Research Engineer, Institute of High Performance Computing (IHPC)

Agency for Science, Technology and Research (A*STAR), Singapore

Biography

ZHANG Hao is a research engineer at Institute of High Performance Computing (IHPC), A*STAR, Singapore. His research interests include natural language processing, visual grounding, reinfor-cement learning for robotics and machine learning methods.
Meanwhile, ZHANG Hao is pursuing his Ph.D. in computer science at Nanyang Technological University (NTU) since August 2019, and his supervisor is Associate Prof. Aixin SUN (NTU) and cosupervisor is Dr. Joey Tianyi ZHOU (A*STAR).

Email: hzhang26 AT outlook DOT com

Interests

  • Vision-and-Language
  • Natural Language Processing
  • Computational Linguistics
  • Artificial Intelligence
  • Machine & Deep Learning

Education

  • Ph.D. in Computer Science, 2019-Present

    Nanyang Technological University (NTU)

  • M.Sc. in Communications Engineering, 2015-2016

    Nanyang Technological University (NTU)

  • B.Eng. in Communications Engineering, 2011-2015

    Dalian University of Technology (DUT)

Experience

 
 
 
 
 

Research Engineer

Institute of High Performance Computing (IHPC), A*STAR

Jul 2016 – Present Singapore
  • Social & Cognitive Computing (SCC) Department (07/2016-05/2018)
  • Human-Centric AI Group at Artificial Intelligence Initiative (A*AI) (06/2018-07/2020)
  • Computational AI Group at Computing & Intelligence (CI) Department (08/2020-Present)

Publications

Quickly discover relevant content by filtering publications.

COSY: COunterfactual SYntax for Cross-Lingual Understanding

Pre-trained multilingual language models, e.g., multilingual-BERT, are widely used in cross-lingual tasks, yielding the …
Sicheng Yu, Hao Zhang, Yulei Niu, Qianru Sun, Jing Jiang
PDF Slides DOI
COSY: COunterfactual SYntax for Cross-Lingual Understanding

Parallel Attention Network with Sequence Matching for Video Grounding

Given a video, video grounding aims to retrieve a temporal moment that semantically corresponds to a language query. In this work, we …
Hao Zhang, Aixin Sun, Wei Jing, Liangli Zhen, Joey Tianyi Zhou, Rick Siow Mong Goh
Preprint PDF Code Slides DOI
Parallel Attention Network with Sequence Matching for Video Grounding

Video Corpus Moment Retrieval with Contrastive Learning

Given a collection of untrimmed and unsegmented videos, video corpus moment retrieval (VCMR) is to retrieve a temporal moment (i.e., a …
Hao Zhang, Aixin Sun, Wei Jing, Guoshun Nan, Liangli Zhen, Joey Tianyi Zhou, Rick Siow Mong Goh
Preprint PDF Code Slides Video DOI
Video Corpus Moment Retrieval with Contrastive Learning

Interventional Video Grounding with Dual Contrastive Learning

Video grounding aims to localize a moment from an untrimmed video for a given textual query. Existing approaches focus more on the …
Guoshun Nan, Rui Qiao, Yao Xiao, Jun Liu, Sicong Leng, Hao Zhang, Wei Lu
Preprint PDF Code
Interventional Video Grounding with Dual Contrastive Learning

Natural Language Video Localization: A Revisit in Span-based Question Answering Framework

Natural Language Video Localization (NLVL) aims to locate a target moment from an untrimmed video that semantically corresponds to a …
Hao Zhang, Aixin Sun, Wei Jing, Liangli Zhen, Joey Tianyi Zhou, Rick Siow Mong Goh
Preprint PDF DOI
Natural Language Video Localization: A Revisit in Span-based Question Answering Framework

GDPNet: Refining Latent Multi-View Graph for Relation Extraction

Relation Extraction (RE) is to predict the relation type of two entities that are mentioned in a piece of text, e.g., a sentence or a …
Fuzhao Xue, Aixin Sun, Hao Zhang, Eng Siong Chng
Preprint PDF Code Poster Slides
GDPNet: Refining Latent Multi-View Graph for Relation Extraction

Deep N-ary Error Correcting Output Codes

Ensemble learning consistently improves the performance of multi-class classification through aggregating a series of base classifiers. …
Hao Zhang, Joey Tianyi Zhou, Tianying Wang, Ivor W. Tsang, Rick Siow Mong Goh
Preprint PDF Code Slides
Deep N-ary Error Correcting Output Codes

Span-based Localizing Network for Natural Language Video Localization

Given an untrimmed video and a text query, natural language video localization (NLVL) is to locate a matching span from the video that …
Hao Zhang, Aixin Sun, Wei Jing, Joey Tianyi Zhou
Preprint PDF Code Slides DOI
Span-based Localizing Network for Natural Language Video Localization

Multi-source Meta Transfer for Low Resource Multiple-Choice Question Answering

Multiple-choice question answering (MCQA) is one of the most challenging tasks in machine reading comprehension since it requires more …
Ming Yan, Hao Zhang, Di Jin, Joey Tianyi Zhou
Preprint PDF Slides DOI
Multi-source Meta Transfer for Low Resource Multiple-Choice Question Answering

RoboCoDraw: Robotic Avatar Drawing with GAN-based Style Transfer and Time-efficient Path Optimization

Robotic drawing has become increasingly popular as an entertainment and interactive tool. In this paper we present RoboCoDraw, a …
Tianying Wang*, Wei Qi Toh*, Hao Zhang*, Xiuchao Sui, Shaohua Li, Yong Liu, Wei Jing
Preprint PDF Code Poster Slides DOI
RoboCoDraw: Robotic Avatar Drawing with GAN-based Style Transfer and Time-efficient Path Optimization

Efficient Robotic Task Generalization Using Deep Model Fusion Reinforcement Learning

Learning-based methods have been used to program robotic tasks in recent years. However, extensive training is usually required not …
Tianying Wang, Hao Zhang, Wei Qi Toh, Hongyuan Zhu, Cheston Tan, Yan Wu, Yong Liu, Wei Jing
Preprint PDF Slides DOI
Efficient Robotic Task Generalization Using Deep Model Fusion Reinforcement Learning

Dual Adversarial Transfer for Sequence Labeling

We propose a new architecture for addressing sequence labeling, termed Dual Adversarial Transfer Network (DATNet). Specifically, the …
Joey Tianyi Zhou*, Hao Zhang*, Di Jing, Xi Peng
Preprint PDF Code DOI
Dual Adversarial Transfer for Sequence Labeling

Dual Adversarial Neural Transfer for Low-resource Named Entity Recognition

We propose a new neural transfer method termed Dual Adversarial Transfer Network (DATNet) for addressing low-resource Named Entity …
Joey Tianyi Zhou*, Hao Zhang*, Di Jing, Hongyuan Zhu, Rick Siow Mong Goh, Kenneth Kwok
PDF Code Poster Slides DOI
Dual Adversarial Neural Transfer for Low-resource Named Entity Recognition

RoSeq: Robust Sequence Labeling

In this paper, we mainly investigate two issues for sequence labeling, namely label imbalance and noisy data which are commonly seen in …
Joey Tianyi Zhou*, Hao Zhang*, Di Jing, Xi Peng, Yang Xiao, Zhiguo Cao
Preprint PDF Code DOI
RoSeq: Robust Sequence Labeling

Learning With Annotation of Various Degrees

In this paper, we study a new problem in the scenario of sequences labeling. To be exact, we consider that the training data are with …
Joey Tianyi Zhou, Meng Fang, Hao Zhang, Chen Gong, Xi Peng, Zhiguo Cao, Rick Siow Mong Goh
Preprint PDF Code DOI
Learning With Annotation of Various Degrees

Removing Backscatter to Enhance the Visibility of Underwater Object

Underwater vision enhancement via backscatter removing is widely used in ocean engineering. With increasing ocean exploration, …
Hao Zhang, Lap Pui Chau
Preprint PDF Code
Removing Backscatter to Enhance the Visibility of Underwater Object

Projects

Human-Robot Collaborative Al for Advanced Manufacturing and Engineering (AME)

Work Package 3 - Human-like Concept and Task Learning.
Human-Robot Collaborative Al for Advanced Manufacturing and Engineering (AME)

PrimeNet: Human-inspired Framework for Commonsense Knowledge Representation and Reasoning

A human-inspired framework for commonsense knowledge representation and reasoning.
PrimeNet: Human-inspired Framework for Commonsense Knowledge Representation and Reasoning

MARACANA: Behavioural Understanding and Narrative Descriptions from Videos

An effectively and flexibly multimodal system to analyze and narrate real world events captured in video.
MARACANA: Behavioural Understanding and Narrative Descriptions from Videos

Removing Backscatter to Enhance the Visibility of Underwater Object

A novel and effective method based on underwater optical model for underwater object visibility enhancement.
Removing Backscatter to Enhance the Visibility of Underwater Object

Achievements

Best Paper Award for the paper: Deep N-ary Error Correcting Output Codes

The 13th EAI International Conference on Mobile Multimedia Communications (MOBIMEDIA 2020) Aug 2020
See certificate

1st Runner Up in Artificial Intelligence (AI) Hackathon

Agency for Science, Technology and Research (A*STAR) Sep 2018
See certificate