{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:M7WRTU3M5E5RWGOBMFVZNB4VPP","short_pith_number":"pith:M7WRTU3M","schema_version":"1.0","canonical_sha256":"67ed19d36ce93b1b19c1616b9687957bd42708a201b463149a5971e3533bc430","source":{"kind":"arxiv","id":"2410.00741","version":2},"attestation_state":"computed","paper":{"title":"VideoCLIP-XL: Advancing Long Description Understanding for Video CLIP Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CV","cs.MM"],"primary_cat":"cs.CL","authors_text":"Chengyu Wang, Jiapeng Wang, Jun Huang, Kunzhe Huang, Lianwen Jin","submitted_at":"2024-10-01T14:33:22Z","abstract_excerpt":"Contrastive Language-Image Pre-training (CLIP) has been widely studied and applied in numerous applications. However, the emphasis on brief summary texts during pre-training prevents CLIP from understanding long descriptions. This issue is particularly acute regarding videos given that videos often contain abundant detailed contents. In this paper, we propose the VideoCLIP-XL (eXtra Length) model, which aims to unleash the long-description understanding capability of video CLIP models. Firstly, we establish an automatic data collection system and gather a large-scale VILD pre-training dataset "},"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":"2410.00741","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-10-01T14:33:22Z","cross_cats_sorted":["cs.CV","cs.MM"],"title_canon_sha256":"7731b875eac4f188af93a064b48c7913f113deadc764372082f90bdfb443840b","abstract_canon_sha256":"804c37e3aeeea2755078976d80a8998fc23c3af654bcb84453b37ff39d701de3"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:15:59.688063Z","signature_b64":"DC6RD7cQ0ZE0BnNRiluMHZQlInM7S2kBMjrMmF9Xj4N/1yJapETxrW5LdyG5X6T6PIVMSM3GpnbvgUQczc3WBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"67ed19d36ce93b1b19c1616b9687957bd42708a201b463149a5971e3533bc430","last_reissued_at":"2026-07-05T09:15:59.687543Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:15:59.687543Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"VideoCLIP-XL: Advancing Long Description Understanding for Video CLIP Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CV","cs.MM"],"primary_cat":"cs.CL","authors_text":"Chengyu Wang, Jiapeng Wang, Jun Huang, Kunzhe Huang, Lianwen Jin","submitted_at":"2024-10-01T14:33:22Z","abstract_excerpt":"Contrastive Language-Image Pre-training (CLIP) has been widely studied and applied in numerous applications. However, the emphasis on brief summary texts during pre-training prevents CLIP from understanding long descriptions. This issue is particularly acute regarding videos given that videos often contain abundant detailed contents. In this paper, we propose the VideoCLIP-XL (eXtra Length) model, which aims to unleash the long-description understanding capability of video CLIP models. Firstly, we establish an automatic data collection system and gather a large-scale VILD pre-training dataset "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2410.00741","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/2410.00741/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":"2410.00741","created_at":"2026-07-05T09:15:59.687603+00:00"},{"alias_kind":"arxiv_version","alias_value":"2410.00741v2","created_at":"2026-07-05T09:15:59.687603+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2410.00741","created_at":"2026-07-05T09:15:59.687603+00:00"},{"alias_kind":"pith_short_12","alias_value":"M7WRTU3M5E5R","created_at":"2026-07-05T09:15:59.687603+00:00"},{"alias_kind":"pith_short_16","alias_value":"M7WRTU3M5E5RWGOB","created_at":"2026-07-05T09:15:59.687603+00:00"},{"alias_kind":"pith_short_8","alias_value":"M7WRTU3M","created_at":"2026-07-05T09:15:59.687603+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":6,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.22905","citing_title":"InteractiveAvatar: Real-Time Streaming Video Generation for Consistent and Intent-Aware Avatars","ref_index":31,"is_internal_anchor":false},{"citing_arxiv_id":"2606.31109","citing_title":"InfiniVerse: Occupancy Guided Unbounded Scene Generation for Autonomous Driving","ref_index":41,"is_internal_anchor":false},{"citing_arxiv_id":"2606.22905","citing_title":"InteractiveAvatar: Real-Time Streaming Video Generation for Consistent and Intent-Aware Avatars","ref_index":32,"is_internal_anchor":false},{"citing_arxiv_id":"2512.10571","citing_title":"AVI-Edit: Audio-sync Video Instance Editing with Granularity-Aware Mask Refiner","ref_index":62,"is_internal_anchor":false},{"citing_arxiv_id":"2605.10228","citing_title":"FLARE: Full-Modality Long-Video Audiovisual Retrieval Benchmark with User-Simulated Queries","ref_index":29,"is_internal_anchor":false},{"citing_arxiv_id":"2605.02757","citing_title":"Seeing Realism from Simulation: Efficient Video Transfer for Vision-Language-Action Data Augmentation","ref_index":24,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/M7WRTU3M5E5RWGOBMFVZNB4VPP","json":"https://pith.science/pith/M7WRTU3M5E5RWGOBMFVZNB4VPP.json","graph_json":"https://pith.science/api/pith-number/M7WRTU3M5E5RWGOBMFVZNB4VPP/graph.json","events_json":"https://pith.science/api/pith-number/M7WRTU3M5E5RWGOBMFVZNB4VPP/events.json","paper":"https://pith.science/paper/M7WRTU3M"},"agent_actions":{"view_html":"https://pith.science/pith/M7WRTU3M5E5RWGOBMFVZNB4VPP","download_json":"https://pith.science/pith/M7WRTU3M5E5RWGOBMFVZNB4VPP.json","view_paper":"https://pith.science/paper/M7WRTU3M","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2410.00741&json=true","fetch_graph":"https://pith.science/api/pith-number/M7WRTU3M5E5RWGOBMFVZNB4VPP/graph.json","fetch_events":"https://pith.science/api/pith-number/M7WRTU3M5E5RWGOBMFVZNB4VPP/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/M7WRTU3M5E5RWGOBMFVZNB4VPP/action/timestamp_anchor","attest_storage":"https://pith.science/pith/M7WRTU3M5E5RWGOBMFVZNB4VPP/action/storage_attestation","attest_author":"https://pith.science/pith/M7WRTU3M5E5RWGOBMFVZNB4VPP/action/author_attestation","sign_citation":"https://pith.science/pith/M7WRTU3M5E5RWGOBMFVZNB4VPP/action/citation_signature","submit_replication":"https://pith.science/pith/M7WRTU3M5E5RWGOBMFVZNB4VPP/action/replication_record"}},"created_at":"2026-07-05T09:15:59.687603+00:00","updated_at":"2026-07-05T09:15:59.687603+00:00"}