{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:IXWNMQGNAI2ROC6UGGAYCLOHVY","short_pith_number":"pith:IXWNMQGN","schema_version":"1.0","canonical_sha256":"45ecd640cd0235170bd43181812dc7ae0d27a498b502e7de3fce86f89a07a7b5","source":{"kind":"arxiv","id":"2506.01757","version":1},"attestation_state":"computed","paper":{"title":"Efficient Egocentric Action Recognition with Multimodal Data","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CV","authors_text":"Ard Kastrati, Dushan Vasilevski, Marco Calzavara, Matteo Macchini, Roger Wattenhofer","submitted_at":"2025-06-02T15:04:23Z","abstract_excerpt":"The increasing availability of wearable XR devices opens new perspectives for Egocentric Action Recognition (EAR) systems, which can provide deeper human understanding and situation awareness. However, deploying real-time algorithms on these devices can be challenging due to the inherent trade-offs between portability, battery life, and computational resources. In this work, we systematically analyze the impact of sampling frequency across different input modalities - RGB video and 3D hand pose - on egocentric action recognition performance and CPU usage. By exploring a range of configurations"},"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":"2506.01757","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-06-02T15:04:23Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"1f629069d11bdf99828d848951522b9c8b97fcbeef352c9172bc0f2cd4deabaf","abstract_canon_sha256":"d8fbc725f52fb61ef1b75436113406ae057cba83720d6933781b445e700dd6f5"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:14:19.003200Z","signature_b64":"NdzoIq/o2/iZBRocRftmRQXcJngfb1DZ2P96OWrrzh54/ctS/Xcjum4HPPEUuErkkGS4lqVzNSqA6dZ6SIIXBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"45ecd640cd0235170bd43181812dc7ae0d27a498b502e7de3fce86f89a07a7b5","last_reissued_at":"2026-07-05T11:14:19.002747Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:14:19.002747Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Efficient Egocentric Action Recognition with Multimodal Data","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CV","authors_text":"Ard Kastrati, Dushan Vasilevski, Marco Calzavara, Matteo Macchini, Roger Wattenhofer","submitted_at":"2025-06-02T15:04:23Z","abstract_excerpt":"The increasing availability of wearable XR devices opens new perspectives for Egocentric Action Recognition (EAR) systems, which can provide deeper human understanding and situation awareness. However, deploying real-time algorithms on these devices can be challenging due to the inherent trade-offs between portability, battery life, and computational resources. In this work, we systematically analyze the impact of sampling frequency across different input modalities - RGB video and 3D hand pose - on egocentric action recognition performance and CPU usage. By exploring a range of configurations"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2506.01757","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/2506.01757/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":"2506.01757","created_at":"2026-07-05T11:14:19.002799+00:00"},{"alias_kind":"arxiv_version","alias_value":"2506.01757v1","created_at":"2026-07-05T11:14:19.002799+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.01757","created_at":"2026-07-05T11:14:19.002799+00:00"},{"alias_kind":"pith_short_12","alias_value":"IXWNMQGNAI2R","created_at":"2026-07-05T11:14:19.002799+00:00"},{"alias_kind":"pith_short_16","alias_value":"IXWNMQGNAI2ROC6U","created_at":"2026-07-05T11:14:19.002799+00:00"},{"alias_kind":"pith_short_8","alias_value":"IXWNMQGN","created_at":"2026-07-05T11:14:19.002799+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/IXWNMQGNAI2ROC6UGGAYCLOHVY","json":"https://pith.science/pith/IXWNMQGNAI2ROC6UGGAYCLOHVY.json","graph_json":"https://pith.science/api/pith-number/IXWNMQGNAI2ROC6UGGAYCLOHVY/graph.json","events_json":"https://pith.science/api/pith-number/IXWNMQGNAI2ROC6UGGAYCLOHVY/events.json","paper":"https://pith.science/paper/IXWNMQGN"},"agent_actions":{"view_html":"https://pith.science/pith/IXWNMQGNAI2ROC6UGGAYCLOHVY","download_json":"https://pith.science/pith/IXWNMQGNAI2ROC6UGGAYCLOHVY.json","view_paper":"https://pith.science/paper/IXWNMQGN","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2506.01757&json=true","fetch_graph":"https://pith.science/api/pith-number/IXWNMQGNAI2ROC6UGGAYCLOHVY/graph.json","fetch_events":"https://pith.science/api/pith-number/IXWNMQGNAI2ROC6UGGAYCLOHVY/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/IXWNMQGNAI2ROC6UGGAYCLOHVY/action/timestamp_anchor","attest_storage":"https://pith.science/pith/IXWNMQGNAI2ROC6UGGAYCLOHVY/action/storage_attestation","attest_author":"https://pith.science/pith/IXWNMQGNAI2ROC6UGGAYCLOHVY/action/author_attestation","sign_citation":"https://pith.science/pith/IXWNMQGNAI2ROC6UGGAYCLOHVY/action/citation_signature","submit_replication":"https://pith.science/pith/IXWNMQGNAI2ROC6UGGAYCLOHVY/action/replication_record"}},"created_at":"2026-07-05T11:14:19.002799+00:00","updated_at":"2026-07-05T11:14:19.002799+00:00"}