{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2021:2RXIEVKWNC47NZ5A2Q6L2K432S","short_pith_number":"pith:2RXIEVKW","canonical_record":{"source":{"id":"2111.08910","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SD","submitted_at":"2021-11-17T05:22:22Z","cross_cats_sorted":["cs.MM","eess.AS"],"title_canon_sha256":"edc57f36d03f576c1e02fbb947af2be252b97b2f550317c398e6aa1d647f0cad","abstract_canon_sha256":"f65201b8187db6011211311112032c81d9df7e663d529fbfb75885c705865efd"},"schema_version":"1.0"},"canonical_sha256":"d46e82555668b9f6e7a0d43cbd2b9bd4b9e02662f482f280efda389deffe8c77","source":{"kind":"arxiv","id":"2111.08910","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2111.08910","created_at":"2026-07-05T03:32:42Z"},{"alias_kind":"arxiv_version","alias_value":"2111.08910v1","created_at":"2026-07-05T03:32:42Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2111.08910","created_at":"2026-07-05T03:32:42Z"},{"alias_kind":"pith_short_12","alias_value":"2RXIEVKWNC47","created_at":"2026-07-05T03:32:42Z"},{"alias_kind":"pith_short_16","alias_value":"2RXIEVKWNC47NZ5A","created_at":"2026-07-05T03:32:42Z"},{"alias_kind":"pith_short_8","alias_value":"2RXIEVKW","created_at":"2026-07-05T03:32:42Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2021:2RXIEVKWNC47NZ5A2Q6L2K432S","target":"record","payload":{"canonical_record":{"source":{"id":"2111.08910","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SD","submitted_at":"2021-11-17T05:22:22Z","cross_cats_sorted":["cs.MM","eess.AS"],"title_canon_sha256":"edc57f36d03f576c1e02fbb947af2be252b97b2f550317c398e6aa1d647f0cad","abstract_canon_sha256":"f65201b8187db6011211311112032c81d9df7e663d529fbfb75885c705865efd"},"schema_version":"1.0"},"canonical_sha256":"d46e82555668b9f6e7a0d43cbd2b9bd4b9e02662f482f280efda389deffe8c77","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T03:32:42.458325Z","signature_b64":"fQgzcsIyAEKbVhh1Ivdxg52PW/ztvXvLV6p0VhaBbMLZovYgLgb9wQh+4meQVCR3kW3OOcS6Oiga0tEL2ZCnCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"d46e82555668b9f6e7a0d43cbd2b9bd4b9e02662f482f280efda389deffe8c77","last_reissued_at":"2026-07-05T03:32:42.457704Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T03:32:42.457704Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2111.08910","source_version":1,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T03:32:42Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"4+k1yTfuqFKifIUI6b6aLlOG1v0x9MorvhGGr0B7qBmaFwyLS5c6UbOjVbpjPEnL0oavtyu6WtHinmCzIC2sCA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-23T00:15:52.470269Z"},"content_sha256":"520dd5fdf254bf447c673b21fe62d66a61d6ddb8ca08b5c42989a5549c2b308c","schema_version":"1.0","event_id":"sha256:520dd5fdf254bf447c673b21fe62d66a61d6ddb8ca08b5c42989a5549c2b308c"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2021:2RXIEVKWNC47NZ5A2Q6L2K432S","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Information Fusion in Attention Networks Using Adaptive and Multi-level Factorized Bilinear Pooling for Audio-visual Emotion Recognition","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.MM","eess.AS"],"primary_cat":"cs.SD","authors_text":"Chin-Hui Lee, Hengshun Zhou, Jun Du, Qing-Feng Liu, Qing Wang, Yuanyuan Zhang","submitted_at":"2021-11-17T05:22:22Z","abstract_excerpt":"Multimodal emotion recognition is a challenging task in emotion computing as it is quite difficult to extract discriminative features to identify the subtle differences in human emotions with abstract concept and multiple expressions. Moreover, how to fully utilize both audio and visual information is still an open problem. In this paper, we propose a novel multimodal fusion attention network for audio-visual emotion recognition based on adaptive and multi-level factorized bilinear pooling (FBP). First, for the audio stream, a fully convolutional network (FCN) equipped with 1-D attention mecha"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2111.08910","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/2111.08910/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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T03:32:42Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"v2PMTKmvJ9nZidOa3lVnwuDhPPDvG8sfmoSJiahrrs8zFRcJz/EvjNE8PdcwfLyIlWfT31C5kn51z7P266cqBw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-23T00:15:52.470776Z"},"content_sha256":"10554661b1f18e42758acc21a6084effbe686758f928d2b44f43703ae0b18bc4","schema_version":"1.0","event_id":"sha256:10554661b1f18e42758acc21a6084effbe686758f928d2b44f43703ae0b18bc4"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/2RXIEVKWNC47NZ5A2Q6L2K432S/bundle.json","state_url":"https://pith.science/pith/2RXIEVKWNC47NZ5A2Q6L2K432S/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/2RXIEVKWNC47NZ5A2Q6L2K432S/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-08-23T00:15:52Z","links":{"resolver":"https://pith.science/pith/2RXIEVKWNC47NZ5A2Q6L2K432S","bundle":"https://pith.science/pith/2RXIEVKWNC47NZ5A2Q6L2K432S/bundle.json","state":"https://pith.science/pith/2RXIEVKWNC47NZ5A2Q6L2K432S/state.json","well_known_bundle":"https://pith.science/.well-known/pith/2RXIEVKWNC47NZ5A2Q6L2K432S/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2021:2RXIEVKWNC47NZ5A2Q6L2K432S","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":"f65201b8187db6011211311112032c81d9df7e663d529fbfb75885c705865efd","cross_cats_sorted":["cs.MM","eess.AS"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SD","submitted_at":"2021-11-17T05:22:22Z","title_canon_sha256":"edc57f36d03f576c1e02fbb947af2be252b97b2f550317c398e6aa1d647f0cad"},"schema_version":"1.0","source":{"id":"2111.08910","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2111.08910","created_at":"2026-07-05T03:32:42Z"},{"alias_kind":"arxiv_version","alias_value":"2111.08910v1","created_at":"2026-07-05T03:32:42Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2111.08910","created_at":"2026-07-05T03:32:42Z"},{"alias_kind":"pith_short_12","alias_value":"2RXIEVKWNC47","created_at":"2026-07-05T03:32:42Z"},{"alias_kind":"pith_short_16","alias_value":"2RXIEVKWNC47NZ5A","created_at":"2026-07-05T03:32:42Z"},{"alias_kind":"pith_short_8","alias_value":"2RXIEVKW","created_at":"2026-07-05T03:32:42Z"}],"graph_snapshots":[{"event_id":"sha256:10554661b1f18e42758acc21a6084effbe686758f928d2b44f43703ae0b18bc4","target":"graph","created_at":"2026-07-05T03:32:42Z","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/2111.08910/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Multimodal emotion recognition is a challenging task in emotion computing as it is quite difficult to extract discriminative features to identify the subtle differences in human emotions with abstract concept and multiple expressions. Moreover, how to fully utilize both audio and visual information is still an open problem. In this paper, we propose a novel multimodal fusion attention network for audio-visual emotion recognition based on adaptive and multi-level factorized bilinear pooling (FBP). First, for the audio stream, a fully convolutional network (FCN) equipped with 1-D attention mecha","authors_text":"Chin-Hui Lee, Hengshun Zhou, Jun Du, Qing-Feng Liu, Qing Wang, Yuanyuan Zhang","cross_cats":["cs.MM","eess.AS"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SD","submitted_at":"2021-11-17T05:22:22Z","title":"Information Fusion in Attention Networks Using Adaptive and Multi-level Factorized Bilinear Pooling for Audio-visual Emotion Recognition"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2111.08910","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":"sha256:520dd5fdf254bf447c673b21fe62d66a61d6ddb8ca08b5c42989a5549c2b308c","target":"record","created_at":"2026-07-05T03:32:42Z","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":"f65201b8187db6011211311112032c81d9df7e663d529fbfb75885c705865efd","cross_cats_sorted":["cs.MM","eess.AS"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SD","submitted_at":"2021-11-17T05:22:22Z","title_canon_sha256":"edc57f36d03f576c1e02fbb947af2be252b97b2f550317c398e6aa1d647f0cad"},"schema_version":"1.0","source":{"id":"2111.08910","kind":"arxiv","version":1}},"canonical_sha256":"d46e82555668b9f6e7a0d43cbd2b9bd4b9e02662f482f280efda389deffe8c77","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"d46e82555668b9f6e7a0d43cbd2b9bd4b9e02662f482f280efda389deffe8c77","first_computed_at":"2026-07-05T03:32:42.457704Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T03:32:42.457704Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"fQgzcsIyAEKbVhh1Ivdxg52PW/ztvXvLV6p0VhaBbMLZovYgLgb9wQh+4meQVCR3kW3OOcS6Oiga0tEL2ZCnCg==","signature_status":"signed_v1","signed_at":"2026-07-05T03:32:42.458325Z","signed_message":"canonical_sha256_bytes"},"source_id":"2111.08910","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:520dd5fdf254bf447c673b21fe62d66a61d6ddb8ca08b5c42989a5549c2b308c","sha256:10554661b1f18e42758acc21a6084effbe686758f928d2b44f43703ae0b18bc4"],"state_sha256":"fc942f107ade2beafa72d072c359144c5ac39fed4575691f405d547cbbee2af0"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"PYqtFdFC2H8PPYubV3K99Vkaj2GrdHohlCQrYI+ApkqxLA3/bFdygQSLRpFWDi2SVlhAy3+A2FZt6YzqO/7gAQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-23T00:15:52.475989Z","bundle_sha256":"c05a12228f415d5f0dfebdab2d6637962dfebb2ce3630af7b51c745901048ace"}}