{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:GSH4AE2XMGR7DITSW5IU3TIBIB","short_pith_number":"pith:GSH4AE2X","schema_version":"1.0","canonical_sha256":"348fc0135761a3f1a272b7514dcd014044231b9d453ae68123c20e56d08351e8","source":{"kind":"arxiv","id":"2503.13016","version":1},"attestation_state":"computed","paper":{"title":"Efficient Motion-Aware Video MLLM","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Bingning Wang, Haoyu Lu, Jing Liu, Longteng Guo, Tongtian Yue, Weipeng Chen, Yuqi Huo, Zijia Zhao","submitted_at":"2025-03-17T10:20:05Z","abstract_excerpt":"Most current video MLLMs rely on uniform frame sampling and image-level encoders, resulting in inefficient data processing and limited motion awareness. To address these challenges, we introduce EMA, an Efficient Motion-Aware video MLLM that utilizes compressed video structures as inputs. We propose a motion-aware GOP (Group of Pictures) encoder that fuses spatial and motion information within a GOP unit in the compressed video stream, generating compact, informative visual tokens. By integrating fewer but denser RGB frames with more but sparser motion vectors in this native slow-fast input ar"},"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":"2503.13016","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-03-17T10:20:05Z","cross_cats_sorted":[],"title_canon_sha256":"888f4a2edb0a0abbb1156b866b2d214df490aee8d29c6911668532f097b4f110","abstract_canon_sha256":"c44f490d8c580b7fc7efb3746684dde62b68b20b4322e16aa8ca30a0e7d91a0e"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:32:51.548010Z","signature_b64":"vUvH5nNeO5gKnMnl8HvEQR050h7RcKFNSavEVU0Wk57G8jP1EeTrY1fIdd3YFyGPSM9fP9Ogp3foiRKX9GgEDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"348fc0135761a3f1a272b7514dcd014044231b9d453ae68123c20e56d08351e8","last_reissued_at":"2026-07-05T10:32:51.547525Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:32:51.547525Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Efficient Motion-Aware Video MLLM","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Bingning Wang, Haoyu Lu, Jing Liu, Longteng Guo, Tongtian Yue, Weipeng Chen, Yuqi Huo, Zijia Zhao","submitted_at":"2025-03-17T10:20:05Z","abstract_excerpt":"Most current video MLLMs rely on uniform frame sampling and image-level encoders, resulting in inefficient data processing and limited motion awareness. To address these challenges, we introduce EMA, an Efficient Motion-Aware video MLLM that utilizes compressed video structures as inputs. We propose a motion-aware GOP (Group of Pictures) encoder that fuses spatial and motion information within a GOP unit in the compressed video stream, generating compact, informative visual tokens. By integrating fewer but denser RGB frames with more but sparser motion vectors in this native slow-fast input ar"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2503.13016","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/2503.13016/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":"2503.13016","created_at":"2026-07-05T10:32:51.547584+00:00"},{"alias_kind":"arxiv_version","alias_value":"2503.13016v1","created_at":"2026-07-05T10:32:51.547584+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2503.13016","created_at":"2026-07-05T10:32:51.547584+00:00"},{"alias_kind":"pith_short_12","alias_value":"GSH4AE2XMGR7","created_at":"2026-07-05T10:32:51.547584+00:00"},{"alias_kind":"pith_short_16","alias_value":"GSH4AE2XMGR7DITS","created_at":"2026-07-05T10:32:51.547584+00:00"},{"alias_kind":"pith_short_8","alias_value":"GSH4AE2X","created_at":"2026-07-05T10:32:51.547584+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/GSH4AE2XMGR7DITSW5IU3TIBIB","json":"https://pith.science/pith/GSH4AE2XMGR7DITSW5IU3TIBIB.json","graph_json":"https://pith.science/api/pith-number/GSH4AE2XMGR7DITSW5IU3TIBIB/graph.json","events_json":"https://pith.science/api/pith-number/GSH4AE2XMGR7DITSW5IU3TIBIB/events.json","paper":"https://pith.science/paper/GSH4AE2X"},"agent_actions":{"view_html":"https://pith.science/pith/GSH4AE2XMGR7DITSW5IU3TIBIB","download_json":"https://pith.science/pith/GSH4AE2XMGR7DITSW5IU3TIBIB.json","view_paper":"https://pith.science/paper/GSH4AE2X","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2503.13016&json=true","fetch_graph":"https://pith.science/api/pith-number/GSH4AE2XMGR7DITSW5IU3TIBIB/graph.json","fetch_events":"https://pith.science/api/pith-number/GSH4AE2XMGR7DITSW5IU3TIBIB/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/GSH4AE2XMGR7DITSW5IU3TIBIB/action/timestamp_anchor","attest_storage":"https://pith.science/pith/GSH4AE2XMGR7DITSW5IU3TIBIB/action/storage_attestation","attest_author":"https://pith.science/pith/GSH4AE2XMGR7DITSW5IU3TIBIB/action/author_attestation","sign_citation":"https://pith.science/pith/GSH4AE2XMGR7DITSW5IU3TIBIB/action/citation_signature","submit_replication":"https://pith.science/pith/GSH4AE2XMGR7DITSW5IU3TIBIB/action/replication_record"}},"created_at":"2026-07-05T10:32:51.547584+00:00","updated_at":"2026-07-05T10:32:51.547584+00:00"}