{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:Y4PWFZ3IT5MKFUZ7QN45457QJJ","short_pith_number":"pith:Y4PWFZ3I","schema_version":"1.0","canonical_sha256":"c71f62e7689f58a2d33f8379de77f04a768e299a3f85e504c0ec0864b5171ba7","source":{"kind":"arxiv","id":"2111.01024","version":1},"attestation_state":"computed","paper":{"title":"With a Little Help from my Temporal Context: Multimodal Egocentric Action Recognition","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.SD","eess.AS"],"primary_cat":"cs.CV","authors_text":"Andrew Zisserman, Arsha Nagrani, Dima Damen, Evangelos Kazakos, Jaesung Huh","submitted_at":"2021-11-01T15:27:35Z","abstract_excerpt":"In egocentric videos, actions occur in quick succession. We capitalise on the action's temporal context and propose a method that learns to attend to surrounding actions in order to improve recognition performance. To incorporate the temporal context, we propose a transformer-based multimodal model that ingests video and audio as input modalities, with an explicit language model providing action sequence context to enhance the predictions. We test our approach on EPIC-KITCHENS and EGTEA datasets reporting state-of-the-art performance. Our ablations showcase the advantage of utilising temporal "},"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":"2111.01024","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2021-11-01T15:27:35Z","cross_cats_sorted":["cs.SD","eess.AS"],"title_canon_sha256":"0e954f6203ef570eb6b59fc1abeab30c1b2f83f1f8688e7e94b3e18ed0fa9922","abstract_canon_sha256":"0bafd0ce230aa298a96f539fe1d91fad6e77f575e5883fa2d74567051a0d5a2a"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T03:27:52.751190Z","signature_b64":"0bTwTGpiBBmiclNCEU8lO6yzaUxbTJnKwm6lgG7Dy+uXinThP95RIq54IPCGuanaCLDCJjnQkSyYE2OrLuFjBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"c71f62e7689f58a2d33f8379de77f04a768e299a3f85e504c0ec0864b5171ba7","last_reissued_at":"2026-07-05T03:27:52.750664Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T03:27:52.750664Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"With a Little Help from my Temporal Context: Multimodal Egocentric Action Recognition","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.SD","eess.AS"],"primary_cat":"cs.CV","authors_text":"Andrew Zisserman, Arsha Nagrani, Dima Damen, Evangelos Kazakos, Jaesung Huh","submitted_at":"2021-11-01T15:27:35Z","abstract_excerpt":"In egocentric videos, actions occur in quick succession. We capitalise on the action's temporal context and propose a method that learns to attend to surrounding actions in order to improve recognition performance. To incorporate the temporal context, we propose a transformer-based multimodal model that ingests video and audio as input modalities, with an explicit language model providing action sequence context to enhance the predictions. We test our approach on EPIC-KITCHENS and EGTEA datasets reporting state-of-the-art performance. Our ablations showcase the advantage of utilising temporal "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2111.01024","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/2111.01024/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":"2111.01024","created_at":"2026-07-05T03:27:52.750724+00:00"},{"alias_kind":"arxiv_version","alias_value":"2111.01024v1","created_at":"2026-07-05T03:27:52.750724+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2111.01024","created_at":"2026-07-05T03:27:52.750724+00:00"},{"alias_kind":"pith_short_12","alias_value":"Y4PWFZ3IT5MK","created_at":"2026-07-05T03:27:52.750724+00:00"},{"alias_kind":"pith_short_16","alias_value":"Y4PWFZ3IT5MKFUZ7","created_at":"2026-07-05T03:27:52.750724+00:00"},{"alias_kind":"pith_short_8","alias_value":"Y4PWFZ3I","created_at":"2026-07-05T03:27:52.750724+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2507.10977","citing_title":"Conceptualizing Multi-scale Wavelet Attention and Ray-based Encoding for Human-Object Interaction Detection","ref_index":4,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/Y4PWFZ3IT5MKFUZ7QN45457QJJ","json":"https://pith.science/pith/Y4PWFZ3IT5MKFUZ7QN45457QJJ.json","graph_json":"https://pith.science/api/pith-number/Y4PWFZ3IT5MKFUZ7QN45457QJJ/graph.json","events_json":"https://pith.science/api/pith-number/Y4PWFZ3IT5MKFUZ7QN45457QJJ/events.json","paper":"https://pith.science/paper/Y4PWFZ3I"},"agent_actions":{"view_html":"https://pith.science/pith/Y4PWFZ3IT5MKFUZ7QN45457QJJ","download_json":"https://pith.science/pith/Y4PWFZ3IT5MKFUZ7QN45457QJJ.json","view_paper":"https://pith.science/paper/Y4PWFZ3I","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2111.01024&json=true","fetch_graph":"https://pith.science/api/pith-number/Y4PWFZ3IT5MKFUZ7QN45457QJJ/graph.json","fetch_events":"https://pith.science/api/pith-number/Y4PWFZ3IT5MKFUZ7QN45457QJJ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/Y4PWFZ3IT5MKFUZ7QN45457QJJ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/Y4PWFZ3IT5MKFUZ7QN45457QJJ/action/storage_attestation","attest_author":"https://pith.science/pith/Y4PWFZ3IT5MKFUZ7QN45457QJJ/action/author_attestation","sign_citation":"https://pith.science/pith/Y4PWFZ3IT5MKFUZ7QN45457QJJ/action/citation_signature","submit_replication":"https://pith.science/pith/Y4PWFZ3IT5MKFUZ7QN45457QJJ/action/replication_record"}},"created_at":"2026-07-05T03:27:52.750724+00:00","updated_at":"2026-07-05T03:27:52.750724+00:00"}