{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:F7WZ5ZHMBTSED2JAV6YZ4CSUEX","short_pith_number":"pith:F7WZ5ZHM","schema_version":"1.0","canonical_sha256":"2fed9ee4ec0ce441e920afb19e0a5425f207ab61e10c3c460333443109de1628","source":{"kind":"arxiv","id":"2311.13435","version":2},"attestation_state":"computed","paper":{"title":"PG-Video-LLaVA: Pixel Grounding Large Video-Language Models","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CV","authors_text":"Fahad Khan, Hanoona Abdul Rasheed, Mubarak Shah, Muhammad Maaz, Rusiru Thushara, Salman Khan, Shehan Munasinghe","submitted_at":"2023-11-22T14:48:30Z","abstract_excerpt":"Extending image-based Large Multimodal Models (LMMs) to videos is challenging due to the inherent complexity of video data. The recent approaches extending image-based LMMs to videos either lack the grounding capabilities (e.g., VideoChat, Video-ChatGPT, Video-LLaMA) or do not utilize the audio-signals for better video understanding (e.g., Video-ChatGPT). Addressing these gaps, we propose PG-Video-LLaVA, the first LMM with pixel-level grounding capability, integrating audio cues by transcribing them into text to enrich video-context understanding. Our framework uses an off-the-shelf tracker an"},"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":"2311.13435","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2023-11-22T14:48:30Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"594f4229804c22d012495cf17cb8e14fc0ce00582ec6072864fdd3353e993f41","abstract_canon_sha256":"3b96b63731758ff4f330a10b853e50906d2e2dbd9f42f891bb0315ab7bebd944"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:23:50.222721Z","signature_b64":"gUQkNRrOb3fkeyxDSlBouNacmta1oZqcPWUBrgP2VCGz046ll9G1dHeiBN/MeEaotnbTobhF8KQb6pz6RygdDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"2fed9ee4ec0ce441e920afb19e0a5425f207ab61e10c3c460333443109de1628","last_reissued_at":"2026-07-05T07:23:50.222264Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:23:50.222264Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"PG-Video-LLaVA: Pixel Grounding Large Video-Language Models","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CV","authors_text":"Fahad Khan, Hanoona Abdul Rasheed, Mubarak Shah, Muhammad Maaz, Rusiru Thushara, Salman Khan, Shehan Munasinghe","submitted_at":"2023-11-22T14:48:30Z","abstract_excerpt":"Extending image-based Large Multimodal Models (LMMs) to videos is challenging due to the inherent complexity of video data. The recent approaches extending image-based LMMs to videos either lack the grounding capabilities (e.g., VideoChat, Video-ChatGPT, Video-LLaMA) or do not utilize the audio-signals for better video understanding (e.g., Video-ChatGPT). Addressing these gaps, we propose PG-Video-LLaVA, the first LMM with pixel-level grounding capability, integrating audio cues by transcribing them into text to enrich video-context understanding. Our framework uses an off-the-shelf tracker an"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2311.13435","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/2311.13435/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":"2311.13435","created_at":"2026-07-05T07:23:50.222322+00:00"},{"alias_kind":"arxiv_version","alias_value":"2311.13435v2","created_at":"2026-07-05T07:23:50.222322+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2311.13435","created_at":"2026-07-05T07:23:50.222322+00:00"},{"alias_kind":"pith_short_12","alias_value":"F7WZ5ZHMBTSE","created_at":"2026-07-05T07:23:50.222322+00:00"},{"alias_kind":"pith_short_16","alias_value":"F7WZ5ZHMBTSED2JA","created_at":"2026-07-05T07:23:50.222322+00:00"},{"alias_kind":"pith_short_8","alias_value":"F7WZ5ZHM","created_at":"2026-07-05T07:23:50.222322+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":5,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.00592","citing_title":"Through the PRISM: Principle-Aware, Interpretable, and Multi-Scale Evaluation of Visual Designs","ref_index":29,"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":69,"is_internal_anchor":false},{"citing_arxiv_id":"2604.23173","citing_title":"One Identity, Many Roles: Multimodal Entity Coreference for Enhanced Video Situation Recognition","ref_index":41,"is_internal_anchor":false},{"citing_arxiv_id":"2605.00891","citing_title":"X2SAM: Any Segmentation in Images and Videos","ref_index":67,"is_internal_anchor":false},{"citing_arxiv_id":"2604.11283","citing_title":"Multimodal Large Language Model-Enabled Video Translation: A Role-Oriented Survey","ref_index":62,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/F7WZ5ZHMBTSED2JAV6YZ4CSUEX","json":"https://pith.science/pith/F7WZ5ZHMBTSED2JAV6YZ4CSUEX.json","graph_json":"https://pith.science/api/pith-number/F7WZ5ZHMBTSED2JAV6YZ4CSUEX/graph.json","events_json":"https://pith.science/api/pith-number/F7WZ5ZHMBTSED2JAV6YZ4CSUEX/events.json","paper":"https://pith.science/paper/F7WZ5ZHM"},"agent_actions":{"view_html":"https://pith.science/pith/F7WZ5ZHMBTSED2JAV6YZ4CSUEX","download_json":"https://pith.science/pith/F7WZ5ZHMBTSED2JAV6YZ4CSUEX.json","view_paper":"https://pith.science/paper/F7WZ5ZHM","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2311.13435&json=true","fetch_graph":"https://pith.science/api/pith-number/F7WZ5ZHMBTSED2JAV6YZ4CSUEX/graph.json","fetch_events":"https://pith.science/api/pith-number/F7WZ5ZHMBTSED2JAV6YZ4CSUEX/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/F7WZ5ZHMBTSED2JAV6YZ4CSUEX/action/timestamp_anchor","attest_storage":"https://pith.science/pith/F7WZ5ZHMBTSED2JAV6YZ4CSUEX/action/storage_attestation","attest_author":"https://pith.science/pith/F7WZ5ZHMBTSED2JAV6YZ4CSUEX/action/author_attestation","sign_citation":"https://pith.science/pith/F7WZ5ZHMBTSED2JAV6YZ4CSUEX/action/citation_signature","submit_replication":"https://pith.science/pith/F7WZ5ZHMBTSED2JAV6YZ4CSUEX/action/replication_record"}},"created_at":"2026-07-05T07:23:50.222322+00:00","updated_at":"2026-07-05T07:23:50.222322+00:00"}