLZYH2MRDA6JEC/action/timestamp_anchor","attest_storage":"https://pith.science/pith/557OFCM45FQYBLZYH2MRDA6JEC/action/storage_attestation","attest_author":"https://pith.science/pith/557OFCM45FQYBLZYH2MRDA6JEC/action/author_attestation","sign_citation":"https://pith.science/pith/557OFCM45FQYBLZYH2MRDA6JEC/action/citation_signature","submit_replication":"https://pith.science/pith/557OFCM45FQYBLZYH2MRDA6JEC/action/replication_record"}},"created_at":"2026-07-05T06:15:43.096310+00:00","updated_at":"2026-07-05T06:15:43.096310+00:00"}