{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:UQSPJI3FLHHWPUSHRLKZMEQOXU","short_pith_number":"pith:UQSPJI3F","schema_version":"1.0","canonical_sha256":"a424f4a36559cf67d2478ad596120ebd3fddb6c2d3f1b3dab805d995d202e91a","source":{"kind":"arxiv","id":"2403.16558","version":2},"attestation_state":"computed","paper":{"title":"Elysium: Exploring Object-level Perception in Videos via MLLM","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Can Huang, Han Wang, Yanjie Wang, YongJie Ye, Yuxiang Nie","submitted_at":"2024-03-25T09:17:15Z","abstract_excerpt":"Multi-modal Large Language Models (MLLMs) have demonstrated their ability to perceive objects in still images, but their application in video-related tasks, such as object tracking, remains understudied. This lack of exploration is primarily due to two key challenges. Firstly, extensive pretraining on large-scale video datasets is required to equip MLLMs with the capability to perceive objects across multiple frames and understand inter-frame relationships. Secondly, processing a large number of frames within the context window of Large Language Models (LLMs) can impose a significant computati"},"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":"2403.16558","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-03-25T09:17:15Z","cross_cats_sorted":[],"title_canon_sha256":"b15edd7179a49efb02d0666dbf6b42a53100f8fcbf5acece213e585286effa9e","abstract_canon_sha256":"af1d64da1f0494d7ba0b9b40562a52d32c76e5738a08f3d822eaf9fdef45436b"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:02:06.389917Z","signature_b64":"LRrMXuf+QCHu1bYaT90TGwCN5NrblV0FqdkqhA1i479s24YTkHMFySf+z+U2uhdip+vNdKZdUhZKD4TrKiumAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"a424f4a36559cf67d2478ad596120ebd3fddb6c2d3f1b3dab805d995d202e91a","last_reissued_at":"2026-07-05T08:02:06.389484Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:02:06.389484Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Elysium: Exploring Object-level Perception in Videos via MLLM","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Can Huang, Han Wang, Yanjie Wang, YongJie Ye, Yuxiang Nie","submitted_at":"2024-03-25T09:17:15Z","abstract_excerpt":"Multi-modal Large Language Models (MLLMs) have demonstrated their ability to perceive objects in still images, but their application in video-related tasks, such as object tracking, remains understudied. This lack of exploration is primarily due to two key challenges. Firstly, extensive pretraining on large-scale video datasets is required to equip MLLMs with the capability to perceive objects across multiple frames and understand inter-frame relationships. Secondly, processing a large number of frames within the context window of Large Language Models (LLMs) can impose a significant computati"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2403.16558","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/2403.16558/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":"2403.16558","created_at":"2026-07-05T08:02:06.389550+00:00"},{"alias_kind":"arxiv_version","alias_value":"2403.16558v2","created_at":"2026-07-05T08:02:06.389550+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2403.16558","created_at":"2026-07-05T08:02:06.389550+00:00"},{"alias_kind":"pith_short_12","alias_value":"UQSPJI3FLHHW","created_at":"2026-07-05T08:02:06.389550+00:00"},{"alias_kind":"pith_short_16","alias_value":"UQSPJI3FLHHWPUSH","created_at":"2026-07-05T08:02:06.389550+00:00"},{"alias_kind":"pith_short_8","alias_value":"UQSPJI3F","created_at":"2026-07-05T08:02:06.389550+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2608.00847","citing_title":"Models as Tools: An Agentic Coordination Framework for Unified Multimodal Visual Tracking","ref_index":43,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/UQSPJI3FLHHWPUSHRLKZMEQOXU","json":"https://pith.science/pith/UQSPJI3FLHHWPUSHRLKZMEQOXU.json","graph_json":"https://pith.science/api/pith-number/UQSPJI3FLHHWPUSHRLKZMEQOXU/graph.json","events_json":"https://pith.science/api/pith-number/UQSPJI3FLHHWPUSHRLKZMEQOXU/events.json","paper":"https://pith.science/paper/UQSPJI3F"},"agent_actions":{"view_html":"https://pith.science/pith/UQSPJI3FLHHWPUSHRLKZMEQOXU","download_json":"https://pith.science/pith/UQSPJI3FLHHWPUSHRLKZMEQOXU.json","view_paper":"https://pith.science/paper/UQSPJI3F","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2403.16558&json=true","fetch_graph":"https://pith.science/api/pith-number/UQSPJI3FLHHWPUSHRLKZMEQOXU/graph.json","fetch_events":"https://pith.science/api/pith-number/UQSPJI3FLHHWPUSHRLKZMEQOXU/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/UQSPJI3FLHHWPUSHRLKZMEQOXU/action/timestamp_anchor","attest_storage":"https://pith.science/pith/UQSPJI3FLHHWPUSHRLKZMEQOXU/action/storage_attestation","attest_author":"https://pith.science/pith/UQSPJI3FLHHWPUSHRLKZMEQOXU/action/author_attestation","sign_citation":"https://pith.science/pith/UQSPJI3FLHHWPUSHRLKZMEQOXU/action/citation_signature","submit_replication":"https://pith.science/pith/UQSPJI3FLHHWPUSHRLKZMEQOXU/action/replication_record"}},"created_at":"2026-07-05T08:02:06.389550+00:00","updated_at":"2026-07-05T08:02:06.389550+00:00"}