{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:NKQ56QAGLS7ERAJI7TTC7XYD46","short_pith_number":"pith:NKQ56QAG","schema_version":"1.0","canonical_sha256":"6aa1df40065cbe488128fce62fdf03e78c510eac51cc395bcbf77d212cb13bac","source":{"kind":"arxiv","id":"2409.02910","version":1},"attestation_state":"computed","paper":{"title":"SITAR: Semi-supervised Image Transformer for Action Recognition","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Abir Das, Aftab Hussain, Omprakash Chakraborty, Owais Iqbal, Rameswar Panda","submitted_at":"2024-09-04T17:49:54Z","abstract_excerpt":"Recognizing actions from a limited set of labeled videos remains a challenge as annotating visual data is not only tedious but also can be expensive due to classified nature. Moreover, handling spatio-temporal data using deep $3$D transformers for this can introduce significant computational complexity. In this paper, our objective is to address video action recognition in a semi-supervised setting by leveraging only a handful of labeled videos along with a collection of unlabeled videos in a compute efficient manner. Specifically, we rearrange multiple frames from the input videos in row-colu"},"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":"2409.02910","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-09-04T17:49:54Z","cross_cats_sorted":[],"title_canon_sha256":"06a2c3105aea40bd0823e1f0dfe3d50fcdcdd65dca9c2f3e19afdcd224e52551","abstract_canon_sha256":"b2cb30a1911298398187f4a22e2acf4ddb3c10c29a6b024b380c180e8caec006"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:03:12.376900Z","signature_b64":"TJA72Sy092DAHvnjSLqZe0cdbpampaEB+40MXdxYn3ikCsVjFo+7O97aRHj0o0r5SE2DpxyVnCyoK92ArIhACw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"6aa1df40065cbe488128fce62fdf03e78c510eac51cc395bcbf77d212cb13bac","last_reissued_at":"2026-07-05T09:03:12.376426Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:03:12.376426Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"SITAR: Semi-supervised Image Transformer for Action Recognition","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Abir Das, Aftab Hussain, Omprakash Chakraborty, Owais Iqbal, Rameswar Panda","submitted_at":"2024-09-04T17:49:54Z","abstract_excerpt":"Recognizing actions from a limited set of labeled videos remains a challenge as annotating visual data is not only tedious but also can be expensive due to classified nature. Moreover, handling spatio-temporal data using deep $3$D transformers for this can introduce significant computational complexity. In this paper, our objective is to address video action recognition in a semi-supervised setting by leveraging only a handful of labeled videos along with a collection of unlabeled videos in a compute efficient manner. Specifically, we rearrange multiple frames from the input videos in row-colu"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2409.02910","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/2409.02910/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":"2409.02910","created_at":"2026-07-05T09:03:12.376487+00:00"},{"alias_kind":"arxiv_version","alias_value":"2409.02910v1","created_at":"2026-07-05T09:03:12.376487+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2409.02910","created_at":"2026-07-05T09:03:12.376487+00:00"},{"alias_kind":"pith_short_12","alias_value":"NKQ56QAGLS7E","created_at":"2026-07-05T09:03:12.376487+00:00"},{"alias_kind":"pith_short_16","alias_value":"NKQ56QAGLS7ERAJI","created_at":"2026-07-05T09:03:12.376487+00:00"},{"alias_kind":"pith_short_8","alias_value":"NKQ56QAG","created_at":"2026-07-05T09:03:12.376487+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/NKQ56QAGLS7ERAJI7TTC7XYD46","json":"https://pith.science/pith/NKQ56QAGLS7ERAJI7TTC7XYD46.json","graph_json":"https://pith.science/api/pith-number/NKQ56QAGLS7ERAJI7TTC7XYD46/graph.json","events_json":"https://pith.science/api/pith-number/NKQ56QAGLS7ERAJI7TTC7XYD46/events.json","paper":"https://pith.science/paper/NKQ56QAG"},"agent_actions":{"view_html":"https://pith.science/pith/NKQ56QAGLS7ERAJI7TTC7XYD46","download_json":"https://pith.science/pith/NKQ56QAGLS7ERAJI7TTC7XYD46.json","view_paper":"https://pith.science/paper/NKQ56QAG","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2409.02910&json=true","fetch_graph":"https://pith.science/api/pith-number/NKQ56QAGLS7ERAJI7TTC7XYD46/graph.json","fetch_events":"https://pith.science/api/pith-number/NKQ56QAGLS7ERAJI7TTC7XYD46/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/NKQ56QAGLS7ERAJI7TTC7XYD46/action/timestamp_anchor","attest_storage":"https://pith.science/pith/NKQ56QAGLS7ERAJI7TTC7XYD46/action/storage_attestation","attest_author":"https://pith.science/pith/NKQ56QAGLS7ERAJI7TTC7XYD46/action/author_attestation","sign_citation":"https://pith.science/pith/NKQ56QAGLS7ERAJI7TTC7XYD46/action/citation_signature","submit_replication":"https://pith.science/pith/NKQ56QAGLS7ERAJI7TTC7XYD46/action/replication_record"}},"created_at":"2026-07-05T09:03:12.376487+00:00","updated_at":"2026-07-05T09:03:12.376487+00:00"}