{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:QSCCG5CEWKTWMZJPV3JDTHV2IH","short_pith_number":"pith:QSCCG5CE","schema_version":"1.0","canonical_sha256":"8484237444b2a766652faed2399eba41f0f35e3ee3a375dcccff4a9b1f1702c5","source":{"kind":"arxiv","id":"2210.11929","version":1},"attestation_state":"computed","paper":{"title":"LiteVL: Efficient Video-Language Learning with Enhanced Spatial-Temporal Modeling","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CL"],"primary_cat":"cs.CV","authors_text":"Chaofan Tao, Dongsheng Chen, Lifeng Shang, Lu Hou, Qun Liu, Xin Jiang","submitted_at":"2022-10-21T13:03:49Z","abstract_excerpt":"Recent large-scale video-language pre-trained models have shown appealing performance on various downstream tasks. However, the pre-training process is computationally expensive due to the requirement of millions of video-text pairs and the redundant data structure of each video. To mitigate these problems, we propose LiteVL, which adapts a pre-trained image-language model BLIP into a video-text model directly on downstream tasks, without heavy pre-training. To enhance the temporal modeling lacking in the image-language model, we propose to add temporal attention modules in the image encoder o"},"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":"2210.11929","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2022-10-21T13:03:49Z","cross_cats_sorted":["cs.CL"],"title_canon_sha256":"7eea5db5149933fb9e2ab8c4a9e211fed6c143f206b29fee6653710918b2c20d","abstract_canon_sha256":"5ec84dc29eeec2f309a139819a3bf87129c9f69f604a89bb566c79bead2cfb8f"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:09:07.271181Z","signature_b64":"kchbSPReDpwr/wPgbQ5HHipTpmL9K9w8CytcUkKGLaAg7NP5CO5yIET8CACIaTTaNxArs2qRm5RPlXd5CofOCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"8484237444b2a766652faed2399eba41f0f35e3ee3a375dcccff4a9b1f1702c5","last_reissued_at":"2026-07-05T05:09:07.270741Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:09:07.270741Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"LiteVL: Efficient Video-Language Learning with Enhanced Spatial-Temporal Modeling","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CL"],"primary_cat":"cs.CV","authors_text":"Chaofan Tao, Dongsheng Chen, Lifeng Shang, Lu Hou, Qun Liu, Xin Jiang","submitted_at":"2022-10-21T13:03:49Z","abstract_excerpt":"Recent large-scale video-language pre-trained models have shown appealing performance on various downstream tasks. However, the pre-training process is computationally expensive due to the requirement of millions of video-text pairs and the redundant data structure of each video. To mitigate these problems, we propose LiteVL, which adapts a pre-trained image-language model BLIP into a video-text model directly on downstream tasks, without heavy pre-training. To enhance the temporal modeling lacking in the image-language model, we propose to add temporal attention modules in the image encoder o"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2210.11929","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/2210.11929/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":"2210.11929","created_at":"2026-07-05T05:09:07.270810+00:00"},{"alias_kind":"arxiv_version","alias_value":"2210.11929v1","created_at":"2026-07-05T05:09:07.270810+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2210.11929","created_at":"2026-07-05T05:09:07.270810+00:00"},{"alias_kind":"pith_short_12","alias_value":"QSCCG5CEWKTW","created_at":"2026-07-05T05:09:07.270810+00:00"},{"alias_kind":"pith_short_16","alias_value":"QSCCG5CEWKTWMZJP","created_at":"2026-07-05T05:09:07.270810+00:00"},{"alias_kind":"pith_short_8","alias_value":"QSCCG5CE","created_at":"2026-07-05T05:09:07.270810+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.27025","citing_title":"Improving General Role-Playing Agents via Psychology-Grounded Reasoning and Role-Aware Policy Optimization","ref_index":146,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/QSCCG5CEWKTWMZJPV3JDTHV2IH","json":"https://pith.science/pith/QSCCG5CEWKTWMZJPV3JDTHV2IH.json","graph_json":"https://pith.science/api/pith-number/QSCCG5CEWKTWMZJPV3JDTHV2IH/graph.json","events_json":"https://pith.science/api/pith-number/QSCCG5CEWKTWMZJPV3JDTHV2IH/events.json","paper":"https://pith.science/paper/QSCCG5CE"},"agent_actions":{"view_html":"https://pith.science/pith/QSCCG5CEWKTWMZJPV3JDTHV2IH","download_json":"https://pith.science/pith/QSCCG5CEWKTWMZJPV3JDTHV2IH.json","view_paper":"https://pith.science/paper/QSCCG5CE","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2210.11929&json=true","fetch_graph":"https://pith.science/api/pith-number/QSCCG5CEWKTWMZJPV3JDTHV2IH/graph.json","fetch_events":"https://pith.science/api/pith-number/QSCCG5CEWKTWMZJPV3JDTHV2IH/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/QSCCG5CEWKTWMZJPV3JDTHV2IH/action/timestamp_anchor","attest_storage":"https://pith.science/pith/QSCCG5CEWKTWMZJPV3JDTHV2IH/action/storage_attestation","attest_author":"https://pith.science/pith/QSCCG5CEWKTWMZJPV3JDTHV2IH/action/author_attestation","sign_citation":"https://pith.science/pith/QSCCG5CEWKTWMZJPV3JDTHV2IH/action/citation_signature","submit_replication":"https://pith.science/pith/QSCCG5CEWKTWMZJPV3JDTHV2IH/action/replication_record"}},"created_at":"2026-07-05T05:09:07.270810+00:00","updated_at":"2026-07-05T05:09:07.270810+00:00"}