{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:O7555Z35KNABD4766UORL64SG7","short_pith_number":"pith:O7555Z35","schema_version":"1.0","canonical_sha256":"77fbdee77d534011f3fef51d15fb9237eb25dec875ee9d82b99c3c4144e7f059","source":{"kind":"arxiv","id":"2205.10747","version":4},"attestation_state":"computed","paper":{"title":"Language Models with Image Descriptors are Strong Few-Shot Video-Language Learners","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CV","authors_text":"Chenguang Zhu, Derek Hoiem, Heng Ji, Jie Lei, Luowei Zhou, Manling Li, Mohit Bansal, Ruochen Xu, Shih-Fu Chang, Shuohang Wang, Xudong Lin, Zhenhailong Wang, Ziyi Yang","submitted_at":"2022-05-22T05:18:27Z","abstract_excerpt":"The goal of this work is to build flexible video-language models that can generalize to various video-to-text tasks from few examples, such as domain-specific captioning, question answering, and future event prediction. Existing few-shot video-language learners focus exclusively on the encoder, resulting in the absence of a video-to-text decoder to handle generative tasks. Video captioners have been pretrained on large-scale video-language datasets, but they rely heavily on finetuning and lack the ability to generate text for unseen tasks in a few-shot setting. We propose VidIL, a few-shot Vid"},"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":"2205.10747","kind":"arxiv","version":4},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2022-05-22T05:18:27Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"3997bc25af811b53fb3d38f0d761dc67a63d51dba4c6a99dee5c640aaa109a4e","abstract_canon_sha256":"bd43e284eceb5c3a954068218b13f126598ab343844776db3be0936ee0eb3ac1"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:06:11.975519Z","signature_b64":"izPLQtCarA1t70Ook8H5J2G9cMHC/sfU3KxXV1k1pMtvyjdG+C8DaiKmzizQwkQ5P2hJXaBfRVrEE+AGiTSzAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"77fbdee77d534011f3fef51d15fb9237eb25dec875ee9d82b99c3c4144e7f059","last_reissued_at":"2026-07-05T05:06:11.975040Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:06:11.975040Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Language Models with Image Descriptors are Strong Few-Shot Video-Language Learners","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CV","authors_text":"Chenguang Zhu, Derek Hoiem, Heng Ji, Jie Lei, Luowei Zhou, Manling Li, Mohit Bansal, Ruochen Xu, Shih-Fu Chang, Shuohang Wang, Xudong Lin, Zhenhailong Wang, Ziyi Yang","submitted_at":"2022-05-22T05:18:27Z","abstract_excerpt":"The goal of this work is to build flexible video-language models that can generalize to various video-to-text tasks from few examples, such as domain-specific captioning, question answering, and future event prediction. Existing few-shot video-language learners focus exclusively on the encoder, resulting in the absence of a video-to-text decoder to handle generative tasks. Video captioners have been pretrained on large-scale video-language datasets, but they rely heavily on finetuning and lack the ability to generate text for unseen tasks in a few-shot setting. We propose VidIL, a few-shot Vid"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2205.10747","kind":"arxiv","version":4},"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/2205.10747/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":"2205.10747","created_at":"2026-07-05T05:06:11.975097+00:00"},{"alias_kind":"arxiv_version","alias_value":"2205.10747v4","created_at":"2026-07-05T05:06:11.975097+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2205.10747","created_at":"2026-07-05T05:06:11.975097+00:00"},{"alias_kind":"pith_short_12","alias_value":"O7555Z35KNAB","created_at":"2026-07-05T05:06:11.975097+00:00"},{"alias_kind":"pith_short_16","alias_value":"O7555Z35KNABD476","created_at":"2026-07-05T05:06:11.975097+00:00"},{"alias_kind":"pith_short_8","alias_value":"O7555Z35","created_at":"2026-07-05T05:06:11.975097+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2412.01115","citing_title":"DIR: Retrieval-Augmented Image Captioning with Comprehensive Understanding","ref_index":36,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/O7555Z35KNABD4766UORL64SG7","json":"https://pith.science/pith/O7555Z35KNABD4766UORL64SG7.json","graph_json":"https://pith.science/api/pith-number/O7555Z35KNABD4766UORL64SG7/graph.json","events_json":"https://pith.science/api/pith-number/O7555Z35KNABD4766UORL64SG7/events.json","paper":"https://pith.science/paper/O7555Z35"},"agent_actions":{"view_html":"https://pith.science/pith/O7555Z35KNABD4766UORL64SG7","download_json":"https://pith.science/pith/O7555Z35KNABD4766UORL64SG7.json","view_paper":"https://pith.science/paper/O7555Z35","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2205.10747&json=true","fetch_graph":"https://pith.science/api/pith-number/O7555Z35KNABD4766UORL64SG7/graph.json","fetch_events":"https://pith.science/api/pith-number/O7555Z35KNABD4766UORL64SG7/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/O7555Z35KNABD4766UORL64SG7/action/timestamp_anchor","attest_storage":"https://pith.science/pith/O7555Z35KNABD4766UORL64SG7/action/storage_attestation","attest_author":"https://pith.science/pith/O7555Z35KNABD4766UORL64SG7/action/author_attestation","sign_citation":"https://pith.science/pith/O7555Z35KNABD4766UORL64SG7/action/citation_signature","submit_replication":"https://pith.science/pith/O7555Z35KNABD4766UORL64SG7/action/replication_record"}},"created_at":"2026-07-05T05:06:11.975097+00:00","updated_at":"2026-07-05T05:06:11.975097+00:00"}