{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:OYGKL2R3TSU7E5VUWTNLXNKKJY","short_pith_number":"pith:OYGKL2R3","schema_version":"1.0","canonical_sha256":"760ca5ea3b9ca9f276b4b4dabbb54a4e1536f1753a994e2daa75c070673695cc","source":{"kind":"arxiv","id":"2303.01589","version":1},"attestation_state":"computed","paper":{"title":"AZTR: Aerial Video Action Recognition with Auto Zoom and Temporal Reasoning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.RO"],"primary_cat":"cs.CV","authors_text":"Aniket Bera, Celso M. de Melo, Dinesh Manocha, Ruiqi Xian, Stephen M. Nogar, Tianrui Guan, Xijun Wang","submitted_at":"2023-03-02T21:24:19Z","abstract_excerpt":"We propose a novel approach for aerial video action recognition. Our method is designed for videos captured using UAVs and can run on edge or mobile devices. We present a learning-based approach that uses customized auto zoom to automatically identify the human target and scale it appropriately. This makes it easier to extract the key features and reduces the computational overhead. We also present an efficient temporal reasoning algorithm to capture the action information along the spatial and temporal domains within a controllable computational cost. Our approach has been implemented and eva"},"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":"2303.01589","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2023-03-02T21:24:19Z","cross_cats_sorted":["cs.RO"],"title_canon_sha256":"105300aa3796216cf9b8eee4e626cbbaeeae22f07b2da0f8c345a74002594abb","abstract_canon_sha256":"b6adaf9af3e6297d8daac88ce69244a5974b1fc3433f28b4f0d46629ff6e7db2"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:32:37.186932Z","signature_b64":"3S44abIMzcLY4sHGrPuL/VSdiszkMVh76esvqSDKF3ggu2pJVntn0DbEGLUNwO6LvMAx7PBZiNNXbR+Dp0DYAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"760ca5ea3b9ca9f276b4b4dabbb54a4e1536f1753a994e2daa75c070673695cc","last_reissued_at":"2026-07-05T06:32:37.186459Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:32:37.186459Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"AZTR: Aerial Video Action Recognition with Auto Zoom and Temporal Reasoning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.RO"],"primary_cat":"cs.CV","authors_text":"Aniket Bera, Celso M. de Melo, Dinesh Manocha, Ruiqi Xian, Stephen M. Nogar, Tianrui Guan, Xijun Wang","submitted_at":"2023-03-02T21:24:19Z","abstract_excerpt":"We propose a novel approach for aerial video action recognition. Our method is designed for videos captured using UAVs and can run on edge or mobile devices. We present a learning-based approach that uses customized auto zoom to automatically identify the human target and scale it appropriately. This makes it easier to extract the key features and reduces the computational overhead. We also present an efficient temporal reasoning algorithm to capture the action information along the spatial and temporal domains within a controllable computational cost. Our approach has been implemented and eva"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2303.01589","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/2303.01589/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":"2303.01589","created_at":"2026-07-05T06:32:37.186517+00:00"},{"alias_kind":"arxiv_version","alias_value":"2303.01589v1","created_at":"2026-07-05T06:32:37.186517+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2303.01589","created_at":"2026-07-05T06:32:37.186517+00:00"},{"alias_kind":"pith_short_12","alias_value":"OYGKL2R3TSU7","created_at":"2026-07-05T06:32:37.186517+00:00"},{"alias_kind":"pith_short_16","alias_value":"OYGKL2R3TSU7E5VU","created_at":"2026-07-05T06:32:37.186517+00:00"},{"alias_kind":"pith_short_8","alias_value":"OYGKL2R3","created_at":"2026-07-05T06:32:37.186517+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.25615","citing_title":"UAV-OVO: Out-of-Viewpoint Generalization in UAV Action Recognition","ref_index":10,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/OYGKL2R3TSU7E5VUWTNLXNKKJY","json":"https://pith.science/pith/OYGKL2R3TSU7E5VUWTNLXNKKJY.json","graph_json":"https://pith.science/api/pith-number/OYGKL2R3TSU7E5VUWTNLXNKKJY/graph.json","events_json":"https://pith.science/api/pith-number/OYGKL2R3TSU7E5VUWTNLXNKKJY/events.json","paper":"https://pith.science/paper/OYGKL2R3"},"agent_actions":{"view_html":"https://pith.science/pith/OYGKL2R3TSU7E5VUWTNLXNKKJY","download_json":"https://pith.science/pith/OYGKL2R3TSU7E5VUWTNLXNKKJY.json","view_paper":"https://pith.science/paper/OYGKL2R3","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2303.01589&json=true","fetch_graph":"https://pith.science/api/pith-number/OYGKL2R3TSU7E5VUWTNLXNKKJY/graph.json","fetch_events":"https://pith.science/api/pith-number/OYGKL2R3TSU7E5VUWTNLXNKKJY/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/OYGKL2R3TSU7E5VUWTNLXNKKJY/action/timestamp_anchor","attest_storage":"https://pith.science/pith/OYGKL2R3TSU7E5VUWTNLXNKKJY/action/storage_attestation","attest_author":"https://pith.science/pith/OYGKL2R3TSU7E5VUWTNLXNKKJY/action/author_attestation","sign_citation":"https://pith.science/pith/OYGKL2R3TSU7E5VUWTNLXNKKJY/action/citation_signature","submit_replication":"https://pith.science/pith/OYGKL2R3TSU7E5VUWTNLXNKKJY/action/replication_record"}},"created_at":"2026-07-05T06:32:37.186517+00:00","updated_at":"2026-07-05T06:32:37.186517+00:00"}