{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:LIRSIX3IZPRNHBY4S7EWUUHXFZ","short_pith_number":"pith:LIRSIX3I","schema_version":"1.0","canonical_sha256":"5a23245f68cbe2d3871c97c96a50f72e666a1b9a2a7ca3dda1666b4259c15153","source":{"kind":"arxiv","id":"2410.10589","version":1},"attestation_state":"computed","paper":{"title":"MoTE: Reconciling Generalization with Specialization for Visual-Language to Video Knowledge Transfer","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Chengju Liu, Mengxian Hu, Minghao Zhu, Qijun Chen, Ronghao Dang, Xiao Lin, Xun Zhou, Zhengpu Wang","submitted_at":"2024-10-14T15:00:55Z","abstract_excerpt":"Transferring visual-language knowledge from large-scale foundation models for video recognition has proved to be effective. To bridge the domain gap, additional parametric modules are added to capture the temporal information. However, zero-shot generalization diminishes with the increase in the number of specialized parameters, making existing works a trade-off between zero-shot and close-set performance. In this paper, we present MoTE, a novel framework that enables generalization and specialization to be balanced in one unified model. Our approach tunes a mixture of temporal experts to lear"},"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":"2410.10589","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-10-14T15:00:55Z","cross_cats_sorted":[],"title_canon_sha256":"8cc40fa5525a520b259030adfedfa4d2c59eaa1cee1f1dd8e987da094f1bc066","abstract_canon_sha256":"6930ae883b34afb7dabde26efa877ce77704b0d446c719d38b6cea63372670ed"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:20:18.519147Z","signature_b64":"/DKBGKvdOwBsa79okKyUUPrq0+oVIKxGF6woLJ/UVpQsPYBLcz3Slw2zCgeWIN/ah9/Y+g01udx7AwpcwBiyBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"5a23245f68cbe2d3871c97c96a50f72e666a1b9a2a7ca3dda1666b4259c15153","last_reissued_at":"2026-07-05T09:20:18.518676Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:20:18.518676Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"MoTE: Reconciling Generalization with Specialization for Visual-Language to Video Knowledge Transfer","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Chengju Liu, Mengxian Hu, Minghao Zhu, Qijun Chen, Ronghao Dang, Xiao Lin, Xun Zhou, Zhengpu Wang","submitted_at":"2024-10-14T15:00:55Z","abstract_excerpt":"Transferring visual-language knowledge from large-scale foundation models for video recognition has proved to be effective. To bridge the domain gap, additional parametric modules are added to capture the temporal information. However, zero-shot generalization diminishes with the increase in the number of specialized parameters, making existing works a trade-off between zero-shot and close-set performance. In this paper, we present MoTE, a novel framework that enables generalization and specialization to be balanced in one unified model. Our approach tunes a mixture of temporal experts to lear"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2410.10589","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/2410.10589/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":"2410.10589","created_at":"2026-07-05T09:20:18.518740+00:00"},{"alias_kind":"arxiv_version","alias_value":"2410.10589v1","created_at":"2026-07-05T09:20:18.518740+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2410.10589","created_at":"2026-07-05T09:20:18.518740+00:00"},{"alias_kind":"pith_short_12","alias_value":"LIRSIX3IZPRN","created_at":"2026-07-05T09:20:18.518740+00:00"},{"alias_kind":"pith_short_16","alias_value":"LIRSIX3IZPRNHBY4","created_at":"2026-07-05T09:20:18.518740+00:00"},{"alias_kind":"pith_short_8","alias_value":"LIRSIX3I","created_at":"2026-07-05T09:20:18.518740+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/LIRSIX3IZPRNHBY4S7EWUUHXFZ","json":"https://pith.science/pith/LIRSIX3IZPRNHBY4S7EWUUHXFZ.json","graph_json":"https://pith.science/api/pith-number/LIRSIX3IZPRNHBY4S7EWUUHXFZ/graph.json","events_json":"https://pith.science/api/pith-number/LIRSIX3IZPRNHBY4S7EWUUHXFZ/events.json","paper":"https://pith.science/paper/LIRSIX3I"},"agent_actions":{"view_html":"https://pith.science/pith/LIRSIX3IZPRNHBY4S7EWUUHXFZ","download_json":"https://pith.science/pith/LIRSIX3IZPRNHBY4S7EWUUHXFZ.json","view_paper":"https://pith.science/paper/LIRSIX3I","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2410.10589&json=true","fetch_graph":"https://pith.science/api/pith-number/LIRSIX3IZPRNHBY4S7EWUUHXFZ/graph.json","fetch_events":"https://pith.science/api/pith-number/LIRSIX3IZPRNHBY4S7EWUUHXFZ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/LIRSIX3IZPRNHBY4S7EWUUHXFZ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/LIRSIX3IZPRNHBY4S7EWUUHXFZ/action/storage_attestation","attest_author":"https://pith.science/pith/LIRSIX3IZPRNHBY4S7EWUUHXFZ/action/author_attestation","sign_citation":"https://pith.science/pith/LIRSIX3IZPRNHBY4S7EWUUHXFZ/action/citation_signature","submit_replication":"https://pith.science/pith/LIRSIX3IZPRNHBY4S7EWUUHXFZ/action/replication_record"}},"created_at":"2026-07-05T09:20:18.518740+00:00","updated_at":"2026-07-05T09:20:18.518740+00:00"}