{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:2COMO4YJSTW4VLKP6RINLCCQQR","short_pith_number":"pith:2COMO4YJ","schema_version":"1.0","canonical_sha256":"d09cc7730994edcaad4ff450d588508463d36a700a7c90c6542629671c98be6c","source":{"kind":"arxiv","id":"2211.09552","version":1},"attestation_state":"computed","paper":{"title":"UniFormerV2: Spatiotemporal Learning by Arming Image ViTs with Video UniFormer","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Kunchang Li, Limin Wang, Yali Wang, Yinan He, Yi Wang, Yizhuo Li, Yu Qiao","submitted_at":"2022-11-17T14:17:40Z","abstract_excerpt":"Learning discriminative spatiotemporal representation is the key problem of video understanding. Recently, Vision Transformers (ViTs) have shown their power in learning long-term video dependency with self-attention. Unfortunately, they exhibit limitations in tackling local video redundancy, due to the blind global comparison among tokens. UniFormer has successfully alleviated this issue, by unifying convolution and self-attention as a relation aggregator in the transformer format. However, this model has to require a tiresome and complicated image-pretraining phrase, before being finetuned on"},"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":"2211.09552","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2022-11-17T14:17:40Z","cross_cats_sorted":[],"title_canon_sha256":"0f17f8051f1d028cbafdd51e48bc2c1cb6f97b880c418fc28802fca95e3ce9e5","abstract_canon_sha256":"c463fa6beb6aae7c532105b372d8b9e030f24beb13b3be67d029a98cb04cf379"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:17:03.566250Z","signature_b64":"mTYM6M622sf8/Fdj2vt8mWJEq6TOEQShg8CQGRGOT5VYCoYruCjZ4ZBNZxm7qcsdjTSuDRaAVJ17g4ZzIsWgDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"d09cc7730994edcaad4ff450d588508463d36a700a7c90c6542629671c98be6c","last_reissued_at":"2026-07-05T05:17:03.565914Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:17:03.565914Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"UniFormerV2: Spatiotemporal Learning by Arming Image ViTs with Video UniFormer","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Kunchang Li, Limin Wang, Yali Wang, Yinan He, Yi Wang, Yizhuo Li, Yu Qiao","submitted_at":"2022-11-17T14:17:40Z","abstract_excerpt":"Learning discriminative spatiotemporal representation is the key problem of video understanding. Recently, Vision Transformers (ViTs) have shown their power in learning long-term video dependency with self-attention. Unfortunately, they exhibit limitations in tackling local video redundancy, due to the blind global comparison among tokens. UniFormer has successfully alleviated this issue, by unifying convolution and self-attention as a relation aggregator in the transformer format. However, this model has to require a tiresome and complicated image-pretraining phrase, before being finetuned on"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2211.09552","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/2211.09552/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":"2211.09552","created_at":"2026-07-05T05:17:03.565968+00:00"},{"alias_kind":"arxiv_version","alias_value":"2211.09552v1","created_at":"2026-07-05T05:17:03.565968+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2211.09552","created_at":"2026-07-05T05:17:03.565968+00:00"},{"alias_kind":"pith_short_12","alias_value":"2COMO4YJSTW4","created_at":"2026-07-05T05:17:03.565968+00:00"},{"alias_kind":"pith_short_16","alias_value":"2COMO4YJSTW4VLKP","created_at":"2026-07-05T05:17:03.565968+00:00"},{"alias_kind":"pith_short_8","alias_value":"2COMO4YJ","created_at":"2026-07-05T05:17:03.565968+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":12,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.17437","citing_title":"Spatio-Temporal Fusion Model for Standard View Classification of Echocardiographic Videos","ref_index":42,"is_internal_anchor":false},{"citing_arxiv_id":"2501.02955","citing_title":"MotionBench: Benchmarking and Improving Fine-grained Video Motion Understanding for Vision Language Models","ref_index":21,"is_internal_anchor":false},{"citing_arxiv_id":"2605.17133","citing_title":"CAM-VFD: Cross-Attention Multimodal Video Forgery Detection","ref_index":45,"is_internal_anchor":false},{"citing_arxiv_id":"2311.17005","citing_title":"MVBench: A Comprehensive Multi-modal Video Understanding Benchmark","ref_index":41,"is_internal_anchor":false},{"citing_arxiv_id":"2212.03191","citing_title":"InternVideo: General Video Foundation Models via Generative and Discriminative Learning","ref_index":56,"is_internal_anchor":false},{"citing_arxiv_id":"2408.16500","citing_title":"CogVLM2: Visual Language Models for Image and Video Understanding","ref_index":36,"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":26,"is_internal_anchor":false},{"citing_arxiv_id":"2305.06355","citing_title":"VideoChat: Chat-Centric Video Understanding","ref_index":20,"is_internal_anchor":false},{"citing_arxiv_id":"2604.11913","citing_title":"V-Nutri: Dish-Level Nutrition Estimation from Egocentric Cooking Videos","ref_index":25,"is_internal_anchor":false},{"citing_arxiv_id":"2604.11389","citing_title":"ConvFormer3D-TAP: Phase/Uncertainty-Aware Front-End Fusion for Cine CMR View Classification Pipelines","ref_index":38,"is_internal_anchor":false},{"citing_arxiv_id":"2604.15718","citing_title":"NeuroLip: An Event-driven Spatiotemporal Learning Framework for Cross-Scene Lip-Motion-based Visual Speaker Recognition","ref_index":60,"is_internal_anchor":false},{"citing_arxiv_id":"2604.16987","citing_title":"DVAR: Adversarial Multi-Agent Debate for Video Authenticity Detection","ref_index":19,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/2COMO4YJSTW4VLKP6RINLCCQQR","json":"https://pith.science/pith/2COMO4YJSTW4VLKP6RINLCCQQR.json","graph_json":"https://pith.science/api/pith-number/2COMO4YJSTW4VLKP6RINLCCQQR/graph.json","events_json":"https://pith.science/api/pith-number/2COMO4YJSTW4VLKP6RINLCCQQR/events.json","paper":"https://pith.science/paper/2COMO4YJ"},"agent_actions":{"view_html":"https://pith.science/pith/2COMO4YJSTW4VLKP6RINLCCQQR","download_json":"https://pith.science/pith/2COMO4YJSTW4VLKP6RINLCCQQR.json","view_paper":"https://pith.science/paper/2COMO4YJ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2211.09552&json=true","fetch_graph":"https://pith.science/api/pith-number/2COMO4YJSTW4VLKP6RINLCCQQR/graph.json","fetch_events":"https://pith.science/api/pith-number/2COMO4YJSTW4VLKP6RINLCCQQR/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/2COMO4YJSTW4VLKP6RINLCCQQR/action/timestamp_anchor","attest_storage":"https://pith.science/pith/2COMO4YJSTW4VLKP6RINLCCQQR/action/storage_attestation","attest_author":"https://pith.science/pith/2COMO4YJSTW4VLKP6RINLCCQQR/action/author_attestation","sign_citation":"https://pith.science/pith/2COMO4YJSTW4VLKP6RINLCCQQR/action/citation_signature","submit_replication":"https://pith.science/pith/2COMO4YJSTW4VLKP6RINLCCQQR/action/replication_record"}},"created_at":"2026-07-05T05:17:03.565968+00:00","updated_at":"2026-07-05T05:17:03.565968+00:00"}