{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:SQ6LMZEVLZS74PRAXOLXEZLTZ5","short_pith_number":"pith:SQ6LMZEV","schema_version":"1.0","canonical_sha256":"943cb664955e65fe3e20bb97726573cf70a918b8aa0c88eff00221c4c4f7709a","source":{"kind":"arxiv","id":"2404.13400","version":2},"attestation_state":"computed","paper":{"title":"HiVG: Hierarchical Multimodal Fine-grained Modulation for Visual Grounding","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Changsheng Xu, Fang Peng, Linhui Xiao, Xiaoshan Yang, Yaowei Wang","submitted_at":"2024-04-20T14:57:31Z","abstract_excerpt":"Visual grounding, which aims to ground a visual region via natural language, is a task that heavily relies on cross-modal alignment. Existing works utilized uni-modal pre-trained models to transfer visual or linguistic knowledge separately while ignoring the multimodal corresponding information. Motivated by recent advancements in contrastive language-image pre-training and low-rank adaptation (LoRA) methods, we aim to solve the grounding task based on multimodal pre-training. However, there exists significant task gaps between pre-training and grounding. Therefore, to address these gaps, we p"},"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":"2404.13400","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-04-20T14:57:31Z","cross_cats_sorted":[],"title_canon_sha256":"739e37a30c3145a561b8c3a845e3a70fe940dad241101f9b411ea341419d5f3e","abstract_canon_sha256":"439ddef1b8241c121b85ffdc72ff582be1415379b898d1dc27eab5c62a0214e0"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:03:19.794955Z","signature_b64":"k1Bw7lXRNySTBL6hW1C4yHZEpAjH8elmt8c7dVAeVeGPUk3sVx1est79SQ0S9aRDCbix/5nXMX0SbZxJrVlPCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"943cb664955e65fe3e20bb97726573cf70a918b8aa0c88eff00221c4c4f7709a","last_reissued_at":"2026-07-05T09:03:19.794460Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:03:19.794460Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"HiVG: Hierarchical Multimodal Fine-grained Modulation for Visual Grounding","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Changsheng Xu, Fang Peng, Linhui Xiao, Xiaoshan Yang, Yaowei Wang","submitted_at":"2024-04-20T14:57:31Z","abstract_excerpt":"Visual grounding, which aims to ground a visual region via natural language, is a task that heavily relies on cross-modal alignment. Existing works utilized uni-modal pre-trained models to transfer visual or linguistic knowledge separately while ignoring the multimodal corresponding information. Motivated by recent advancements in contrastive language-image pre-training and low-rank adaptation (LoRA) methods, we aim to solve the grounding task based on multimodal pre-training. However, there exists significant task gaps between pre-training and grounding. Therefore, to address these gaps, we p"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2404.13400","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/2404.13400/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":"2404.13400","created_at":"2026-07-05T09:03:19.794525+00:00"},{"alias_kind":"arxiv_version","alias_value":"2404.13400v2","created_at":"2026-07-05T09:03:19.794525+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2404.13400","created_at":"2026-07-05T09:03:19.794525+00:00"},{"alias_kind":"pith_short_12","alias_value":"SQ6LMZEVLZS7","created_at":"2026-07-05T09:03:19.794525+00:00"},{"alias_kind":"pith_short_16","alias_value":"SQ6LMZEVLZS74PRA","created_at":"2026-07-05T09:03:19.794525+00:00"},{"alias_kind":"pith_short_8","alias_value":"SQ6LMZEV","created_at":"2026-07-05T09:03:19.794525+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/SQ6LMZEVLZS74PRAXOLXEZLTZ5","json":"https://pith.science/pith/SQ6LMZEVLZS74PRAXOLXEZLTZ5.json","graph_json":"https://pith.science/api/pith-number/SQ6LMZEVLZS74PRAXOLXEZLTZ5/graph.json","events_json":"https://pith.science/api/pith-number/SQ6LMZEVLZS74PRAXOLXEZLTZ5/events.json","paper":"https://pith.science/paper/SQ6LMZEV"},"agent_actions":{"view_html":"https://pith.science/pith/SQ6LMZEVLZS74PRAXOLXEZLTZ5","download_json":"https://pith.science/pith/SQ6LMZEVLZS74PRAXOLXEZLTZ5.json","view_paper":"https://pith.science/paper/SQ6LMZEV","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2404.13400&json=true","fetch_graph":"https://pith.science/api/pith-number/SQ6LMZEVLZS74PRAXOLXEZLTZ5/graph.json","fetch_events":"https://pith.science/api/pith-number/SQ6LMZEVLZS74PRAXOLXEZLTZ5/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/SQ6LMZEVLZS74PRAXOLXEZLTZ5/action/timestamp_anchor","attest_storage":"https://pith.science/pith/SQ6LMZEVLZS74PRAXOLXEZLTZ5/action/storage_attestation","attest_author":"https://pith.science/pith/SQ6LMZEVLZS74PRAXOLXEZLTZ5/action/author_attestation","sign_citation":"https://pith.science/pith/SQ6LMZEVLZS74PRAXOLXEZLTZ5/action/citation_signature","submit_replication":"https://pith.science/pith/SQ6LMZEVLZS74PRAXOLXEZLTZ5/action/replication_record"}},"created_at":"2026-07-05T09:03:19.794525+00:00","updated_at":"2026-07-05T09:03:19.794525+00:00"}