{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:MD2ULJV5UMOBWF5GNC4V7SW65E","short_pith_number":"pith:MD2ULJV5","schema_version":"1.0","canonical_sha256":"60f545a6bda31c1b17a668b95fcadee933c26edc45944a814e0d577df97a1c9e","source":{"kind":"arxiv","id":"2506.02550","version":2},"attestation_state":"computed","paper":{"title":"Technical Report for Ego4D Long-Term Action Anticipation Challenge 2025","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CV","authors_text":"Haoyu Zhang, Liqiang Nie, Meng Liu, Qiaohui Chu, Weili Guan, Yaowei Wang, Yisen Feng","submitted_at":"2025-06-03T07:36:52Z","abstract_excerpt":"In this report, we present a novel three-stage framework developed for the Ego4D Long-Term Action Anticipation (LTA) task. Inspired by recent advances in foundation models, our method consists of three stages: feature extraction, action recognition, and long-term action anticipation. First, visual features are extracted using a high-performance visual encoder. The features are then fed into a Transformer to predict verbs and nouns, with a verb-noun co-occurrence matrix incorporated to enhance recognition accuracy. Finally, the predicted verb-noun pairs are formatted as textual prompts and inpu"},"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":"2506.02550","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-06-03T07:36:52Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"daaff4428778aaee35fcb6b200d3c4ce7fcee2aca39dd48c6210ba6f07f61311","abstract_canon_sha256":"eb67caaded02475f3f1fa61758392c11dbc5e8c3dea40f0724720af6c2d76836"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:19:27.938140Z","signature_b64":"HmPd9FmuTUif9AkZeIbbx8dAMBiu3t4L982bexqvbxovX15HN+DoAlltAsnVKv5IWnx/136xpTBXA8ecjz6bCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"60f545a6bda31c1b17a668b95fcadee933c26edc45944a814e0d577df97a1c9e","last_reissued_at":"2026-07-05T11:19:27.937603Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:19:27.937603Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Technical Report for Ego4D Long-Term Action Anticipation Challenge 2025","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CV","authors_text":"Haoyu Zhang, Liqiang Nie, Meng Liu, Qiaohui Chu, Weili Guan, Yaowei Wang, Yisen Feng","submitted_at":"2025-06-03T07:36:52Z","abstract_excerpt":"In this report, we present a novel three-stage framework developed for the Ego4D Long-Term Action Anticipation (LTA) task. Inspired by recent advances in foundation models, our method consists of three stages: feature extraction, action recognition, and long-term action anticipation. First, visual features are extracted using a high-performance visual encoder. The features are then fed into a Transformer to predict verbs and nouns, with a verb-noun co-occurrence matrix incorporated to enhance recognition accuracy. Finally, the predicted verb-noun pairs are formatted as textual prompts and inpu"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2506.02550","kind":"arxiv","version":2},"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/2506.02550/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":"2506.02550","created_at":"2026-07-05T11:19:27.937661+00:00"},{"alias_kind":"arxiv_version","alias_value":"2506.02550v2","created_at":"2026-07-05T11:19:27.937661+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.02550","created_at":"2026-07-05T11:19:27.937661+00:00"},{"alias_kind":"pith_short_12","alias_value":"MD2ULJV5UMOB","created_at":"2026-07-05T11:19:27.937661+00:00"},{"alias_kind":"pith_short_16","alias_value":"MD2ULJV5UMOBWF5G","created_at":"2026-07-05T11:19:27.937661+00:00"},{"alias_kind":"pith_short_8","alias_value":"MD2ULJV5","created_at":"2026-07-05T11:19:27.937661+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":5,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.00662","citing_title":"TAP-JEPA: Frozen Future-Latent Probing and Two-Stage Score Fusion for EPIC-KITCHENS-100 Action Anticipation","ref_index":3,"is_internal_anchor":false},{"citing_arxiv_id":"2606.00694","citing_title":"FROST-STA: Frozen Dense Features for the Ego4D Short-Term Object Interaction Anticipation","ref_index":7,"is_internal_anchor":false},{"citing_arxiv_id":"2605.20901","citing_title":"VISTA: Technical Report for the Ego4D Short-Term Object Interaction Anticipation at EgoVis 2026","ref_index":1,"is_internal_anchor":false},{"citing_arxiv_id":"2605.20904","citing_title":"JFAA: Technical Report for the EPIC-KITCHENS-100 Action Anticipation Challenge at EgoVis 2026","ref_index":1,"is_internal_anchor":false},{"citing_arxiv_id":"2605.18176","citing_title":"MARS: Technical Report for the CASTLE Challenge at EgoVis 2026","ref_index":1,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/MD2ULJV5UMOBWF5GNC4V7SW65E","json":"https://pith.science/pith/MD2ULJV5UMOBWF5GNC4V7SW65E.json","graph_json":"https://pith.science/api/pith-number/MD2ULJV5UMOBWF5GNC4V7SW65E/graph.json","events_json":"https://pith.science/api/pith-number/MD2ULJV5UMOBWF5GNC4V7SW65E/events.json","paper":"https://pith.science/paper/MD2ULJV5"},"agent_actions":{"view_html":"https://pith.science/pith/MD2ULJV5UMOBWF5GNC4V7SW65E","download_json":"https://pith.science/pith/MD2ULJV5UMOBWF5GNC4V7SW65E.json","view_paper":"https://pith.science/paper/MD2ULJV5","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2506.02550&json=true","fetch_graph":"https://pith.science/api/pith-number/MD2ULJV5UMOBWF5GNC4V7SW65E/graph.json","fetch_events":"https://pith.science/api/pith-number/MD2ULJV5UMOBWF5GNC4V7SW65E/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/MD2ULJV5UMOBWF5GNC4V7SW65E/action/timestamp_anchor","attest_storage":"https://pith.science/pith/MD2ULJV5UMOBWF5GNC4V7SW65E/action/storage_attestation","attest_author":"https://pith.science/pith/MD2ULJV5UMOBWF5GNC4V7SW65E/action/author_attestation","sign_citation":"https://pith.science/pith/MD2ULJV5UMOBWF5GNC4V7SW65E/action/citation_signature","submit_replication":"https://pith.science/pith/MD2ULJV5UMOBWF5GNC4V7SW65E/action/replication_record"}},"created_at":"2026-07-05T11:19:27.937661+00:00","updated_at":"2026-07-05T11:19:27.937661+00:00"}