{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:ERG6DNFMREMOPYDCH2GL22DKBR","short_pith_number":"pith:ERG6DNFM","schema_version":"1.0","canonical_sha256":"244de1b4ac8918e7e0623e8cbd686a0c6803e585f14e1689b7bbb410fded95ac","source":{"kind":"arxiv","id":"2112.01368","version":1},"attestation_state":"computed","paper":{"title":"ScaleVLAD: Improving Multimodal Sentiment Analysis via Multi-Scale Fusion of Locally Descriptors","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.CL","authors_text":"Bin Wang, Huaishao Luo, Lei Ji, Shenggong Ji, Tianrui Li, Yanyong Huang","submitted_at":"2021-12-02T16:09:33Z","abstract_excerpt":"Fusion technique is a key research topic in multimodal sentiment analysis. The recent attention-based fusion demonstrates advances over simple operation-based fusion. However, these fusion works adopt single-scale, i.e., token-level or utterance-level, unimodal representation. Such single-scale fusion is suboptimal because that different modality should be aligned with different granularities. This paper proposes a fusion model named ScaleVLAD to gather multi-Scale representation from text, video, and audio with shared Vectors of Locally Aggregated Descriptors to improve unaligned multimodal s"},"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":"2112.01368","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2021-12-02T16:09:33Z","cross_cats_sorted":["cs.AI","cs.LG"],"title_canon_sha256":"7448092d84c8ce7d57172ce8f365aee9bba9f98dbb69cfb1d67dd44853833285","abstract_canon_sha256":"8c12614592b4bfb481df90dea5e7b332688993d03a38c83e11d25476d10c5ed9"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T03:37:08.704447Z","signature_b64":"yl3ZTHG8Om51zmS0e9bHzOsdE6+zuJ76wTLvZ/3sr4wnbB65hsHZg4LENWVbPxfeAjvuRlqWYhB/UtgM9Ex4CQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"244de1b4ac8918e7e0623e8cbd686a0c6803e585f14e1689b7bbb410fded95ac","last_reissued_at":"2026-07-05T03:37:08.703884Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T03:37:08.703884Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"ScaleVLAD: Improving Multimodal Sentiment Analysis via Multi-Scale Fusion of Locally Descriptors","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.CL","authors_text":"Bin Wang, Huaishao Luo, Lei Ji, Shenggong Ji, Tianrui Li, Yanyong Huang","submitted_at":"2021-12-02T16:09:33Z","abstract_excerpt":"Fusion technique is a key research topic in multimodal sentiment analysis. The recent attention-based fusion demonstrates advances over simple operation-based fusion. However, these fusion works adopt single-scale, i.e., token-level or utterance-level, unimodal representation. Such single-scale fusion is suboptimal because that different modality should be aligned with different granularities. This paper proposes a fusion model named ScaleVLAD to gather multi-Scale representation from text, video, and audio with shared Vectors of Locally Aggregated Descriptors to improve unaligned multimodal s"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2112.01368","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/2112.01368/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":"2112.01368","created_at":"2026-07-05T03:37:08.703949+00:00"},{"alias_kind":"arxiv_version","alias_value":"2112.01368v1","created_at":"2026-07-05T03:37:08.703949+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2112.01368","created_at":"2026-07-05T03:37:08.703949+00:00"},{"alias_kind":"pith_short_12","alias_value":"ERG6DNFMREMO","created_at":"2026-07-05T03:37:08.703949+00:00"},{"alias_kind":"pith_short_16","alias_value":"ERG6DNFMREMOPYDC","created_at":"2026-07-05T03:37:08.703949+00:00"},{"alias_kind":"pith_short_8","alias_value":"ERG6DNFM","created_at":"2026-07-05T03:37:08.703949+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2607.06611","citing_title":"Audio Sentiment Analysis via Distillation and Cross-Modal Integration of Generated Multilingual Transcripts","ref_index":27,"is_internal_anchor":true},{"citing_arxiv_id":"2409.07388","citing_title":"Recent Advances in Multimodal Affective Computing: An NLP Perspective","ref_index":203,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/ERG6DNFMREMOPYDCH2GL22DKBR","json":"https://pith.science/pith/ERG6DNFMREMOPYDCH2GL22DKBR.json","graph_json":"https://pith.science/api/pith-number/ERG6DNFMREMOPYDCH2GL22DKBR/graph.json","events_json":"https://pith.science/api/pith-number/ERG6DNFMREMOPYDCH2GL22DKBR/events.json","paper":"https://pith.science/paper/ERG6DNFM"},"agent_actions":{"view_html":"https://pith.science/pith/ERG6DNFMREMOPYDCH2GL22DKBR","download_json":"https://pith.science/pith/ERG6DNFMREMOPYDCH2GL22DKBR.json","view_paper":"https://pith.science/paper/ERG6DNFM","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2112.01368&json=true","fetch_graph":"https://pith.science/api/pith-number/ERG6DNFMREMOPYDCH2GL22DKBR/graph.json","fetch_events":"https://pith.science/api/pith-number/ERG6DNFMREMOPYDCH2GL22DKBR/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/ERG6DNFMREMOPYDCH2GL22DKBR/action/timestamp_anchor","attest_storage":"https://pith.science/pith/ERG6DNFMREMOPYDCH2GL22DKBR/action/storage_attestation","attest_author":"https://pith.science/pith/ERG6DNFMREMOPYDCH2GL22DKBR/action/author_attestation","sign_citation":"https://pith.science/pith/ERG6DNFMREMOPYDCH2GL22DKBR/action/citation_signature","submit_replication":"https://pith.science/pith/ERG6DNFMREMOPYDCH2GL22DKBR/action/replication_record"}},"created_at":"2026-07-05T03:37:08.703949+00:00","updated_at":"2026-07-05T03:37:08.703949+00:00"}