Time | Paper ID | Paper Title | Author Names |
Award Paper Session (25 Oct) | |||
10:30 | 88 | FBR-CNN: A Feedback Recurrent Network for Video Saliency Detection | Ding, Guanqun*; Imamoglu, Nevrez; Caglayan, Ali; Murakawa, Masahiro; Nakamura, Ryosuke |
10:40 | 111 | Learning Signal Representations for EEG Cross-Subject Channel Selection and Trial Classification | Massi, Michela C*; Ieva, Francesca |
10:50 | 166 | Hierarchical graph neural nets can capture long-range interactions | Rampasek, Ladislav*; Wolf, Guy |
11:00 | 167 | Multimodal data visualization and denoising with integrated diffusion | KUCHROO, MANIK ; Godavarthi, Abhinav; Tong, Alexander Y; Wolf, Guy; Krishnaswamy, Smita* |
11:10 | 39 | Self-Attention for Audio Super-Resolution | Carraz Rakotonirina, Nathanael* |
11:20 | 62 | Noise ReTF Estimation and Removal for Low SNR Speech Enhancement | Birnie, Lachlan I*; Samarasinghe, Prasanga; abhayapala, thushara; Grixti-Cheng, Daniel |
Paper Session 1.1 (Oct 25) | |||
11:30 | 28 | Robustness-aware Filter Pruning for Robust Neural Networks Against Adversarial Attacks | Lim, Hyuntak*; Roh, Si-Dong; Park, Sangki; Chung, Ki-Seok |
11:40 | 42 | Differentially Private Variable Selection via the Knockoff Filter | Pournaderi, Mehrdad*; Xiang, Yu |
11:50 | 101 | TRANSFER BAYESIAN META-LEARNING VIA WEIGHTED FREE ENERGY MINIMIZATION | Zhang, Yunchuan*; Jose, Sharu Theresa; Simeone, Osvaldo |
12:00 | 113 | Gaussian approximations of SDEs in Metropolis-adjusted Langevin Algorithms | Särkkä, Simo*; Merkatas, Christos; Karvonen, Toni |
12:10 | 133 | EVALUATION OF COMPLEXITY MEASURES FOR DEEP LEARNING GENERALIZATION IN MEDICAL IMAGE ANALYSIS | Vakanski, Aleksandar; Xian, Min* |
12:20 | 151 | Uncertain Bayesian Networks: Learning from Incomplete Data | Hougen, Conrad*; Kaplan, Lance; Cerutti, Federico; Hero, Alfred |
Paper Session 1.2 (Oct 25) | |||
14:00 | 24 | SMALL MOVING TARGET MOT TRACKING WITH GM-PHD FILTER AND ATTENTION-BASED CNN | Aguilar, Camilo G*; Ortner, Mathias; Zerubia, Josiane |
14:10 | 49 | BayesRadar : Bayesian Metric-Kalman Filter Learning for Improved and Reliable Radar Target Classification | Dubey, Anand*; Santra, Avik; Fuchs, Jonas; Lübke, Maximilian; Weigel, Robert; Lurz, Fabian |
14:20 | 70 | BLOCK-WISE INTRA-PREDICTION OF IMAGING DATA BASED ON OVERFITTED NEURAL NETWORKS WITH ON-LINE LEARNING | Sanchez, Victor*; Hernandez-Cabronero, Miguel; Serra-Sagrista, Joan |
14:30 | 80 | Convolutional Dense Neural Network based Spirometry Variable FVC Prediction using Sustained Phonations | yadav, shivani*; Gope, Dipanjan; Maheswari Krishnaswamy, Uma; Ghosh, Prasanta |
14:40 | 84 | About the equivalence between complex-valued and real-valued fully connected neural networks – application to PolInSAR images | BARRACHINA, Jose Agustin; Ren, Chengfang; Vieillard, Gilles; Morisseau, Christele; Ovarlez, Jean-Philippe* |
14:50 | 93 | Joint optimization of system design and reconstruction in MIMO radar imaging | Weiss, Tomer*; P, N; Vedula, Sanketh; Feuer, Arie; Bronstein, Alex |
15:00 | 100 | DEEP LOW-DIMENSIONAL SPECTRAL IMAGE REPRESENTATION FOR COMPRESSIVE SPECTRAL RECONSTRUCTION | Monroy, Brayan *; Bacca, Jorge; Arguello, Henry |
15:10 | 120 | A Hybrid Model Integrating LSTM And GARCH For Bitcoin Price Prediction | He, Yiwen*; Gao, Zidi; Kuruoglu, Ercan E |
15:20 | 121 | Anonymizing motion sensor data through time-frequency domain | Rougé, Pierre*; Moukadem, Ali; Dieterlen, Alain; Boutet, Antoine; Frindel, Carole |
Paper Session 1.3 (Oct 25) | |||
16:00 | 130 | Introducing K-anonymity principles to adversarial attacks for privacy protection in image classification problems | Mygdalis, Vasileios*; TEFAS, ANASTASIOS; Pitas, Ioannis |
16:10 | 137 | A Weighted Loss Function to Predict Control Parameters for Supercontinuum Generation via Neural Networks | Stucchi, Diego*; Corsini, Andrea; Genty, Goëry; Boracchi, Giacomo; Foi, Alessandro |
16:20 | 142 | A Semi-Supervised Generative Adversarial Network for Prediction of Genetic Disease Outcomes | Davi, Caio C M *; Braga-Neto, Ulisses M. |
16:30 | 147 | Learning-Based UE Classification in Millimeter-Wave Cellular Systems With Mobility | Pjanic, Dino*; Sopasakis, Alexandros; Tufvesson, Fredrik ; Tataria, Harsh ; Reial, Andres |
16:40 | 149 | DETECTING NETWORK STATE IN THE PRESENCE OF VARYING LEVELS OF CONGESTION | de Fréin, Ruairí*; Izima, Obinna; Malik, Ali |
16:50 | 159 | Convolutional Neural Network Denoising of Focused Ion Beam Micrographs | Peng, Minxu*; Cokbas, Mertcan; Dorken Gallastegi, Unay; Ishwar, Prakash; Konrad, Janusz; Kulis, Brian; Goyal, Vivek K |
17:00 | 168 | A COARSE-TO-FINE OBJECT DETECTION FRAMEWORK FOR HIGH-RESOLUTION IMAGES WITH SPARSE OBJECTS | Liu, Jinyan; Yan, Longbin; Chen, Jie* |
17:10 | 172 | DETECTION OF INSECTS IN CLASS-IMBALANCED LIDAR FIELD MEASUREMENTS | Vannoy, Trevor*; Scofield, Trey; Logan, Riley; Rehbein, Elizabeth; Shaw, Joseph; Whitaker, Bradley M |
Paper Session 2.1 (Oct 26) | |||
10:30 | 10 | SIAMNET: SIAMESE CNN BASED SIMILARITY MODEL FOR ADVERSARIALLY GENERATED ENVIRONMENTAL SOUNDS | Madhu, Aswathy*; K, Suresh |
10:40 | 57 | Compression of DNNs Using Magnitude Pruning and Nonlinear Information Bottleneck Training | Nielsen, Morten Østergaard*; Ostergaard, Jan; Jensen, Jesper; Tan, Zheng-Hua |
10:50 | 75 | OPINION RECOMMENDATION USING COVERAGE FOR ADAPTIVE PREDICTION | Gionanidis, Emmanouil*; Kotropoulos, Constantine; Ntemi, Myrsini |
11:00 | 90 | Not all noise is accounted equally: How differentially private learning benefits from large sampling rates | Dörmann, Friedrich*; Frisk, Osvald; Andersen, Lars Nørvang; Fischer Pedersen, Christian |
11:10 | 109 | BI-RADS-NET: AN EXPLAINABLE MULTITASK LEARNING APPROACH FOR CANCER DIAGNOSIS IN BREAST ULTRASOUND IMAGES | Zhang, Boyu; Vakanski, Aleksandar; Xian, Min* |
11:20 | 110 | Explainable Deep Learning Detection of Gaussian Propeller Noise with Unknown Signal-to-Noise Ratio | Mahiout, Thomas; Fillatre, Lionel*; Deruaz Pepin, Laurent |
11:30 | 150 | Data-driven Learning of Geometric Scattering Modules for GNNs | Tong, Alexander Y*; Wenkel, Frederik; Macdonald, Kincaid; Krishnaswamy, Smita; Wolf, Guy |
11:40 | 174 | FEW-SHOT LEARNING VIA DEPENDENCY MAXIMIZATION AND INSTANCE DISCRIMINANT ANALYSIS | Hou, Zejiang*; Kung, Sun-Yuan |
11:50 | 31 | Distributed Variational Information Bottleneck for IoT Environments | Alsulaimawi, Zahir*; Liu, Huaping |
12:00 | 140 | PRIVACY ASSESSMENT OF FEDERATED LEARNING USING PRIVATE PERSONALIZED LAYERS | Jourdan, Theo; Boutet, Antoine*; Frindel, Carole |
12:10 | 180 | Distributed Dictionary Learning over Heterogeneous Clients using Local Adaptive Dictionaries | You-De, Huang; Hong, Y.-W. Peter* |
12:20 | 107 | A Copula-Driven Unsupervised Learning Framework for Anomaly Detection with Multivariate Heterogeneous Data | Damodaran , Swaroop*; Padmanabhan, Ram; R., Maahin; Gurugopinath, Sanjeev |
Paper Session 3.1 (Oct 27) | |||
11:00 | 8 | MODEL SELECTION OF KERNEL RIDGE REGRESSION FOR EXTRAPOLATION | Tanaka, Akira*; Nakamura, Masanari; Imai, Hideyuki |
11:10 | 38 | Adaptive Normalized LMP Estimation for Graph Signal Processing | Yan, Yi*; Adel, Radwa; Kuruoglu, Ercan E |
11:20 | 65 | MESSAGE PASSING-BASED INFERENCE IN THE GAMMA MIXTURE MODEL | Podusenko, Albert*; van Erp, Bart; Bagaev, Dmitry; Senoz, Ismail; de Vries, Bert |
11:30 | 92 | Estimating Partially Observed Graph Signals by Learning Spectrally Concentrated Graph Kernels | Turhan, Gulce; Vural, Elif* |
11:40 | 116 | Random Feature Approximation for Online Nonlinear Graph Topology Identification | Money, Rohan T.*; Krishnan, Joshin; Beferull-Lozano, Baltasar |
11:50 | 124 | Learning Parametric Time-Vertex Graph Processes from Incomplete Realizations | Guneyi, Eylem Tugce; Canbolat, Abdullah; Vural, Elif* |
12:00 | 141 | GRAPH-BASED TRANSFORM BASED ON NEURAL NETWORKS FOR INTRA-PREDICTION OF IMAGING DATA | Roy, Debaleena*; Guha, Tanaya; Sanchez, Victor |
12:10 | 158 | Multimodal Graph Coarsening for Interpretable, MRI-Based Brain Graph Neural Network | Sebenius, Isaac*; Campbell, Alex; Morgan, Sarah; Bullmore, Edward; Lió, Pietro |
12:20 | 163 | Tracking of quantized signals based on online kernel regression | Ruiz-Moreno, Emilio*; Beferull-Lozano, Baltasar |
Paper Session 3.2 (Oct 27) | |||
14:00 | 47 | Preferential batch Bayesian optimization | Siivola, Eero*; Dhaka, Akash Kumar; Andersen, Michael; Gonzalez, Javier; Moreno, Pablo; Vehtari, Aki |
14:10 | 52 | A DEEP Q-NETWORK BASED APPROACH FOR ONLINE BAYESIAN CHANGE POINT DETECTION | Ma, Xiaochuan*; Lai, Lifeng; Cui, Shuguang |
14:20 | 53 | Bayesian Two-stage Sequential Change Diagnosis via multi-sensor array | Ma, Xiaochuan*; Lai, Lifeng; Cui, Shuguang |
14:30 | 95 | A GENERAL PARAMETRIZATION FRAMEWORK FOR PAIRWISE MARKOV MODELS: AN APPLICATION TO UNSUPERVISED IMAGE SEGMENTATION | Gangloff, Hugo*; Morales, Katherine; Petetin, Yohan |
14:40 | 183 | Self-trained video anomaly detection based on Teacher-Student model | Wang, Xusheng; Pei, Mingtao*; nie, zhengang |
14:50 | 185 | RECOGNIZING ACTIVITIES FROM EGOCENTRIC IMAGES WITH APPEARANCE AND MOTION FEATURES | Chen, Yanhua; Pei, Mingtao*; nie, zhengang |
15:00 | 186 | EARLY FUSION GRAPH CONVOLUTIONAL NETWORK FOR SKELETON-BASED ACTION RECOGNITION | zhao, xiaoxue*; Liu, Cuiwei; Shi, Xiangbin |
15:10 | 187 | LIGHTWEIGHT FOREST FIRE DETECTION BASED ON DEEP LEARNING | Fan, Ruixian; Pei, Mingtao* |
15:20 | 189 | OBJECT DETECTION IN SAR VIA GENERATIVE KNOWLEDGE TRANSFER | Lou, Xin*; Wang, Han |
Paper Session 3.3 (Oct 27) | |||
16:00 | 55 | L3DAS21 Challenge: Machine Learning for 3D Audio Signal Processing | Guizzo, Eric*; Comminiello, Danilo |
16:10 | 156 | Optimizing Time Domain Fully Convolutional Networks for 3D Speech Enhancement in a Reverberant Environment Using Perceptual Losses | Guimarães, Heitor R*; Beccaro, Wesley; Arjona Ramírez, Miguel |
16:20 | 182 | A NEURAL BEAMFORMING NETWORK FOR B-FORMAT 3D SPEECH ENHANCEMENT AND RECOGNITION | Ren, Xinlei*; Chen, Lianwu; Zheng, Xiguang; Xu, Chenglin; Zhang, Xu; Zhang, Chen; Guo, Liang; Yu, Bing |
16:30 | 190 | Optimized Spatial Matching for Visual Object Tracking | Fuxiang, Wang* |
16:40 | 191 | An improved DiracNet convolutional neural network for haze visibility detection | Xiyu, Mu*; Qi, Xu; Qiang, Zhang; Junchi, Ren; Hongbin, Wang; Linyi, Zhou |
16:50 | 194 | REAL-TIME OPTIMIZING WEIGHTED GAUSSIAN CURVATURE FOR 4K VIDEOS | Tang, Wenming*; Gong, Yuanhao; Zhou, LeBin |
17:00 | 198 | CONTENT-BASED RECOMMENDATION USING MACHINE LEARNING | Tai, Yifan *; Sun, Zhenyu; Yao, Zixuan |
17:10 | 200 | A placement angle detection method of recyclable object for garbage power generation | cai, yong*; chen, mengwei; feng, yifei; ming, zheng |
Paper Session 4.1 (Oct 28) | |||
9:30 | 12 | A Unified PAC-Bayesian Framework for Machine Unlearning via Information Risk Minimization | Jose, Sharu Theresa*; Simeone, Osvaldo |
9:40 | 60 | Beyond the bias variance trade-off: a mutual information trade-off in deep learning | LAN, XINJIE*; Zhu, Bin; Boncelet, Charles; Barner, Kenneth |
9:50 | 131 | Toward minimal-sufficiency in regression tasks: An approach based on a variational estimation bottleneck | Lyu, Zhaoyan*; Aminian, Gholamali; Rodrigues, Miguel |
10:00 | 3 | Understanding Linear Style Transfer Auto-encoders | Pradhan, Ian; Lyu, Siwei* |
10:10 | 32 | An empirical comparison of joint-training and pre-training for domain-agnostic semi-supervised learning via energy-based models | Song, Yunfu; Zheng, Huahuan; Ou, Zhijian* |
10:20 | 61 | Affinity Mixup for Weakly Supervised Sound Event Detection | Izadi, Mohammad Rasool*; Stevenson, Robert; Kloepper, Laura |
Paper Session 4.2 (Oct 28) | |||
11:00 | 1 | Dynamic Graph Convolutional Network: A Topology Optimization Perspective | Deng, Bowen*; Jiang, Aimin |
11:10 | 27 | GRAD-CAM GUIDED CHANNEL-SPATIAL ATTENTION MODULE FOR FINE-GRAINED VISUAL CLASSIFICATION | Xu, Shuai ; Chang, Dongliang; Xie, Jiyang; Ma, Zhanyu* |
11:20 | 51 | Bag of Groups of Convolutional Features Model for Visual Object Recognition | Singh, Jaspreet*; singh, chandan |
11:30 | 97 | ADVERSARIAL PERTURBATION ATTACKS ON NESTED DICHOTOMIES CLASSIFICATION SYSTEMS | Alkhouri, Ismail *; Velasquez, Alvaro; Atia, George |
11:40 | 105 | Scalable Community Detection in the Degree-Corrected Stochastic Block Model | He, Yicong*; Beckus, Andre; Atia, George |
11:50 | 126 | Zero-Shot Motion Pattern Recognition From 4D Point-Clouds | Salami, Dariush*; Sigg, Stephan |
12:00 | 160 | ADVERSARIAL ATTACKS ON MULTI-LEVEL FAULT DETECTION AND DIAGNOSIS SYSTEMS | Awad, Akram*; Alkhouri, Ismail ; Atia, George |
12:10 | 162 | FAST SUBSPACE CLUSTERING ALGORITHM WITH EFFICIENT SIMILARITY-CONSTRAINED SAMPLING FOR HYPERSPECTRAL IMAGES | Lopez, Jhon E*; Hinojosa, Carlos; Arguello, Henry |
12:20 | 164 | HyPhyLearn: A Domain Adaptation-Inspired Approach to Classification Using Limited Number of Training Samples | Nooraiepour, Alireza*; Bajwa, Waheed; Mandayam, Narayan |
Paper Session 4.3 (Oct 28) | |||
14:00 | 21 | Deep Complex Convolutional Recurrent Network for Multi-channel Speech Enhancement and Dereverberation | Gelderblom, Femke B.*; Myrvoll, Tor Andre |
14:10 | 66 | CAESYNTH: REAL-TIME TIMBRE INTERPOLATION AND PITCH CONTROL WITH CONDITIONAL AUTOENCODERS | Valero Puche, Aaron; LEE, SUKHAN* |
14:20 | 73 | Disentangled Speech Representation Learning Based on Factorized Hierarchical Variational Autoencoder with Self-Supervised Objective | Xie, Yuying*; Arildsen, Thomas; Tan, Zheng-Hua |
14:30 | 77 | MLP Singer: Towards Rapid Parallel Korean Singing Voice Synthesis | Tae, Jaesung*; Lee, Younggun; Kim, Hyeongju |
14:40 | 98 | Conditional Sound Generation Using Neural Discrete Time-Frequency Representation Learning | Liu, Xubo*; Iqbal, Turab; ZHAO, Jinzheng; Huang, Qiushi; Plumbley, Mark D.; Wang, Wenwu |
14:50 | 99 | Detecting cover songs with Pitch Class Key-invariant Networks | O’Hanlon, Ken*; Benetos, Emmanouil; Dixon, Simon |
15:00 | 104 | SINGING FUNDAMENTAL FREQUENCY CONTOUR GENERATION USING GENERALIZED COMMAND-RESPONSE MODEL AND SCORE-CONDITIONAL VARIATIONAL AUTOENCODER | Seki, Shogo*; Taga, Haruka; Toda, Tomoki |
15:10 | 63 | IMPROVING DEEP REINFORCEMENT LEARNING FOR FINANCIAL TRADING USING DEEP ADAPTIVE GROUP-BASED NORMALIZATION | Nalmpantis, Angelos; Passalis, Nikolaos*; Tsantekidis, Avraam; TEFAS, ANASTASIOS |
15:20 | 165 | Model-Free Learning of Optimal Deterministic Resource Allocations in Wireless Systems via Action-Space Exploration | Hashmi, Hassaan*; Kalogerias, Dionysios |
Paper Session 4.4 (Oct 28) | |||
16:00 | 23 | Ambiguity-Free and Efficient Sparse Phase Retrieval from Affine Measurements under Outlier Corruption | Yang, Ming-Hsun *; Hong, Y.-W. Peter; Wu, Jwo-Yuh |
16:10 | 102 | A Constrained Linearly involved Generalized Moreau Enhanced Model and Its Proximal Splitting Algorithm | Yata, Wataru; Yamagishi, Masao; Yamada, Isao* |
16:20 | 176 | ADAPTIVE APPROACH FOR SPARSE REPRESENTATIONS USING THE LOCALLY COMPETITIVE ALGORITHM FOR AUDIO | Bahadi, Soufiyan*; Plourde, Eric; Rouat, Jean |
16:30 | 20 | Online DOA Estimation for Noninteger Linear Antenna Arrays in Coarray Domain | Chen, Yitian; Nosrati, Hamed*; Aboutanios, Elias |
16:40 | 161 | Two-way Spectrum Pursuit for CUR Decomposition and Its Application in Joint Column/Row Subset Selection | Joneidi, Mohsen; Esmaeili, Ashkan*; Salimitari, Mehrdad; Khalid, Umar; Rahnavard, Nazanin |
16:50 | 178 | SpecRank: Ranking by Pairwise Comparisons from Specialty Workers in a Crowdsourced Setting | Hong, Y.-W. Peter*; Chen, Wen-Yang; Chang, Hao-Tang |
17:00 | 48 | Deep Variational Generative Models for Audio-Visual Speech Separation | Nguyen, Vietnhat; Sadeghi, Mostafa; Ricci, Elisa; Alameda-Pineda, Xavier* |
Australian Eastern Daylight Time
Time zone in Sydney NSW (GMT+11)