{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:U73BM72ZIBWZC2YQHBTDVO54KZ","short_pith_number":"pith:U73BM72Z","schema_version":"1.0","canonical_sha256":"a7f6167f59406d916b1038663abbbc566dab737790d72299bcad3138ba227d42","source":{"kind":"arxiv","id":"2411.04923","version":3},"attestation_state":"computed","paper":{"title":"VideoGLaMM: A Large Multimodal Model for Pixel-Level Visual Grounding in Videos","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Eric Xing, Fahad Shahbaz Khan, Hanan Gani, Jiale Cao, Salman Khan, Shehan Munasinghe, Wenqi Zhu","submitted_at":"2024-11-07T17:59:27Z","abstract_excerpt":"Fine-grained alignment between videos and text is challenging due to complex spatial and temporal dynamics in videos. Existing video-based Large Multimodal Models (LMMs) handle basic conversations but struggle with precise pixel-level grounding in videos. To address this, we introduce VideoGLaMM, a LMM designed for fine-grained pixel-level grounding in videos based on user-provided textual inputs. Our design seamlessly connects three key components: a Large Language Model, a dual vision encoder that emphasizes both spatial and temporal details, and a spatio-temporal decoder for accurate mask g"},"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":"2411.04923","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2024-11-07T17:59:27Z","cross_cats_sorted":[],"title_canon_sha256":"770949bd7137bb3fbba2b25ad901328a8086b5c4886d2cbad8a6130fa9d2661e","abstract_canon_sha256":"4c34e8c0eb212c7a064ad74201a8df673fbd1520a0c4d3602559233b8f4cde3e"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:38:37.748790Z","signature_b64":"cZ9DoNShjd1Ts6geICi2LaDteu8v08fX1ROrV6x2s6DTZ/hkVGpEfeAZNULNAULzaFUWmocTIOQOOZhRYKXZBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"a7f6167f59406d916b1038663abbbc566dab737790d72299bcad3138ba227d42","last_reissued_at":"2026-07-05T10:38:37.748205Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:38:37.748205Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"VideoGLaMM: A Large Multimodal Model for Pixel-Level Visual Grounding in Videos","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Eric Xing, Fahad Shahbaz Khan, Hanan Gani, Jiale Cao, Salman Khan, Shehan Munasinghe, Wenqi Zhu","submitted_at":"2024-11-07T17:59:27Z","abstract_excerpt":"Fine-grained alignment between videos and text is challenging due to complex spatial and temporal dynamics in videos. Existing video-based Large Multimodal Models (LMMs) handle basic conversations but struggle with precise pixel-level grounding in videos. To address this, we introduce VideoGLaMM, a LMM designed for fine-grained pixel-level grounding in videos based on user-provided textual inputs. Our design seamlessly connects three key components: a Large Language Model, a dual vision encoder that emphasizes both spatial and temporal details, and a spatio-temporal decoder for accurate mask g"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2411.04923","kind":"arxiv","version":3},"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/2411.04923/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":"2411.04923","created_at":"2026-07-05T10:38:37.748275+00:00"},{"alias_kind":"arxiv_version","alias_value":"2411.04923v3","created_at":"2026-07-05T10:38:37.748275+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2411.04923","created_at":"2026-07-05T10:38:37.748275+00:00"},{"alias_kind":"pith_short_12","alias_value":"U73BM72ZIBWZ","created_at":"2026-07-05T10:38:37.748275+00:00"},{"alias_kind":"pith_short_16","alias_value":"U73BM72ZIBWZC2YQ","created_at":"2026-07-05T10:38:37.748275+00:00"},{"alias_kind":"pith_short_8","alias_value":"U73BM72Z","created_at":"2026-07-05T10:38:37.748275+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":3,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.05259","citing_title":"VideoKR: Towards Knowledge- and Reasoning-Intensive Video Understanding","ref_index":8,"is_internal_anchor":false},{"citing_arxiv_id":"2605.22558","citing_title":"GeoWeaver: Grounding Visual Tokens with Geometric Evidence before Scene Reasoning","ref_index":36,"is_internal_anchor":false},{"citing_arxiv_id":"2501.04001","citing_title":"Sa2VA: Marrying SAM2 with LLaVA for Dense Grounded Understanding of Images and Videos","ref_index":70,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/U73BM72ZIBWZC2YQHBTDVO54KZ","json":"https://pith.science/pith/U73BM72ZIBWZC2YQHBTDVO54KZ.json","graph_json":"https://pith.science/api/pith-number/U73BM72ZIBWZC2YQHBTDVO54KZ/graph.json","events_json":"https://pith.science/api/pith-number/U73BM72ZIBWZC2YQHBTDVO54KZ/events.json","paper":"https://pith.science/paper/U73BM72Z"},"agent_actions":{"view_html":"https://pith.science/pith/U73BM72ZIBWZC2YQHBTDVO54KZ","download_json":"https://pith.science/pith/U73BM72ZIBWZC2YQHBTDVO54KZ.json","view_paper":"https://pith.science/paper/U73BM72Z","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2411.04923&json=true","fetch_graph":"https://pith.science/api/pith-number/U73BM72ZIBWZC2YQHBTDVO54KZ/graph.json","fetch_events":"https://pith.science/api/pith-number/U73BM72ZIBWZC2YQHBTDVO54KZ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/U73BM72ZIBWZC2YQHBTDVO54KZ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/U73BM72ZIBWZC2YQHBTDVO54KZ/action/storage_attestation","attest_author":"https://pith.science/pith/U73BM72ZIBWZC2YQHBTDVO54KZ/action/author_attestation","sign_citation":"https://pith.science/pith/U73BM72ZIBWZC2YQHBTDVO54KZ/action/citation_signature","submit_replication":"https://pith.science/pith/U73BM72ZIBWZC2YQHBTDVO54KZ/action/replication_record"}},"created_at":"2026-07-05T10:38:37.748275+00:00","updated_at":"2026-07-05T10:38:37.748275+00:00"}