TimePaper IDPaper TitleAuthor Names
Award Paper Session (25 Oct)
10:3088FBR-CNN: A Feedback Recurrent Network for Video Saliency DetectionDing, Guanqun*; Imamoglu, Nevrez; Caglayan, Ali; Murakawa, Masahiro; Nakamura, Ryosuke
10:40111Learning Signal Representations for EEG Cross-Subject Channel Selection and Trial ClassificationMassi, Michela C*; Ieva, Francesca
10:50166Hierarchical graph neural nets can capture long-range interactionsRampasek, Ladislav*; Wolf, Guy
11:00167Multimodal data visualization and denoising with integrated diffusionKUCHROO, MANIK ; Godavarthi, Abhinav; Tong, Alexander Y; Wolf, Guy; Krishnaswamy, Smita*
11:1039Self-Attention for Audio Super-ResolutionCarraz Rakotonirina, Nathanael*
11:2062Noise ReTF Estimation and Removal for Low SNR Speech EnhancementBirnie, Lachlan I*; Samarasinghe, Prasanga; abhayapala, thushara; Grixti-Cheng, Daniel


Paper Session 1.1 (Oct 25)
11:3028Robustness-aware Filter Pruning for Robust Neural Networks Against Adversarial AttacksLim, Hyuntak*; Roh, Si-Dong; Park, Sangki; Chung, Ki-Seok
11:4042Differentially Private Variable Selection via the Knockoff FilterPournaderi, Mehrdad*; Xiang, Yu
11:50101TRANSFER BAYESIAN META-LEARNING VIA WEIGHTED FREE ENERGY MINIMIZATIONZhang, Yunchuan*; Jose, Sharu Theresa; Simeone, Osvaldo
12:00113Gaussian approximations of SDEs in Metropolis-adjusted Langevin AlgorithmsSärkkä, Simo*; Merkatas, Christos; Karvonen, Toni
12:10133EVALUATION OF COMPLEXITY MEASURES FOR DEEP LEARNING GENERALIZATION IN MEDICAL IMAGE ANALYSIS Vakanski, Aleksandar; Xian, Min*
12:20151Uncertain Bayesian Networks: Learning from Incomplete DataHougen, Conrad*; Kaplan, Lance; Cerutti, Federico; Hero, Alfred


Paper Session 1.2 (Oct 25)
14:0024SMALL MOVING TARGET MOT TRACKING WITH GM-PHD FILTER AND ATTENTION-BASED CNNAguilar, Camilo G*; Ortner, Mathias; Zerubia, Josiane
14:1049BayesRadar : Bayesian Metric-Kalman Filter Learning for Improved and Reliable Radar Target ClassificationDubey, Anand*; Santra, Avik; Fuchs, Jonas; Lübke, Maximilian; Weigel, Robert; Lurz, Fabian
14:2070BLOCK-WISE INTRA-PREDICTION OF IMAGING DATA BASED ON OVERFITTED NEURAL NETWORKS WITH ON-LINE LEARNINGSanchez, Victor*; Hernandez-Cabronero, Miguel; Serra-Sagrista, Joan
14:3080Convolutional Dense Neural Network based Spirometry Variable FVC Prediction using Sustained Phonationsyadav, shivani*; Gope, Dipanjan; Maheswari Krishnaswamy, Uma; Ghosh, Prasanta
14:4084About the equivalence between complex-valued and real-valued fully connected neural networks – application to PolInSAR imagesBARRACHINA, Jose Agustin; Ren, Chengfang; Vieillard, Gilles; Morisseau, Christele; Ovarlez,  Jean-Philippe*
14:5093Joint optimization of system design and reconstruction in MIMO radar imagingWeiss, Tomer*; P, N; Vedula, Sanketh; Feuer, Arie; Bronstein, Alex
15:00100DEEP LOW-DIMENSIONAL SPECTRAL IMAGE REPRESENTATION FOR COMPRESSIVE SPECTRAL RECONSTRUCTIONMonroy, Brayan *; Bacca, Jorge; Arguello, Henry
15:10120A Hybrid Model Integrating LSTM And GARCH For Bitcoin Price PredictionHe, Yiwen*; Gao, Zidi; Kuruoglu, Ercan E
15:20121Anonymizing motion sensor data through time-frequency domainRougé, Pierre*; Moukadem, Ali; Dieterlen, Alain; Boutet, Antoine; Frindel, Carole


Paper Session 1.3 (Oct 25)
16:00130Introducing K-anonymity principles to adversarial attacks for privacy protection in image classification problemsMygdalis, Vasileios*; TEFAS, ANASTASIOS; Pitas, Ioannis
16:10137A Weighted Loss Function to Predict Control Parameters for Supercontinuum Generation via Neural NetworksStucchi, Diego*; Corsini, Andrea; Genty, Goëry; Boracchi, Giacomo; Foi, Alessandro
16:20142A Semi-Supervised Generative Adversarial Network for Prediction of Genetic Disease OutcomesDavi, Caio C M *; Braga-Neto, Ulisses M.
16:30147Learning-Based UE Classification in Millimeter-Wave Cellular Systems With MobilityPjanic, Dino*; Sopasakis, Alexandros; Tufvesson, Fredrik ; Tataria, Harsh ; Reial, Andres
16:40149DETECTING NETWORK STATE IN THE PRESENCE OF VARYING LEVELS OF CONGESTIONde Fréin, Ruairí*; Izima, Obinna; Malik, Ali 
16:50159Convolutional Neural Network Denoising of Focused Ion Beam MicrographsPeng, Minxu*; Cokbas, Mertcan; Dorken Gallastegi, Unay; Ishwar, Prakash; Konrad, Janusz; Kulis, Brian; Goyal, Vivek K
17:00168A COARSE-TO-FINE OBJECT DETECTION FRAMEWORK FOR HIGH-RESOLUTION IMAGES WITH SPARSE OBJECTSLiu, Jinyan; Yan, Longbin; Chen, Jie*
17:10172DETECTION OF INSECTS IN CLASS-IMBALANCED LIDAR FIELD MEASUREMENTSVannoy, Trevor*; Scofield, Trey; Logan, Riley; Rehbein, Elizabeth; Shaw, Joseph; Whitaker, Bradley M


Paper Session 2.1 (Oct 26)
10:3010SIAMNET: SIAMESE CNN BASED SIMILARITY MODEL FOR ADVERSARIALLY GENERATED ENVIRONMENTAL SOUNDSMadhu, Aswathy*; K, Suresh 
10:4057Compression of DNNs Using Magnitude Pruning and Nonlinear Information Bottleneck TrainingNielsen, Morten Østergaard*; Ostergaard, Jan; Jensen, Jesper; Tan, Zheng-Hua
10:5075OPINION RECOMMENDATION USING COVERAGE FOR ADAPTIVE PREDICTIONGionanidis, Emmanouil*; Kotropoulos, Constantine; Ntemi, Myrsini
11:0090Not all noise is accounted equally: How differentially private learning benefits from large sampling ratesDörmann, Friedrich*; Frisk, Osvald; Andersen, Lars Nørvang; Fischer Pedersen, Christian
11:10109BI-RADS-NET: AN EXPLAINABLE MULTITASK LEARNING APPROACH FOR CANCER DIAGNOSIS IN BREAST ULTRASOUND IMAGESZhang, Boyu;  Vakanski, Aleksandar; Xian, Min*
11:20110Explainable Deep Learning Detection of Gaussian Propeller Noise with Unknown Signal-to-Noise RatioMahiout, Thomas; Fillatre, Lionel*; Deruaz Pepin, Laurent
11:30150Data-driven Learning of Geometric Scattering Modules for GNNsTong, Alexander Y*; Wenkel, Frederik; Macdonald, Kincaid; Krishnaswamy, Smita; Wolf, Guy
11:40174FEW-SHOT LEARNING VIA DEPENDENCY MAXIMIZATION AND INSTANCE DISCRIMINANT ANALYSISHou, Zejiang*; Kung, Sun-Yuan
11:5031Distributed Variational Information Bottleneck for IoT EnvironmentsAlsulaimawi, Zahir*; Liu, Huaping
12:00140PRIVACY ASSESSMENT OF FEDERATED LEARNING USING PRIVATE PERSONALIZED LAYERSJourdan, Theo; Boutet, Antoine*; Frindel, Carole
12:10180Distributed Dictionary Learning over Heterogeneous Clients using Local Adaptive DictionariesYou-De, Huang; Hong, Y.-W. Peter*
12:20107A Copula-Driven Unsupervised Learning Framework for Anomaly Detection with Multivariate Heterogeneous DataDamodaran , Swaroop*; Padmanabhan, Ram; R., Maahin; Gurugopinath, Sanjeev 


Paper Session 3.1 (Oct 27)
11:008MODEL SELECTION OF KERNEL RIDGE REGRESSION FOR EXTRAPOLATIONTanaka, Akira*; Nakamura, Masanari; Imai, Hideyuki
11:1038Adaptive Normalized LMP Estimation for Graph Signal ProcessingYan, Yi*; Adel, Radwa; Kuruoglu, Ercan E
11:2065MESSAGE PASSING-BASED INFERENCE IN THE GAMMA MIXTURE MODELPodusenko, Albert*; van Erp, Bart; Bagaev, Dmitry; Senoz, Ismail; de Vries, Bert
11:3092Estimating Partially Observed Graph Signals by Learning Spectrally Concentrated Graph KernelsTurhan, Gulce; Vural, Elif*
11:40116Random Feature Approximation for Online Nonlinear Graph Topology IdentificationMoney, Rohan T.*; Krishnan, Joshin; Beferull-Lozano, Baltasar
11:50124Learning Parametric Time-Vertex Graph Processes from Incomplete RealizationsGuneyi, Eylem Tugce; Canbolat, Abdullah; Vural, Elif*
12:00141GRAPH-BASED TRANSFORM BASED ON NEURAL NETWORKS FOR INTRA-PREDICTION OF IMAGING DATARoy, Debaleena*; Guha, Tanaya; Sanchez, Victor
12:10158Multimodal Graph Coarsening for Interpretable, MRI-Based Brain Graph Neural NetworkSebenius, Isaac*; Campbell, Alex; Morgan, Sarah; Bullmore, Edward; Lió, Pietro
12:20163Tracking of quantized signals based on online kernel regressionRuiz-Moreno, Emilio*; Beferull-Lozano, Baltasar


Paper Session 3.2 (Oct 27)
14:0047Preferential batch Bayesian optimizationSiivola, Eero*; Dhaka, Akash Kumar; Andersen, Michael; Gonzalez, Javier; Moreno, Pablo; Vehtari, Aki
14:1052A DEEP Q-NETWORK BASED APPROACH FOR ONLINE BAYESIAN CHANGE POINT DETECTIONMa, Xiaochuan*; Lai, Lifeng; Cui, Shuguang
14:2053Bayesian Two-stage Sequential Change Diagnosis via multi-sensor arrayMa, Xiaochuan*; Lai, Lifeng; Cui, Shuguang
14:3095A GENERAL PARAMETRIZATION FRAMEWORK FOR PAIRWISE MARKOV MODELS: AN APPLICATION TO UNSUPERVISED IMAGE SEGMENTATIONGangloff, Hugo*; Morales, Katherine; Petetin, Yohan
14:40183Self-trained video anomaly detection based on Teacher-Student modelWang, Xusheng; Pei, Mingtao*; nie, zhengang
14:50185RECOGNIZING ACTIVITIES FROM EGOCENTRIC IMAGES WITH APPEARANCE AND MOTION FEATURESChen, Yanhua; Pei, Mingtao*; nie, zhengang
15:00186EARLY FUSION GRAPH CONVOLUTIONAL NETWORK FOR SKELETON-BASED ACTION RECOGNITIONzhao, xiaoxue*; Liu, Cuiwei; Shi, Xiangbin
15:10187LIGHTWEIGHT FOREST FIRE DETECTION BASED ON DEEP LEARNINGFan, Ruixian; Pei, Mingtao*
15:20189OBJECT DETECTION IN SAR VIA GENERATIVE KNOWLEDGE TRANSFERLou, Xin*; Wang, Han


Paper Session 3.3 (Oct 27)
16:0055L3DAS21 Challenge: Machine Learning for 3D Audio Signal ProcessingGuizzo, Eric*; Comminiello, Danilo
16:10156Optimizing Time Domain Fully Convolutional Networks for 3D Speech Enhancement in a Reverberant Environment Using Perceptual LossesGuimarães, Heitor R*; Beccaro, Wesley; Arjona Ramírez, Miguel
16:20182A NEURAL BEAMFORMING NETWORK FOR B-FORMAT 3D SPEECH ENHANCEMENT AND RECOGNITIONRen, Xinlei*; Chen, Lianwu; Zheng, Xiguang; Xu, Chenglin; Zhang, Xu; Zhang, Chen; Guo, Liang; Yu, Bing
16:30190Optimized Spatial Matching for Visual Object TrackingFuxiang, Wang*
16:40191An improved DiracNet convolutional neural network for haze visibility detectionXiyu, Mu*; Qi, Xu; Qiang, Zhang; Junchi, Ren; Hongbin, Wang; Linyi, Zhou
16:50194REAL-TIME OPTIMIZING WEIGHTED GAUSSIAN CURVATURE FOR 4K VIDEOSTang, Wenming*; Gong, Yuanhao; Zhou, LeBin
17:00198CONTENT-BASED RECOMMENDATION USING MACHINE LEARNINGTai, Yifan *; Sun, Zhenyu; Yao, Zixuan
17:10200A placement angle detection method of recyclable object for garbage power generationcai, yong*; chen, mengwei; feng, yifei; ming, zheng


Paper Session 4.1 (Oct 28)
9:3012A Unified PAC-Bayesian Framework for Machine Unlearning via Information Risk MinimizationJose, Sharu Theresa*; Simeone, Osvaldo
9:4060Beyond the bias variance trade-off: a mutual information trade-off in deep learningLAN, XINJIE*; Zhu, Bin; Boncelet, Charles; Barner, Kenneth
9:50131Toward minimal-sufficiency in regression tasks: An approach based on a variational estimation bottleneckLyu, Zhaoyan*; Aminian, Gholamali; Rodrigues, Miguel
10:003Understanding Linear Style Transfer Auto-encodersPradhan, Ian; Lyu, Siwei*
10:1032An empirical comparison of joint-training and pre-training for domain-agnostic semi-supervised learning via energy-based modelsSong, Yunfu; Zheng, Huahuan; Ou, Zhijian*
10:2061Affinity Mixup for Weakly Supervised Sound Event DetectionIzadi, Mohammad Rasool*; Stevenson, Robert; Kloepper, Laura
Paper Session 4.2 (Oct 28)
11:001Dynamic Graph Convolutional Network: A Topology Optimization PerspectiveDeng, Bowen*; Jiang, Aimin
11:1027GRAD-CAM GUIDED CHANNEL-SPATIAL ATTENTION MODULE FOR FINE-GRAINED VISUAL CLASSIFICATIONXu, Shuai ; Chang, Dongliang; Xie, Jiyang; Ma, Zhanyu*
11:2051Bag of Groups of Convolutional Features Model for Visual Object RecognitionSingh, Jaspreet*; singh, chandan
11:3097ADVERSARIAL PERTURBATION ATTACKS ON NESTED DICHOTOMIES CLASSIFICATION SYSTEMSAlkhouri, Ismail *; Velasquez, Alvaro; Atia, George
11:40105Scalable Community Detection in the Degree-Corrected Stochastic Block ModelHe, Yicong*; Beckus, Andre; Atia, George
11:50126Zero-Shot Motion Pattern Recognition From 4D Point-CloudsSalami, Dariush*; Sigg, Stephan
12:00160ADVERSARIAL ATTACKS ON MULTI-LEVEL FAULT DETECTION AND DIAGNOSIS SYSTEMSAwad, Akram*; Alkhouri, Ismail ; Atia, George
12:10162FAST SUBSPACE CLUSTERING ALGORITHM WITH EFFICIENT SIMILARITY-CONSTRAINED SAMPLING FOR HYPERSPECTRAL IMAGESLopez, Jhon E*; Hinojosa, Carlos; Arguello, Henry
12:20164HyPhyLearn: A Domain Adaptation-Inspired Approach to Classification Using Limited Number of Training SamplesNooraiepour, Alireza*; Bajwa, Waheed; Mandayam, Narayan


Paper Session 4.3 (Oct 28)
14:0021Deep Complex Convolutional Recurrent Network for Multi-channel Speech Enhancement and DereverberationGelderblom, Femke   B.*; Myrvoll, Tor Andre
14:1066CAESYNTH: REAL-TIME TIMBRE INTERPOLATION AND PITCH CONTROL WITH CONDITIONAL AUTOENCODERSValero Puche, Aaron; LEE, SUKHAN*
14:2073Disentangled Speech Representation Learning Based on Factorized Hierarchical Variational Autoencoder with Self-Supervised ObjectiveXie, Yuying*; Arildsen, Thomas; Tan, Zheng-Hua
14:3077MLP Singer: Towards Rapid Parallel Korean Singing Voice SynthesisTae, Jaesung*; Lee, Younggun; Kim, Hyeongju
14:4098Conditional Sound Generation Using Neural Discrete Time-Frequency Representation LearningLiu, Xubo*; Iqbal, Turab; ZHAO, Jinzheng; Huang, Qiushi; Plumbley, Mark D.; Wang, Wenwu 
14:5099Detecting cover songs with Pitch Class Key-invariant  NetworksO’Hanlon, Ken*; Benetos, Emmanouil; Dixon, Simon
15:00104SINGING FUNDAMENTAL FREQUENCY CONTOUR GENERATION USING GENERALIZED COMMAND-RESPONSE MODEL AND SCORE-CONDITIONAL VARIATIONAL AUTOENCODERSeki, Shogo*; Taga, Haruka; Toda, Tomoki
15:1063IMPROVING DEEP REINFORCEMENT LEARNING FOR FINANCIAL TRADING USING DEEP ADAPTIVE GROUP-BASED NORMALIZATIONNalmpantis, Angelos; Passalis, Nikolaos*; Tsantekidis, Avraam; TEFAS, ANASTASIOS
15:20165Model-Free Learning of Optimal Deterministic Resource Allocations in Wireless Systems via Action-Space ExplorationHashmi, Hassaan*; Kalogerias, Dionysios


Paper Session 4.4 (Oct 28)
16:0023Ambiguity-Free and Efficient Sparse Phase Retrieval from Affine Measurements under Outlier CorruptionYang, Ming-Hsun *; Hong, Y.-W. Peter; Wu, Jwo-Yuh
16:10102A Constrained Linearly involved Generalized Moreau Enhanced Model and Its Proximal Splitting AlgorithmYata, Wataru; Yamagishi, Masao; Yamada, Isao*
16:20176ADAPTIVE APPROACH FOR SPARSE REPRESENTATIONS USING THE LOCALLY COMPETITIVE ALGORITHM FOR AUDIOBahadi, Soufiyan*; Plourde, Eric; Rouat, Jean
16:3020Online DOA Estimation for Noninteger Linear Antenna Arrays in Coarray DomainChen, Yitian; Nosrati, Hamed*; Aboutanios, Elias
16:40161Two-way Spectrum Pursuit for CUR Decomposition and Its Application in Joint Column/Row Subset SelectionJoneidi, Mohsen; Esmaeili, Ashkan*; Salimitari, Mehrdad; Khalid, Umar; Rahnavard, Nazanin
16:50178SpecRank: Ranking by Pairwise Comparisons from Specialty Workers in a Crowdsourced SettingHong, Y.-W. Peter*; Chen, Wen-Yang; Chang, Hao-Tang
17:0048Deep Variational Generative Models for Audio-Visual Speech SeparationNguyen, Vietnhat; Sadeghi, Mostafa; Ricci, Elisa; Alameda-Pineda, Xavier*

Australian Eastern Daylight Time
Time zone in Sydney NSW (GMT+11)