{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:FVZODSESEBKCVHUL5ZQKGPSWF2","short_pith_number":"pith:FVZODSES","schema_version":"1.0","canonical_sha256":"2d72e1c89220542a9e8bee60a33e562ea1878a531fc7edf0f6aa1a0f6455c6e9","source":{"kind":"arxiv","id":"2103.10043","version":1},"attestation_state":"computed","paper":{"title":"Enhancing Transformer for Video Understanding Using Gated Multi-Level Attention and Temporal Adversarial Training","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG","cs.MM"],"primary_cat":"cs.CV","authors_text":"Palash Goyal, Saurabh Sahu","submitted_at":"2021-03-18T06:39:09Z","abstract_excerpt":"The introduction of Transformer model has led to tremendous advancements in sequence modeling, especially in text domain. However, the use of attention-based models for video understanding is still relatively unexplored. In this paper, we introduce Gated Adversarial Transformer (GAT) to enhance the applicability of attention-based models to videos. GAT uses a multi-level attention gate to model the relevance of a frame based on local and global contexts. This enables the model to understand the video at various granularities. Further, GAT uses adversarial training to improve model generalizati"},"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":"2103.10043","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2021-03-18T06:39:09Z","cross_cats_sorted":["cs.LG","cs.MM"],"title_canon_sha256":"76de83e8c792a561ed36a756055ee7ee09a13a5b874e29659c6b1590b9697f19","abstract_canon_sha256":"0ee013d5a93493590f516a18a41b0ad113c1c5c426a32384b3b6346a26a816f3"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T02:24:15.953344Z","signature_b64":"Gv3UaTt5nKfz9/aUdWhUTWb64GIq/FOGo6G29rFqwfqGkfrFDBeZvp/pFy50RGg1TsUllA3mb2qzxe8fuBlJDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"2d72e1c89220542a9e8bee60a33e562ea1878a531fc7edf0f6aa1a0f6455c6e9","last_reissued_at":"2026-07-05T02:24:15.952988Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T02:24:15.952988Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Enhancing Transformer for Video Understanding Using Gated Multi-Level Attention and Temporal Adversarial Training","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG","cs.MM"],"primary_cat":"cs.CV","authors_text":"Palash Goyal, Saurabh Sahu","submitted_at":"2021-03-18T06:39:09Z","abstract_excerpt":"The introduction of Transformer model has led to tremendous advancements in sequence modeling, especially in text domain. However, the use of attention-based models for video understanding is still relatively unexplored. In this paper, we introduce Gated Adversarial Transformer (GAT) to enhance the applicability of attention-based models to videos. GAT uses a multi-level attention gate to model the relevance of a frame based on local and global contexts. This enables the model to understand the video at various granularities. Further, GAT uses adversarial training to improve model generalizati"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2103.10043","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/2103.10043/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":"2103.10043","created_at":"2026-07-05T02:24:15.953051+00:00"},{"alias_kind":"arxiv_version","alias_value":"2103.10043v1","created_at":"2026-07-05T02:24:15.953051+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2103.10043","created_at":"2026-07-05T02:24:15.953051+00:00"},{"alias_kind":"pith_short_12","alias_value":"FVZODSESEBKC","created_at":"2026-07-05T02:24:15.953051+00:00"},{"alias_kind":"pith_short_16","alias_value":"FVZODSESEBKCVHUL","created_at":"2026-07-05T02:24:15.953051+00:00"},{"alias_kind":"pith_short_8","alias_value":"FVZODSES","created_at":"2026-07-05T02:24:15.953051+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/FVZODSESEBKCVHUL5ZQKGPSWF2","json":"https://pith.science/pith/FVZODSESEBKCVHUL5ZQKGPSWF2.json","graph_json":"https://pith.science/api/pith-number/FVZODSESEBKCVHUL5ZQKGPSWF2/graph.json","events_json":"https://pith.science/api/pith-number/FVZODSESEBKCVHUL5ZQKGPSWF2/events.json","paper":"https://pith.science/paper/FVZODSES"},"agent_actions":{"view_html":"https://pith.science/pith/FVZODSESEBKCVHUL5ZQKGPSWF2","download_json":"https://pith.science/pith/FVZODSESEBKCVHUL5ZQKGPSWF2.json","view_paper":"https://pith.science/paper/FVZODSES","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2103.10043&json=true","fetch_graph":"https://pith.science/api/pith-number/FVZODSESEBKCVHUL5ZQKGPSWF2/graph.json","fetch_events":"https://pith.science/api/pith-number/FVZODSESEBKCVHUL5ZQKGPSWF2/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/FVZODSESEBKCVHUL5ZQKGPSWF2/action/timestamp_anchor","attest_storage":"https://pith.science/pith/FVZODSESEBKCVHUL5ZQKGPSWF2/action/storage_attestation","attest_author":"https://pith.science/pith/FVZODSESEBKCVHUL5ZQKGPSWF2/action/author_attestation","sign_citation":"https://pith.science/pith/FVZODSESEBKCVHUL5ZQKGPSWF2/action/citation_signature","submit_replication":"https://pith.science/pith/FVZODSESEBKCVHUL5ZQKGPSWF2/action/replication_record"}},"created_at":"2026-07-05T02:24:15.953051+00:00","updated_at":"2026-07-05T02:24:15.953051+00:00"}