{"doi":"10.1587/transinf.2019edl8103","title":"Gradient-Enhanced Softmax for Face Recognition","abstract":null,"journal":"IEICE Transactions on Information and Systems","year":2020,"id":647285,"datarank":0.5333022092234121,"base_score":3.5553480614894135,"endowment":3.5553480614894135,"self_citation_contribution":0.5333022092234121,"citation_network_contribution":0.0,"self_endowment_contribution":0.5333022092234121,"citer_contribution":0.0,"corpus_percentile":null,"corpus_rank":null,"citation_count":34,"citer_count":0,"citers_with_citation_signal":0,"citers_with_endowment":0,"datacite_reuse_total":0,"is_dataset":false,"is_dataset_confidence":null,"is_data_producer":false,"deposit_databanks":null,"is_oa":false,"file_count":0,"downloads":0,"has_version_chain":false,"published_date":null,"fair_score":null,"fair_percentile":null,"algorithm_id":"datarank_citation_only_1hop_v6","ranking_scope":"data_only","authors":[{"id":1686302,"name":"Weijun LI","orcid":null,"position":1,"is_corresponding":false},{"id":1686303,"name":"Xin NING","orcid":null,"position":2,"is_corresponding":false},{"id":1686304,"name":"Liping ZHANG","orcid":null,"position":3,"is_corresponding":false},{"id":1686305,"name":"Xiaoli DONG","orcid":null,"position":4,"is_corresponding":false},{"id":1686306,"name":"Wei HE","orcid":null,"position":5,"is_corresponding":false},{"id":1686300,"name":"Linjun SUN","orcid":null,"position":0,"is_corresponding":false}],"reference_count":0,"raw_metadata":{"has_enrichment":true,"resolved":true,"title":"Gradient-Enhanced Softmax for Face Recognition","abstract":"This letter proposes a gradient-enhanced softmax supervisor for face recognition (FR) based on a deep convolutional neural network (DCNN). The proposed supervisor conducts the constant-normalized cosine to obtain the score for each class using a combination of the intra-class score and the soft maximum of the inter-class scores as the objective function. This mitigates the vanishing gradient problem in the conventional softmax classifier. The experiments on the public Labeled Faces in the Wild (LFW) database denote that the proposed supervisor achieves better results when compared with those achieved using the current state-of-the-art softmax-based approaches for FR.","is_dataset_classified":null,"base_score":3.5553480614894135,"endowment":3.5553480614894135,"datacite_reuse_total":0,"file_count":0,"downloads":0,"views":0,"has_version_chain":false,"is_dataset":false,"is_oa":false,"pmid":"19767382","pmcid":null,"openalex_id":"https://openalex.org/W3022820045","authors":[],"funders":[],"total_grants":0,"fwci":3.1733,"citation_percentile":0.92717013,"influential_citations":0,"citation_trend":[{"year":2021,"count":22},{"year":2022,"count":4},{"year":2023,"count":7},{"year":2024,"count":1}],"oa_status":"gold","license":null,"oa_locations":[{"url":"https://www.jstage.jst.go.jp/article/transinf/E103.D/5/E103.D_2019EDL8103/_pdf","host_type":"journal"},{"url":"https://www.jstage.jst.go.jp/article/transinf/E103.D/5/E103.D_2019EDL8103/_pdf","host_type":"publisher"},{"url":"https://doi.org/10.1587/transinf.2019edl8103","host_type":"journal"}],"fields_of_study":["Face recognition and analysis","Face and Expression Recognition","Biometric Identification and Security"],"mesh_terms":[],"keywords":["Softmax function","Supervisor","Computer science","Classifier (UML)","Convolutional neural network","Artificial intelligence","Pattern recognition (psychology)","Facial recognition system","Face (sociological concept)","Class (philosophy)","Trigonometric functions","Mathematics"],"sdg_mappings":[],"linked_datasets":[],"clinical_trials":[],"software_tools":[],"database_accessions":[],"source":"live","citation_network_status":"fetched"},"created_at":"2026-08-09T17:44:19.839562Z","pmid":null,"pmcid":null,"fwci":null,"citation_percentile":null,"influential_citations":0,"oa_status":null,"license":null,"views":0,"total_file_size_bytes":0,"version_count":0,"fair_f":null,"fair_a":null,"fair_i":null,"fair_r":null,"fair_zscore":null,"fair_rationale":null,"fair_model":null,"fair_agent_version":null,"fair_fulltext_source":null,"fair_has_llm":null,"fair_computed_at":null,"clinical_trials":[],"software_tools":[],"db_accessions":[],"linked_datasets":[],"topics":[]}