{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:3Z3LKA2CQ5KGSREWPE2FGY6OJS","short_pith_number":"pith:3Z3LKA2C","schema_version":"1.0","canonical_sha256":"de76b50342875469449679345363ce4cb042e1244d79cc750246c97e439dc9b6","source":{"kind":"arxiv","id":"2507.07744","version":1},"attestation_state":"computed","paper":{"title":"Sparse-Dense Side-Tuner for efficient Video Temporal Grounding","license":"http://creativecommons.org/publicdomain/zero/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Albert Clap\\'es, David Pujol-Perich, Sergio Escalera","submitted_at":"2025-07-10T13:23:41Z","abstract_excerpt":"Video Temporal Grounding (VTG) involves Moment Retrieval (MR) and Highlight Detection (HD) based on textual queries. For this, most methods rely solely on final-layer features of frozen large pre-trained backbones, limiting their adaptability to new domains. While full fine-tuning is often impractical, parameter-efficient fine-tuning -- and particularly side-tuning (ST) -- has emerged as an effective alternative. However, prior ST approaches this problem from a frame-level refinement perspective, overlooking the inherent sparse nature of MR. To address this, we propose the Sparse-Dense Side-Tu"},"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":"2507.07744","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/publicdomain/zero/1.0/","primary_cat":"cs.CV","submitted_at":"2025-07-10T13:23:41Z","cross_cats_sorted":[],"title_canon_sha256":"370e334b9918976ace35d885c9cd12af152f62ae3a53f41d79a2c8773fc4bccc","abstract_canon_sha256":"e9903d44780402ca06bcdd9c07a2f6d8242cf1e4bec581430a570ce6da41beda"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:35:04.376131Z","signature_b64":"6af0rsXi/tv68zX9Pczf7tSHM3XWyTLKiMwol/YNbIW/CqjdFqXI7W6zRkOqAUIDnUmXFRH+3NOIlh1ySlA2AA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"de76b50342875469449679345363ce4cb042e1244d79cc750246c97e439dc9b6","last_reissued_at":"2026-07-05T11:35:04.375681Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:35:04.375681Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Sparse-Dense Side-Tuner for efficient Video Temporal Grounding","license":"http://creativecommons.org/publicdomain/zero/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Albert Clap\\'es, David Pujol-Perich, Sergio Escalera","submitted_at":"2025-07-10T13:23:41Z","abstract_excerpt":"Video Temporal Grounding (VTG) involves Moment Retrieval (MR) and Highlight Detection (HD) based on textual queries. For this, most methods rely solely on final-layer features of frozen large pre-trained backbones, limiting their adaptability to new domains. While full fine-tuning is often impractical, parameter-efficient fine-tuning -- and particularly side-tuning (ST) -- has emerged as an effective alternative. However, prior ST approaches this problem from a frame-level refinement perspective, overlooking the inherent sparse nature of MR. To address this, we propose the Sparse-Dense Side-Tu"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2507.07744","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/2507.07744/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":"2507.07744","created_at":"2026-07-05T11:35:04.375738+00:00"},{"alias_kind":"arxiv_version","alias_value":"2507.07744v1","created_at":"2026-07-05T11:35:04.375738+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2507.07744","created_at":"2026-07-05T11:35:04.375738+00:00"},{"alias_kind":"pith_short_12","alias_value":"3Z3LKA2CQ5KG","created_at":"2026-07-05T11:35:04.375738+00:00"},{"alias_kind":"pith_short_16","alias_value":"3Z3LKA2CQ5KGSREW","created_at":"2026-07-05T11:35:04.375738+00:00"},{"alias_kind":"pith_short_8","alias_value":"3Z3LKA2C","created_at":"2026-07-05T11:35:04.375738+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/3Z3LKA2CQ5KGSREWPE2FGY6OJS","json":"https://pith.science/pith/3Z3LKA2CQ5KGSREWPE2FGY6OJS.json","graph_json":"https://pith.science/api/pith-number/3Z3LKA2CQ5KGSREWPE2FGY6OJS/graph.json","events_json":"https://pith.science/api/pith-number/3Z3LKA2CQ5KGSREWPE2FGY6OJS/events.json","paper":"https://pith.science/paper/3Z3LKA2C"},"agent_actions":{"view_html":"https://pith.science/pith/3Z3LKA2CQ5KGSREWPE2FGY6OJS","download_json":"https://pith.science/pith/3Z3LKA2CQ5KGSREWPE2FGY6OJS.json","view_paper":"https://pith.science/paper/3Z3LKA2C","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2507.07744&json=true","fetch_graph":"https://pith.science/api/pith-number/3Z3LKA2CQ5KGSREWPE2FGY6OJS/graph.json","fetch_events":"https://pith.science/api/pith-number/3Z3LKA2CQ5KGSREWPE2FGY6OJS/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/3Z3LKA2CQ5KGSREWPE2FGY6OJS/action/timestamp_anchor","attest_storage":"https://pith.science/pith/3Z3LKA2CQ5KGSREWPE2FGY6OJS/action/storage_attestation","attest_author":"https://pith.science/pith/3Z3LKA2CQ5KGSREWPE2FGY6OJS/action/author_attestation","sign_citation":"https://pith.science/pith/3Z3LKA2CQ5KGSREWPE2FGY6OJS/action/citation_signature","submit_replication":"https://pith.science/pith/3Z3LKA2CQ5KGSREWPE2FGY6OJS/action/replication_record"}},"created_at":"2026-07-05T11:35:04.375738+00:00","updated_at":"2026-07-05T11:35:04.375738+00:00"}