Singapore University of Technology and Design

research

∙ 09/23/2021

Recent Advances of Continual Learning in Computer Vision: An Overview

In contrast to batch learning where all training data is available at on...

Haoxuan Qu, et al. ∙

research

∙ 11/25/2019

Biologically Plausible Sequence Learning with Spiking Neural Networks

Motivated by the celebrated discrete-time model of nervous activity outl...

Zuozhu Liu, et al. ∙

research

∙ 11/22/2019

Factorized Multimodal Transformer for Multimodal Sequential Learning

The complex world around us is inherently multimodal and sequential (con...

Amir Zadeh, et al. ∙

research

∙ 01/08/2020

Disentangling Representations using Gaussian Processes in Variational Autoencoders for Video Prediction

We introduce MGP-VAE, a variational autoencoder which uses Gaussian proc...

Sarthak Bhagat, et al. ∙

research

∙ 12/24/2021

Analyzing Scientific Publications using Domain-Specific Word Embedding and Topic Modelling

The scientific world is changing at a rapid pace, with new technology be...

Trisha Singhal, et al. ∙

research

∙ 01/24/2020

Simple and Effective Prevention of Mode Collapse in Deep One-Class Classification

Anomaly detection algorithms find extensive use in various fields. This ...

Penny Chong, et al. ∙

research

∙ 08/13/2021

SPACE: A Simulator for Physical Interactions and Causal Learning in 3D Environments

Recent advancements in deep learning, computer vision, and embodied AI h...

Jiafei Duan, et al. ∙

research

∙ 04/26/2019

Representation Similarity Analysis for Efficient Task taxonomy & Transfer Learning

Transfer learning is widely used in deep neural network models when ther...

Kshitij Dwivedi, et al. ∙

research

∙ 08/23/2018

DOPING: Generative Data Augmentation for Unsupervised Anomaly Detection with GAN

Recently, the introduction of the generative adversarial network (GAN) a...

Swee Kiat Lim, et al. ∙

research

∙ 08/16/2021

AutoChart: A Dataset for Chart-to-Text Generation Task

The analytical description of charts is an exciting and important resear...

Jiawen Zhu, et al. ∙

research

∙ 07/28/2021

Bi-Bimodal Modality Fusion for Correlation-Controlled Multimodal Sentiment Analysis

Multimodal sentiment analysis aims to extract and integrate semantic inf...

Wei Han, et al. ∙

research

∙ 02/08/2022

Uncertainty Modeling for Out-of-Distribution Generalization

Though remarkable progress has been achieved in various vision tasks, de...

Xiaotong Li, et al. ∙

research

∙ 06/06/2019

Deep Semi-Supervised Anomaly Detection

Deep approaches to anomaly detection have recently shown promising resul...

Lukas Ruff, et al. ∙

research

∙ 09/06/2021

STaCK: Sentence Ordering with Temporal Commonsense Knowledge

Sentence order prediction is the task of finding the correct order of se...

Deepanway Ghosal, et al. ∙

research

∙ 08/06/2021

Dual-Tuning: Joint Prototype Transfer and Structure Regularization for Compatible Feature Learning

Visual retrieval system faces frequent model update and deployment. It i...

Yan Bai, et al. ∙

research

∙ 07/21/2020

Lymphocyte counting – Error Analysis of Regression versus Bounding Box Detection Approaches

We consider the problem of counting cell nuclei from celltype-agnostic h...

Lin Geng Foo, et al. ∙

research

∙ 05/27/2021

Training Classifiers that are Universally Robust to All Label Noise Levels

For classification tasks, deep neural networks are prone to overfitting ...

Jingyi Xu, et al. ∙

research

∙ 12/26/2020

Dual-Refinement: Joint Label and Feature Refinement for Unsupervised Domain Adaptive Person Re-Identification

Unsupervised domain adaptive (UDA) person re-identification (re-ID) is a...

Yongxing Dai, et al. ∙

research

∙ 08/12/2021

A Contract Theory based Incentive Mechanism for Federated Learning

Federated learning (FL) serves as a data privacy-preserved machine learn...

Mengmeng Tian, et al. ∙

research

∙ 05/18/2022

Deep Reinforcement Learning Based on Location-Aware Imitation Environment for RIS-Aided mmWave MIMO Systems

Reconfigurable intelligent surface (RIS) has recently gained popularity ...

Wangyang Xu, et al. ∙

research

∙ 09/17/2019

A*3D Dataset: Towards Autonomous Driving in Challenging Environments

With the increasing global popularity of self-driving cars, there is an ...

Quang-Hieu Pham, et al. ∙

research

∙ 07/25/2022

IGFormer: Interaction Graph Transformer for Skeleton-based Human Interaction Recognition

Human interaction recognition is very important in many applications. On...

Yunsheng Pang, et al. ∙

research

∙ 07/26/2022

Incremental Few-Shot Semantic Segmentation via Embedding Adaptive-Update and Hyper-class Representation

Incremental few-shot semantic segmentation (IFSS) targets at incremental...

Guangchen Shi, et al. ∙

research

∙ 05/19/2021

Generalizable Person Re-identification with Relevance-aware Mixture of Experts

Domain generalizable (DG) person re-identification (ReID) is a challengi...

Yongxing Dai, et al. ∙

research

∙ 11/13/2021

Networking of Internet of UAVs: Challenges and Intelligent Approaches

Internet of unmanned aerial vehicle (I-UAV) networks promise to accompli...

Peng Yang, et al. ∙

research

∙ 12/16/2021

Graph-wise Common Latent Factor Extraction for Unsupervised Graph Representation Learning

Unsupervised graph-level representation learning plays a crucial role in...

Thilini Cooray, et al. ∙

research

∙ 05/30/2022

Analyzing Modality Robustness in Multimodal Sentiment Analysis

Building robust multimodal models are crucial for achieving reliable dep...

Devamanyu Hazarika, et al. ∙

research

∙ 11/21/2019

WildMix Dataset and Spectro-Temporal Transformer Model for Monoaural Audio Source Separation

Monoaural audio source separation is a challenging research area in mach...

Amir Zadeh, et al. ∙

research

∙ 04/22/2020

Understanding Integrated Gradients with SmoothTaylor for Deep Neural Network Attribution

Integrated gradients as an attribution method for deep neural network mo...

Gary S. W. Goh, et al. ∙

research

∙ 04/10/2022

FedCorr: Multi-Stage Federated Learning for Label Noise Correction

Federated learning (FL) is a privacy-preserving distributed learning par...

Jingyi Xu, et al. ∙

research

∙ 05/08/2022

Pervasive Machine Learning for Smart Radio Environments Enabled by Reconfigurable Intelligent Surfaces

The emerging technology of Reconfigurable Intelligent Surfaces (RISs) is...

George C. Alexandropoulos, et al. ∙

research

∙ 06/22/2022

Jointist: Joint Learning for Multi-instrument Transcription and Its Applications

In this paper, we introduce Jointist, an instrument-aware multi-instrume...

Kin Wai Cheuk, et al. ∙

research

∙ 03/23/2018

Generative Adversarial Autoencoder Networks

We introduce an effective model to overcome the problem of mode collapse...

Ngoc-Trung Tran, et al. ∙

research

∙ 06/05/2019

Towards Multimodal Sarcasm Detection (An _Obviously_ Perfect Paper)

Sarcasm is often expressed through several verbal and non-verbal cues, e...

Santiago Castro, et al. ∙

research

∙ 08/05/2020

Duality Diagram Similarity: a generic framework for initialization selection in task transfer learning

In this paper, we tackle an open research question in transfer learning,...

Kshitij Dwivedi, et al. ∙

research

∙ 08/18/2021

The Multi-Modal Video Reasoning and Analyzing Competition

In this paper, we introduce the Multi-Modal Video Reasoning and Analyzin...

Haoran Peng, et al. ∙

research

∙ 08/05/2021

IDM: An Intermediate Domain Module for Domain Adaptive Person Re-ID

Unsupervised domain adaptive person re-identification (UDA re-ID) aims a...

Yongxing Dai, et al. ∙

research

∙ 06/19/2019

Learning Disentangled Representations of Timbre and Pitch for Musical Instrument Sounds Using Gaussian Mixture Variational Autoencoders

In this paper, we learn disentangled representations of timbre and pitch...

Yin-Jyun Luo, et al. ∙

research

∙ 08/05/2021

Global and Local Texture Randomization for Synthetic-to-Real Semantic Segmentation

Semantic segmentation is a crucial image understanding task, where each ...

Duo Peng, et al. ∙

research

∙ 05/08/2019

Evaluating Cascading Effects of Attacks on Resilience of Industrial Control Systems: A Design-Centric Modeling Approach

A design-centric modeling approach was proposed to model the behavior of...

Zhongyuan Hau, et al. ∙

research

∙ 05/14/2019

The Algonauts Project: A Platform for Communication between the Sciences of Biological and Artificial Intelligence

In the last decade, artificial intelligence (AI) models inspired by the ...

Radoslaw Martin Cichy, et al. ∙

research

∙ 09/06/2019

The Disruptions of 5G on Data-driven Technologies and Applications

With 5G on the verge of being adopted as the next mobile network, there ...

Dumitrel Loghin, et al. ∙

research

∙ 08/04/2021

Skeleton Cloud Colorization for Unsupervised 3D Action Representation Learning

Skeleton-based human action recognition has attracted increasing attenti...

Siyuan Yang, et al. ∙

research

∙ 11/09/2021

Time-Varying Channel Prediction for RIS-Assisted MU-MISO Networks via Deep Learning

To mitigate the effects of shadow fading and obstacle blocking, reconfig...

Wangyang Xu, et al. ∙

research

∙ 03/03/2022

Bridging the Source-to-target Gap for Cross-domain Person Re-Identification with Intermediate Domains

Cross-domain person re-identification (re-ID), such as unsupervised doma...

Yongxing Dai, et al. ∙

research

∙ 09/15/2017

Sensor Fusion for Public Space Utilization Monitoring in a Smart City

Public space utilization is crucial for urban developers to understand h...

Billy Pik Lik Lau, et al. ∙

research

∙ 06/12/2016

SenseFlow: An Experimental Study for Tracking People

The main challenges in large-scale people tracking are the recognition o...

Kai Li, et al. ∙

research

∙ 11/21/2017

Variational Probability Flow for Biologically Plausible Training of Deep Neural Networks

The quest for biologically plausible deep learning is driven, not just b...

Zuozhu Liu, et al. ∙

research

∙ 12/04/2017

Adaptive Quantization for Deep Neural Network

In recent years Deep Neural Networks (DNNs) have been rapidly developed ...

Yiren Zhou, et al. ∙

research

∙ 12/04/2017

Vprop: Variational Inference using RMSprop

Many computationally-efficient methods for Bayesian deep learning rely o...

Mohammad Emtiyaz Khan, et al. ∙

Singapore University of Technology and Design

Featured Researchers