{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2022:2VIIOY5ZQW3K5HFUVMVMTKMGZ6","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"be3a2a4720880b53ac0ed7803c5c62adc38b8bdedabade76f44ebc922752e6f9","cross_cats_sorted":["cs.CV","cs.MM","eess.AS"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SD","submitted_at":"2022-07-27T10:25:59Z","title_canon_sha256":"73d1eacb1b6a9bb31048d23d1746b8dbb90443df418b53810e3fad8249b388d9"},"schema_version":"1.0","source":{"id":"2207.13434","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2207.13434","created_at":"2026-07-05T05:18:48Z"},{"alias_kind":"arxiv_version","alias_value":"2207.13434v1","created_at":"2026-07-05T05:18:48Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2207.13434","created_at":"2026-07-05T05:18:48Z"},{"alias_kind":"pith_short_12","alias_value":"2VIIOY5ZQW3K","created_at":"2026-07-05T05:18:48Z"},{"alias_kind":"pith_short_16","alias_value":"2VIIOY5ZQW3K5HFU","created_at":"2026-07-05T05:18:48Z"},{"alias_kind":"pith_short_8","alias_value":"2VIIOY5Z","created_at":"2026-07-05T05:18:48Z"}],"graph_snapshots":[{"event_id":"sha256:0de307e8a95213c0c46f600ade5d02eb6eb9c13ee7f0f9cd25513fe3cd5a472e","target":"graph","created_at":"2026-07-05T05:18:48Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2207.13434/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Active speaker detection plays a vital role in human-machine interaction. Recently, a few end-to-end audiovisual frameworks emerged. However, these models' inference time was not explored and are not applicable for real-time applications due to their complexity and large input size. In addition, they explored a similar feature extraction strategy that employs the ConvNet on audio and visual inputs. This work presents a novel two-stream end-to-end framework fusing features extracted from images via VGG-M with raw Mel Frequency Cepstrum Coefficients features extracted from the audio waveform. Th","authors_text":"Fiseha B. Tesema, Hong Wu, Jason Gu, Shiqiang Zhu, Wei Song, Zheyuan Lin","cross_cats":["cs.CV","cs.MM","eess.AS"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SD","submitted_at":"2022-07-27T10:25:59Z","title":"End-To-End Audiovisual Feature Fusion for Active Speaker Detection"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2207.13434","kind":"arxiv","version":1},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:178cdd62b741ca17a430b71ccff2a23c3c787f3fe252c22dc1151680d447a582","target":"record","created_at":"2026-07-05T05:18:48Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"be3a2a4720880b53ac0ed7803c5c62adc38b8bdedabade76f44ebc922752e6f9","cross_cats_sorted":["cs.CV","cs.MM","eess.AS"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SD","submitted_at":"2022-07-27T10:25:59Z","title_canon_sha256":"73d1eacb1b6a9bb31048d23d1746b8dbb90443df418b53810e3fad8249b388d9"},"schema_version":"1.0","source":{"id":"2207.13434","kind":"arxiv","version":1}},"canonical_sha256":"d5508763b985b6ae9cb4ab2ac9a986cf9c7849782855eca378f2d467703a46b4","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"d5508763b985b6ae9cb4ab2ac9a986cf9c7849782855eca378f2d467703a46b4","first_computed_at":"2026-07-05T05:18:48.034141Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T05:18:48.034141Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"Qp/Ffg4c2oFoU2rsvjd9YN4wGhafd8uifEFWoyVUK02IfvGsn+Wqhd0E2lH4DqnhLl4V0g8tcsM36e89PWAwBg==","signature_status":"signed_v1","signed_at":"2026-07-05T05:18:48.034587Z","signed_message":"canonical_sha256_bytes"},"source_id":"2207.13434","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:178cdd62b741ca17a430b71ccff2a23c3c787f3fe252c22dc1151680d447a582","sha256:0de307e8a95213c0c46f600ade5d02eb6eb9c13ee7f0f9cd25513fe3cd5a472e"],"state_sha256":"2af913e68da068ce2493c4df8c19529039acf900c66f9a5465583b03e1ef05c6"}