{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:B5GK7HEGNYOBUOMCYAD7QZ3H2U","short_pith_number":"pith:B5GK7HEG","schema_version":"1.0","canonical_sha256":"0f4caf9c866e1c1a3982c007f86767d517198327dbe417a93a4476afcc5958d5","source":{"kind":"arxiv","id":"2111.12681","version":2},"attestation_state":"computed","paper":{"title":"VIOLET : End-to-End Video-Language Transformers with Masked Visual-token Modeling","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Kevin Lin, Lijuan Wang, Linjie Li, Tsu-Jui Fu, William Yang Wang, Zhe Gan, Zicheng Liu","submitted_at":"2021-11-24T18:31:20Z","abstract_excerpt":"A great challenge in video-language (VidL) modeling lies in the disconnection between fixed video representations extracted from image/video understanding models and downstream VidL data. Recent studies try to mitigate this disconnection via end-to-end training. To make it computationally feasible, prior works tend to \"imagify\" video inputs, i.e., a handful of sparsely sampled frames are fed into a 2D CNN, followed by a simple mean-pooling or concatenation to obtain the overall video representations. Although achieving promising results, such simple approaches may lose temporal information tha"},"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":"2111.12681","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2021-11-24T18:31:20Z","cross_cats_sorted":[],"title_canon_sha256":"dd6efaf357de486dac905ca54d574d6be6535ce63a631716ec64a84610a67a4f","abstract_canon_sha256":"4c9b819b41c164495d07d2df0d587c90fc2107bec5ccddafb31ed6b7ff3e4133"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T04:15:11.989182Z","signature_b64":"cQTL8sP8HF1brhZxUjok7wdlE0a1v2n2ki9n3iFoqSJRHrSEK+Ppoex5EoYwY9sWdHpOqNwuEQ6/gQ8U7KbPCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"0f4caf9c866e1c1a3982c007f86767d517198327dbe417a93a4476afcc5958d5","last_reissued_at":"2026-07-05T04:15:11.988646Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T04:15:11.988646Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"VIOLET : End-to-End Video-Language Transformers with Masked Visual-token Modeling","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Kevin Lin, Lijuan Wang, Linjie Li, Tsu-Jui Fu, William Yang Wang, Zhe Gan, Zicheng Liu","submitted_at":"2021-11-24T18:31:20Z","abstract_excerpt":"A great challenge in video-language (VidL) modeling lies in the disconnection between fixed video representations extracted from image/video understanding models and downstream VidL data. Recent studies try to mitigate this disconnection via end-to-end training. To make it computationally feasible, prior works tend to \"imagify\" video inputs, i.e., a handful of sparsely sampled frames are fed into a 2D CNN, followed by a simple mean-pooling or concatenation to obtain the overall video representations. Although achieving promising results, such simple approaches may lose temporal information tha"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2111.12681","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/2111.12681/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":"2111.12681","created_at":"2026-07-05T04:15:11.988701+00:00"},{"alias_kind":"arxiv_version","alias_value":"2111.12681v2","created_at":"2026-07-05T04:15:11.988701+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2111.12681","created_at":"2026-07-05T04:15:11.988701+00:00"},{"alias_kind":"pith_short_12","alias_value":"B5GK7HEGNYOB","created_at":"2026-07-05T04:15:11.988701+00:00"},{"alias_kind":"pith_short_16","alias_value":"B5GK7HEGNYOBUOMC","created_at":"2026-07-05T04:15:11.988701+00:00"},{"alias_kind":"pith_short_8","alias_value":"B5GK7HEG","created_at":"2026-07-05T04:15:11.988701+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":12,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.09181","citing_title":"Counterfactual Reasoning for Fine-Grained Evidence Disentanglement in VideoQA","ref_index":26,"is_internal_anchor":false},{"citing_arxiv_id":"2502.03814","citing_title":"Large Language Models for Multi-Robot Systems: A Survey","ref_index":26,"is_internal_anchor":false},{"citing_arxiv_id":"2505.16819","citing_title":"Character-Centered Dialogue Generation from Scene-Level Prompts","ref_index":20,"is_internal_anchor":false},{"citing_arxiv_id":"2311.17005","citing_title":"MVBench: A Comprehensive Multi-modal Video Understanding Benchmark","ref_index":18,"is_internal_anchor":false},{"citing_arxiv_id":"2310.01852","citing_title":"LanguageBind: Extending Video-Language Pretraining to N-modality by Language-based Semantic Alignment","ref_index":189,"is_internal_anchor":false},{"citing_arxiv_id":"2512.06673","citing_title":"Detector-Empowered Video Large Language Model for Efficient Spatio-Temporal Grounding","ref_index":14,"is_internal_anchor":false},{"citing_arxiv_id":"2212.03191","citing_title":"InternVideo: General Video Foundation Models via Generative and Discriminative Learning","ref_index":30,"is_internal_anchor":false},{"citing_arxiv_id":"2307.06942","citing_title":"InternVid: A Large-scale Video-Text Dataset for Multimodal Understanding and Generation","ref_index":41,"is_internal_anchor":false},{"citing_arxiv_id":"2305.06355","citing_title":"VideoChat: Chat-Centric Video Understanding","ref_index":12,"is_internal_anchor":false},{"citing_arxiv_id":"2303.04671","citing_title":"Visual ChatGPT: Talking, Drawing and Editing with Visual Foundation Models","ref_index":13,"is_internal_anchor":false},{"citing_arxiv_id":"2204.14198","citing_title":"Flamingo: a Visual Language Model for Few-Shot Learning","ref_index":28,"is_internal_anchor":false},{"citing_arxiv_id":"2604.08337","citing_title":"InstAP: Instance-Aware Vision-Language Pre-Train for Spatial-Temporal Understanding","ref_index":16,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/B5GK7HEGNYOBUOMCYAD7QZ3H2U","json":"https://pith.science/pith/B5GK7HEGNYOBUOMCYAD7QZ3H2U.json","graph_json":"https://pith.science/api/pith-number/B5GK7HEGNYOBUOMCYAD7QZ3H2U/graph.json","events_json":"https://pith.science/api/pith-number/B5GK7HEGNYOBUOMCYAD7QZ3H2U/events.json","paper":"https://pith.science/paper/B5GK7HEG"},"agent_actions":{"view_html":"https://pith.science/pith/B5GK7HEGNYOBUOMCYAD7QZ3H2U","download_json":"https://pith.science/pith/B5GK7HEGNYOBUOMCYAD7QZ3H2U.json","view_paper":"https://pith.science/paper/B5GK7HEG","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2111.12681&json=true","fetch_graph":"https://pith.science/api/pith-number/B5GK7HEGNYOBUOMCYAD7QZ3H2U/graph.json","fetch_events":"https://pith.science/api/pith-number/B5GK7HEGNYOBUOMCYAD7QZ3H2U/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/B5GK7HEGNYOBUOMCYAD7QZ3H2U/action/timestamp_anchor","attest_storage":"https://pith.science/pith/B5GK7HEGNYOBUOMCYAD7QZ3H2U/action/storage_attestation","attest_author":"https://pith.science/pith/B5GK7HEGNYOBUOMCYAD7QZ3H2U/action/author_attestation","sign_citation":"https://pith.science/pith/B5GK7HEGNYOBUOMCYAD7QZ3H2U/action/citation_signature","submit_replication":"https://pith.science/pith/B5GK7HEGNYOBUOMCYAD7QZ3H2U/action/replication_record"}},"created_at":"2026-07-05T04:15:11.988701+00:00","updated_at":"2026-07-05T04:15:11.988701+00:00"}