APSIPA 2021
Authors
Paper Submission
Paper Kit
Program
Technical Program
Paper Search
Presentation Instructions
Presentation Instructions
Presentation Upload
Sponsors
APSIPA 2021 Attendee Access
Technical Program
Session OD-MLDA
Paper OD-MLDA.4
OD-MLDA.4
Augmentation-Agnostic Regularization for Unsupervised Contrastive Learning with Its Application to Speaker Verification
Nakamasa Inoue, Tsubasa Maruyama, Keita Goto, Tokyo Institute of Technology, Japan
Session:
Machine Learning and Data Analytics
Track:
Machine Learning and Data Analytics (MLDA)
Session Time:
Thu, 16 Dec, 16:20 - 18:20 Japan Standard Time (UTC +9)
Thu, 16 Dec, 07:20 - 09:20 Coordinated Universal Time
Thu, 16 Dec, 02:20 - 04:20 Eastern Standard Time (UTC -5)
Wed, 15 Dec, 23:20 - 01:20 Pacific Standard Time (UTC -8)
Session Chair:
Jen-Tzung Chien, National Yang Ming Chiao Tung University
Presentation
Not logged in.
Not logged in.
Discussion
Not logged in.
Resources
Not logged in.
Session OD-MLDA
TH3.OD-B.1: MANDARIN SINGING VOICE SYNTHESIS WITH A PHONOLOGY-BASED DURATION MODEL
Fu-Rong Yang, Yin-Ping Cho, Shan-Hung Wu, Yi-Wen Liu, National Tsing Hua University, Taiwan; Yi-Hsuan Yang, Da-Yi Wu, Academia Sinica, Taiwan
TH3.OD-B.2: Task-Aware BERT-based Sentiment Analysis from Multiple Essences of the Text
Jia-Hao Hsu, Chung-Hsien Wu, National Cheng Kung University, Taiwan; Tsung-Hsien Yang, Chunghwa Telecom Co., Ltd., Taiwan
TH3.OD-B.3: CONVOLUTIONAL AUTOENCODER BASED DEEP LEARNING MODEL FOR IDENTIFICATION OF RED PALM WEEVIL SIGNALS
PARVATHY S. R., DEEPAK JAYAN P., NIMMY PATHROSE, RAJESH K. R., CENTRE FOR DEVELOPMENT OF ADVANCED COMPUTING, India
TH3.OD-B.4: Augmentation-Agnostic Regularization for Unsupervised Contrastive Learning with Its Application to Speaker Verification
Nakamasa Inoue, Tsubasa Maruyama, Keita Goto, Tokyo Institute of Technology, Japan
TH3.OD-B.5: Deep Learning Evaluation of a Steganographic Algorithm
Peter Eze, Parampalli Udaya, University of Melbourne, Australia
TH3.OD-B.6: FAQ RETRIEVAL USING QUESTION-AWARE GRAPH CONVOLUTIONAL NETWORK AND CONTEXTUALIZED LANGUAGE MODEL
Wan-Ting Tseng, Chin-Ying Wu, Berlin Chen, National Taiwan Normal University, Taiwan; Yung-Chang Hsu, EZAI, Taiwan
TH3.OD-B.7: 3D-GFE: A THREE-DIMENSIONAL GEOMETRIC-FEATURE EXTRACTOR FOR POINT CLOUD DATA
Yu-Chen Chou, Yen-Po Lin, Yang-Ming Yeh, Yi-Chang Lu, National Taiwan University, Taiwan
TH3.OD-B.8: ATTENTION EDGECONV FOR 3D POINT CLOUD CLASSIFICATION
Yen-Po Lin, Yang-Ming Yeh, Yu-Chen Chou, Yi-Chang Lu, National Taiwan University, Taiwan
TH3.OD-B.9: THE EFFECT OF DENSITY AND PLACEMENT OF BLE BEACONS ON INDOOR LOCATION AND MOTION DIRECTION ESTIMATION ACCURACY
Kaito Echizenya, Kazuhiro Kondo, Yamagata University, Japan
TH3.OD-B.10: MODEL-BASED SOFT ACTOR-CRITIC
Jen-Tzung Chien, Shu-Hsiang Yang, National Yang Ming Chiao Tung University, Taiwan
TH3.OD-B.11: SELF-SUPERVISED LEARNING FOR ONLINE SPEAKER DIARIZATION
Jen-Tzung Chien, Sixun Luo, National Yang Ming Chiao Tung University, Taiwan
TH3.OD-B.12: MULTI-RESOLUTION CONVOLUTIONAL RECURRENT NETWORKS
Jen-Tzung Chien, Yu-Min Huang, National Yang Ming Chiao Tung University, Taiwan
TH3.OD-B.13: NETWORK INTRUSION DETECTION WITH IMPROVED FEATURE REPRESENTATION
Geonsu Lee, Hochang Rhee, Jae Hoon Shim, Nam Ik Cho, Seoul National University, Korea, Republic of; Hyung Il Koo, AjouUniversity, Korea, Republic of
TH3.OD-B.14: 3D LANDMARK-BASED FACE DETECTION AND RECOGNITION SYSTEM FOR LARGE POSES
Ching-Tung Tang, Ching-Te Chiu, Wei-Jyun Chen, National Tsing Hua University, Taiwan
TH3.OD-B.15: ENTAILMENT METHOD BASED ON TEMPLATE SELECTION FOR CHINESE TEXT FEW-SHOT LEARNING
Zeyuan Wang, Zhiyu Wei, Lihui Zhang, Ruifan Li, Zhanyu Ma, Beijing University of Posts and Telecommunications, China
TH3.OD-B.16: IMAGE CAPTIONING BASED ON AN IMPROVED TRANSFORMER WITH IOU POSITION ENCODING
Yazhou Li, Yihui Shi, Yun Liu, Ruifan Li, Zhanyu Ma, Beijing University of Posts and Telecommunications, China