Search Results for author: He Huang

Found 17 papers, 5 papers with code

MetaFi: Device-Free Pose Estimation via Commodity WiFi for Metaverse Avatar Simulation

no code implementations22 Aug 2022 Jianfei Yang, Yunjiao Zhou, He Huang, Han Zou, Lihua Xie

Avatar refers to a representative of a physical user in the virtual world that can engage in different activities and interact with other objects in metaverse.

Pose Estimation

ME-Net: Multi-Encoder Net Framework for Brain Tumor Segmentation

no code implementations21 Mar 2022 Wenbo Zhang, Guang Yang, He Huang, Weiji Yang, Xiaomei Xu, Yongkai Liu, Xiaobo Lai

Moreover, the serious voxel imbalance between the brain tumor and the background as well as the different sizes and locations of the brain tumor makes the segmentation of 3D images a challenging problem.

Brain Tumor Segmentation Tumor Segmentation

SUTD-TrafficQA: A Question Answering Benchmark and an Efficient Network for Video Reasoning over Traffic Events

2 code implementations CVPR 2021 Li Xu, He Huang, Jun Liu

In this paper, we create a novel dataset, SUTD-TrafficQA (Traffic Question Answering), which takes the form of video QA based on the collected 10, 080 in-the-wild videos and annotated 62, 535 QA pairs, for benchmarking the cognitive capability of causal inference and event understanding models in complex traffic scenarios.

Autonomous Vehicles Causal Inference +3

Addressing Class Imbalance in Scene Graph Parsing by Learning to Contrast and Score

1 code implementation28 Sep 2020 He Huang, Shunta Saito, Yuta Kikuchi, Eiichi Matsumoto, Wei Tang, Philip S. Yu

Motivated by the fact that detecting these rare relations can be critical in real-world applications, this paper introduces a novel integrated framework of classification and ranking to resolve the class imbalance problem in scene graph parsing.

Cooperative Communications for Internet of Everything in B5G/6G Hybrid and Ubiquitous Networks: Foundation, Further Optimization and Solutions

no code implementations10 Aug 2020 He Huang, Su Hu, Chaowei Yuan

Cooperative Communications (CC) has been one of most critical communication technologies which plays a founding role on Internet of Everything in B5G/6G networks.

Multi-label Zero-shot Classification by Learning to Transfer from External Knowledge

no code implementations30 Jul 2020 He Huang, Yuanwei Chen, Wei Tang, Wenhao Zheng, Qing-Guo Chen, Yao Hu, Philip Yu

On the other hand, there is a large semantic gap between seen and unseen classes in the existing multi-label classification datasets.

Classification General Classification +3

Travel Time Prediction using Tree-Based Ensembles

1 code implementation28 May 2020 He Huang, Martin Pouls, Anne Meyer, Markus Pauly

The computational results show that the addition of this routing data can be beneficial to the model performance.

On-Demand Video Dispatch Networks: A Scalable End-to-End Learning Approach

no code implementations25 Dec 2018 Damao Yang, Sihan Peng, He Huang, Hongliang Xue

We design a dispatch system to improve the peak service quality of video on demand (VOD).

Generative Dual Adversarial Network for Generalized Zero-shot Learning

1 code implementation CVPR 2019 He Huang, Changhu Wang, Philip S. Yu, Chang-Dong Wang

Most previous models try to learn a fixed one-directional mapping between visual and semantic space, while some recently proposed generative methods try to generate image features for unseen classes so that the zero-shot learning problem becomes a traditional fully-supervised classification problem.

Generalized Zero-Shot Learning Metric Learning

dpMood: Exploiting Local and Periodic Typing Dynamics for Personalized Mood Prediction

1 code implementation29 Aug 2018 He Huang, Bokai Cao, Philip S. Yu, Chang-Dong Wang, Alex D. Leow

Mood disorders are common and associated with significant morbidity and mortality.

Human-Computer Interaction Computers and Society

An Introduction to Image Synthesis with Generative Adversarial Nets

no code implementations12 Mar 2018 He Huang, Philip S. Yu, Changhu Wang

There has been a drastic growth of research in Generative Adversarial Nets (GANs) in the past few years.

Image-to-Image Translation Translation

Learning under uncertainty: a comparison between R-W and Bayesian approach

no code implementations NeurIPS 2016 He Huang, Martin Paulus

The Bayesian approach indicates that the belief of environmental stationarity positively correlates with choice optimality, but not lose-shift rate (inverted U shape).

Context-sensitive active sensing in humans

no code implementations NeurIPS 2013 Sheeraz Ahmad, He Huang, Angela J. Yu

Humans and animals readily utilize active sensing, or the use of self-motion, to focus sensory and cognitive resources on the behaviorally most relevant stimuli and events in the environment.

Cannot find the paper you are looking for? You can Submit a new open access paper.