{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2020:7XOE6IMWQ2EB42N62RX4KR43VB","short_pith_number":"pith:7XOE6IMW","schema_version":"1.0","canonical_sha256":"fddc4f219686881e69bed46fc5479ba863212b8a583c409fb8df899946aab9dc","source":{"kind":"arxiv","id":"2012.05689","version":1},"attestation_state":"computed","paper":{"title":"Interactive Fusion of Multi-level Features for Compositional Activity Recognition","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Jinhui Tang, Lingxi Xie, Rui Yan, Xiangbo Shu","submitted_at":"2020-12-10T14:17:18Z","abstract_excerpt":"To understand a complex action, multiple sources of information, including appearance, positional, and semantic features, need to be integrated. However, these features are difficult to be fused since they often differ significantly in modality and dimensionality. In this paper, we present a novel framework that accomplishes this goal by interactive fusion, namely, projecting features across different spaces and guiding it using an auxiliary prediction task. Specifically, we implement the framework in three steps, namely, positional-to-appearance feature extraction, semantic feature interactio"},"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":"2012.05689","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2020-12-10T14:17:18Z","cross_cats_sorted":[],"title_canon_sha256":"c5e8f4f0f51ea5612692dceb5f697bd96c57c768f5f0e9a0e4f796acbc4b948a","abstract_canon_sha256":"df0cfe36159488deff2f7cda1efbbbdd81de15dea6867fc52a5be2b1b3b79433"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T01:58:36.073275Z","signature_b64":"cEv5Nvj4jPDOfP2aT8cCmL7/57rYv7Lm6DlWED8UR0bOQU9y3C7Dy6dDR0WdavMxk1bZkJ1ASzn9jGOCZHGQCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"fddc4f219686881e69bed46fc5479ba863212b8a583c409fb8df899946aab9dc","last_reissued_at":"2026-07-05T01:58:36.072767Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T01:58:36.072767Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Interactive Fusion of Multi-level Features for Compositional Activity Recognition","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Jinhui Tang, Lingxi Xie, Rui Yan, Xiangbo Shu","submitted_at":"2020-12-10T14:17:18Z","abstract_excerpt":"To understand a complex action, multiple sources of information, including appearance, positional, and semantic features, need to be integrated. However, these features are difficult to be fused since they often differ significantly in modality and dimensionality. In this paper, we present a novel framework that accomplishes this goal by interactive fusion, namely, projecting features across different spaces and guiding it using an auxiliary prediction task. Specifically, we implement the framework in three steps, namely, positional-to-appearance feature extraction, semantic feature interactio"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2012.05689","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/2012.05689/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":"2012.05689","created_at":"2026-07-05T01:58:36.072819+00:00"},{"alias_kind":"arxiv_version","alias_value":"2012.05689v1","created_at":"2026-07-05T01:58:36.072819+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2012.05689","created_at":"2026-07-05T01:58:36.072819+00:00"},{"alias_kind":"pith_short_12","alias_value":"7XOE6IMWQ2EB","created_at":"2026-07-05T01:58:36.072819+00:00"},{"alias_kind":"pith_short_16","alias_value":"7XOE6IMWQ2EB42N6","created_at":"2026-07-05T01:58:36.072819+00:00"},{"alias_kind":"pith_short_8","alias_value":"7XOE6IMW","created_at":"2026-07-05T01:58:36.072819+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/7XOE6IMWQ2EB42N62RX4KR43VB","json":"https://pith.science/pith/7XOE6IMWQ2EB42N62RX4KR43VB.json","graph_json":"https://pith.science/api/pith-number/7XOE6IMWQ2EB42N62RX4KR43VB/graph.json","events_json":"https://pith.science/api/pith-number/7XOE6IMWQ2EB42N62RX4KR43VB/events.json","paper":"https://pith.science/paper/7XOE6IMW"},"agent_actions":{"view_html":"https://pith.science/pith/7XOE6IMWQ2EB42N62RX4KR43VB","download_json":"https://pith.science/pith/7XOE6IMWQ2EB42N62RX4KR43VB.json","view_paper":"https://pith.science/paper/7XOE6IMW","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2012.05689&json=true","fetch_graph":"https://pith.science/api/pith-number/7XOE6IMWQ2EB42N62RX4KR43VB/graph.json","fetch_events":"https://pith.science/api/pith-number/7XOE6IMWQ2EB42N62RX4KR43VB/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/7XOE6IMWQ2EB42N62RX4KR43VB/action/timestamp_anchor","attest_storage":"https://pith.science/pith/7XOE6IMWQ2EB42N62RX4KR43VB/action/storage_attestation","attest_author":"https://pith.science/pith/7XOE6IMWQ2EB42N62RX4KR43VB/action/author_attestation","sign_citation":"https://pith.science/pith/7XOE6IMWQ2EB42N62RX4KR43VB/action/citation_signature","submit_replication":"https://pith.science/pith/7XOE6IMWQ2EB42N62RX4KR43VB/action/replication_record"}},"created_at":"2026-07-05T01:58:36.072819+00:00","updated_at":"2026-07-05T01:58:36.072819+00:00"}