{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:XMQKP4OZQ7SDOEEDYD3ZO4YU2C","short_pith_number":"pith:XMQKP4OZ","schema_version":"1.0","canonical_sha256":"bb20a7f1d987e4371083c0f7977314d0b7c83fd009c3ed260e2f3db9b9db7069","source":{"kind":"arxiv","id":"2504.02286","version":1},"attestation_state":"computed","paper":{"title":"Moment Quantization for Video Temporal Grounding","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Gang Hua, Kun Xia, Le Wang, Liushuai Shi, Mengnan Liu, Sanping Zhou, Xiaolong Sun, Yabing Wang","submitted_at":"2025-04-03T05:21:14Z","abstract_excerpt":"Video temporal grounding is a critical video understanding task, which aims to localize moments relevant to a language description. The challenge of this task lies in distinguishing relevant and irrelevant moments. Previous methods focused on learning continuous features exhibit weak differentiation between foreground and background features. In this paper, we propose a novel Moment-Quantization based Video Temporal Grounding method (MQVTG), which quantizes the input video into various discrete vectors to enhance the discrimination between relevant and irrelevant moments. Specifically, MQVTG m"},"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":"2504.02286","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-04-03T05:21:14Z","cross_cats_sorted":[],"title_canon_sha256":"8c2da7ffee6344e8902e18f0a4be857dc86615a62ef67babda500490463eb31c","abstract_canon_sha256":"f57c42f8c3ed096f2fdf0f9520dc61f96f642305fba8c6b1d23969622bd4bbba"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:43:54.144493Z","signature_b64":"0XpSJKbnc3uGadT173pTrqHwM1CkkraeZVl4eBrJFmqmBTAmixeFhzAQ0xMptbJkNgxpGqHUpxceZKIxcP6iAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"bb20a7f1d987e4371083c0f7977314d0b7c83fd009c3ed260e2f3db9b9db7069","last_reissued_at":"2026-07-05T10:43:54.143957Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:43:54.143957Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Moment Quantization for Video Temporal Grounding","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Gang Hua, Kun Xia, Le Wang, Liushuai Shi, Mengnan Liu, Sanping Zhou, Xiaolong Sun, Yabing Wang","submitted_at":"2025-04-03T05:21:14Z","abstract_excerpt":"Video temporal grounding is a critical video understanding task, which aims to localize moments relevant to a language description. The challenge of this task lies in distinguishing relevant and irrelevant moments. Previous methods focused on learning continuous features exhibit weak differentiation between foreground and background features. In this paper, we propose a novel Moment-Quantization based Video Temporal Grounding method (MQVTG), which quantizes the input video into various discrete vectors to enhance the discrimination between relevant and irrelevant moments. Specifically, MQVTG m"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2504.02286","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/2504.02286/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":"2504.02286","created_at":"2026-07-05T10:43:54.144024+00:00"},{"alias_kind":"arxiv_version","alias_value":"2504.02286v1","created_at":"2026-07-05T10:43:54.144024+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2504.02286","created_at":"2026-07-05T10:43:54.144024+00:00"},{"alias_kind":"pith_short_12","alias_value":"XMQKP4OZQ7SD","created_at":"2026-07-05T10:43:54.144024+00:00"},{"alias_kind":"pith_short_16","alias_value":"XMQKP4OZQ7SDOEED","created_at":"2026-07-05T10:43:54.144024+00:00"},{"alias_kind":"pith_short_8","alias_value":"XMQKP4OZ","created_at":"2026-07-05T10:43:54.144024+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/XMQKP4OZQ7SDOEEDYD3ZO4YU2C","json":"https://pith.science/pith/XMQKP4OZQ7SDOEEDYD3ZO4YU2C.json","graph_json":"https://pith.science/api/pith-number/XMQKP4OZQ7SDOEEDYD3ZO4YU2C/graph.json","events_json":"https://pith.science/api/pith-number/XMQKP4OZQ7SDOEEDYD3ZO4YU2C/events.json","paper":"https://pith.science/paper/XMQKP4OZ"},"agent_actions":{"view_html":"https://pith.science/pith/XMQKP4OZQ7SDOEEDYD3ZO4YU2C","download_json":"https://pith.science/pith/XMQKP4OZQ7SDOEEDYD3ZO4YU2C.json","view_paper":"https://pith.science/paper/XMQKP4OZ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2504.02286&json=true","fetch_graph":"https://pith.science/api/pith-number/XMQKP4OZQ7SDOEEDYD3ZO4YU2C/graph.json","fetch_events":"https://pith.science/api/pith-number/XMQKP4OZQ7SDOEEDYD3ZO4YU2C/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/XMQKP4OZQ7SDOEEDYD3ZO4YU2C/action/timestamp_anchor","attest_storage":"https://pith.science/pith/XMQKP4OZQ7SDOEEDYD3ZO4YU2C/action/storage_attestation","attest_author":"https://pith.science/pith/XMQKP4OZQ7SDOEEDYD3ZO4YU2C/action/author_attestation","sign_citation":"https://pith.science/pith/XMQKP4OZQ7SDOEEDYD3ZO4YU2C/action/citation_signature","submit_replication":"https://pith.science/pith/XMQKP4OZQ7SDOEEDYD3ZO4YU2C/action/replication_record"}},"created_at":"2026-07-05T10:43:54.144024+00:00","updated_at":"2026-07-05T10:43:54.144024+00:00"}