{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:CREFTZATNSY6IPLRSNTXQGKZRG","short_pith_number":"pith:CREFTZAT","schema_version":"1.0","canonical_sha256":"144859e4136cb1e43d7193677819598994808a05512c438177c7db054466f6d7","source":{"kind":"arxiv","id":"2108.10576","version":1},"attestation_state":"computed","paper":{"title":"Support-Set Based Cross-Supervision for Video Grounding","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"De Cheng, Mingqian Tang, Nannan Wang, Shiwei Zhang, Xiaomeng Li, Xinbo Gao, Xinpeng Ding, Ziyuan Huang","submitted_at":"2021-08-24T08:25:26Z","abstract_excerpt":"Current approaches for video grounding propose kinds of complex architectures to capture the video-text relations, and have achieved impressive improvements. However, it is hard to learn the complicated multi-modal relations by only architecture designing in fact. In this paper, we introduce a novel Support-set Based Cross-Supervision (Sscs) module which can improve existing methods during training phase without extra inference cost. The proposed Sscs module contains two main components, i.e., discriminative contrastive objective and generative caption objective. The contrastive objective aims"},"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":"2108.10576","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2021-08-24T08:25:26Z","cross_cats_sorted":[],"title_canon_sha256":"531da6f938225649bd6a24e5dfe5b95b9208e8b818bc0b3b5dd71892556ba893","abstract_canon_sha256":"2115dbbc57a415fc56b8df715ad331fe0f49a818fbc7fd9f9e02297e6ec3d9ba"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T03:08:11.029915Z","signature_b64":"Kovl2w5DqPsmsKIBcqrZBuvkzoInrZeVVLI586jzHEwAmIsPMmv8qsu3GMeM6XbFrGZrRj7gbFTzPGtn+P/bDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"144859e4136cb1e43d7193677819598994808a05512c438177c7db054466f6d7","last_reissued_at":"2026-07-05T03:08:11.029531Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T03:08:11.029531Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Support-Set Based Cross-Supervision for Video Grounding","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"De Cheng, Mingqian Tang, Nannan Wang, Shiwei Zhang, Xiaomeng Li, Xinbo Gao, Xinpeng Ding, Ziyuan Huang","submitted_at":"2021-08-24T08:25:26Z","abstract_excerpt":"Current approaches for video grounding propose kinds of complex architectures to capture the video-text relations, and have achieved impressive improvements. However, it is hard to learn the complicated multi-modal relations by only architecture designing in fact. In this paper, we introduce a novel Support-set Based Cross-Supervision (Sscs) module which can improve existing methods during training phase without extra inference cost. The proposed Sscs module contains two main components, i.e., discriminative contrastive objective and generative caption objective. The contrastive objective aims"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2108.10576","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/2108.10576/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":"2108.10576","created_at":"2026-07-05T03:08:11.029586+00:00"},{"alias_kind":"arxiv_version","alias_value":"2108.10576v1","created_at":"2026-07-05T03:08:11.029586+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2108.10576","created_at":"2026-07-05T03:08:11.029586+00:00"},{"alias_kind":"pith_short_12","alias_value":"CREFTZATNSY6","created_at":"2026-07-05T03:08:11.029586+00:00"},{"alias_kind":"pith_short_16","alias_value":"CREFTZATNSY6IPLR","created_at":"2026-07-05T03:08:11.029586+00:00"},{"alias_kind":"pith_short_8","alias_value":"CREFTZAT","created_at":"2026-07-05T03:08:11.029586+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/CREFTZATNSY6IPLRSNTXQGKZRG","json":"https://pith.science/pith/CREFTZATNSY6IPLRSNTXQGKZRG.json","graph_json":"https://pith.science/api/pith-number/CREFTZATNSY6IPLRSNTXQGKZRG/graph.json","events_json":"https://pith.science/api/pith-number/CREFTZATNSY6IPLRSNTXQGKZRG/events.json","paper":"https://pith.science/paper/CREFTZAT"},"agent_actions":{"view_html":"https://pith.science/pith/CREFTZATNSY6IPLRSNTXQGKZRG","download_json":"https://pith.science/pith/CREFTZATNSY6IPLRSNTXQGKZRG.json","view_paper":"https://pith.science/paper/CREFTZAT","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2108.10576&json=true","fetch_graph":"https://pith.science/api/pith-number/CREFTZATNSY6IPLRSNTXQGKZRG/graph.json","fetch_events":"https://pith.science/api/pith-number/CREFTZATNSY6IPLRSNTXQGKZRG/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/CREFTZATNSY6IPLRSNTXQGKZRG/action/timestamp_anchor","attest_storage":"https://pith.science/pith/CREFTZATNSY6IPLRSNTXQGKZRG/action/storage_attestation","attest_author":"https://pith.science/pith/CREFTZATNSY6IPLRSNTXQGKZRG/action/author_attestation","sign_citation":"https://pith.science/pith/CREFTZATNSY6IPLRSNTXQGKZRG/action/citation_signature","submit_replication":"https://pith.science/pith/CREFTZATNSY6IPLRSNTXQGKZRG/action/replication_record"}},"created_at":"2026-07-05T03:08:11.029586+00:00","updated_at":"2026-07-05T03:08:11.029586+00:00"}