{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:2VIIOY5ZQW3K5HFUVMVMTKMGZ6","short_pith_number":"pith:2VIIOY5Z","schema_version":"1.0","canonical_sha256":"d5508763b985b6ae9cb4ab2ac9a986cf9c7849782855eca378f2d467703a46b4","source":{"kind":"arxiv","id":"2207.13434","version":1},"attestation_state":"computed","paper":{"title":"End-To-End Audiovisual Feature Fusion for Active Speaker Detection","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CV","cs.MM","eess.AS"],"primary_cat":"cs.SD","authors_text":"Fiseha B. Tesema, Hong Wu, Jason Gu, Shiqiang Zhu, Wei Song, Zheyuan Lin","submitted_at":"2022-07-27T10:25:59Z","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"},"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":"2207.13434","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SD","submitted_at":"2022-07-27T10:25:59Z","cross_cats_sorted":["cs.CV","cs.MM","eess.AS"],"title_canon_sha256":"73d1eacb1b6a9bb31048d23d1746b8dbb90443df418b53810e3fad8249b388d9","abstract_canon_sha256":"be3a2a4720880b53ac0ed7803c5c62adc38b8bdedabade76f44ebc922752e6f9"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:18:48.034587Z","signature_b64":"Qp/Ffg4c2oFoU2rsvjd9YN4wGhafd8uifEFWoyVUK02IfvGsn+Wqhd0E2lH4DqnhLl4V0g8tcsM36e89PWAwBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"d5508763b985b6ae9cb4ab2ac9a986cf9c7849782855eca378f2d467703a46b4","last_reissued_at":"2026-07-05T05:18:48.034141Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:18:48.034141Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"End-To-End Audiovisual Feature Fusion for Active Speaker Detection","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CV","cs.MM","eess.AS"],"primary_cat":"cs.SD","authors_text":"Fiseha B. Tesema, Hong Wu, Jason Gu, Shiqiang Zhu, Wei Song, Zheyuan Lin","submitted_at":"2022-07-27T10:25:59Z","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"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2207.13434","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/2207.13434/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":"2207.13434","created_at":"2026-07-05T05:18:48.034190+00:00"},{"alias_kind":"arxiv_version","alias_value":"2207.13434v1","created_at":"2026-07-05T05:18:48.034190+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2207.13434","created_at":"2026-07-05T05:18:48.034190+00:00"},{"alias_kind":"pith_short_12","alias_value":"2VIIOY5ZQW3K","created_at":"2026-07-05T05:18:48.034190+00:00"},{"alias_kind":"pith_short_16","alias_value":"2VIIOY5ZQW3K5HFU","created_at":"2026-07-05T05:18:48.034190+00:00"},{"alias_kind":"pith_short_8","alias_value":"2VIIOY5Z","created_at":"2026-07-05T05:18:48.034190+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/2VIIOY5ZQW3K5HFUVMVMTKMGZ6","json":"https://pith.science/pith/2VIIOY5ZQW3K5HFUVMVMTKMGZ6.json","graph_json":"https://pith.science/api/pith-number/2VIIOY5ZQW3K5HFUVMVMTKMGZ6/graph.json","events_json":"https://pith.science/api/pith-number/2VIIOY5ZQW3K5HFUVMVMTKMGZ6/events.json","paper":"https://pith.science/paper/2VIIOY5Z"},"agent_actions":{"view_html":"https://pith.science/pith/2VIIOY5ZQW3K5HFUVMVMTKMGZ6","download_json":"https://pith.science/pith/2VIIOY5ZQW3K5HFUVMVMTKMGZ6.json","view_paper":"https://pith.science/paper/2VIIOY5Z","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2207.13434&json=true","fetch_graph":"https://pith.science/api/pith-number/2VIIOY5ZQW3K5HFUVMVMTKMGZ6/graph.json","fetch_events":"https://pith.science/api/pith-number/2VIIOY5ZQW3K5HFUVMVMTKMGZ6/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/2VIIOY5ZQW3K5HFUVMVMTKMGZ6/action/timestamp_anchor","attest_storage":"https://pith.science/pith/2VIIOY5ZQW3K5HFUVMVMTKMGZ6/action/storage_attestation","attest_author":"https://pith.science/pith/2VIIOY5ZQW3K5HFUVMVMTKMGZ6/action/author_attestation","sign_citation":"https://pith.science/pith/2VIIOY5ZQW3K5HFUVMVMTKMGZ6/action/citation_signature","submit_replication":"https://pith.science/pith/2VIIOY5ZQW3K5HFUVMVMTKMGZ6/action/replication_record"}},"created_at":"2026-07-05T05:18:48.034190+00:00","updated_at":"2026-07-05T05:18:48.034190+00:00"}