activity
20182021
collaborators

7 papers

cs.CV2021

A Reinforcement-Learning-Based Energy-Efficient Framework for Multi-Task Video Analytics Pipeline

Yingying Zhao, Mingzhi Dong, Yujiang Wang +7

Deep-learning-based video processing has yielded transformative results in recent years. However, the video analytics pipeline is energy-intensive due to high data rates and relian…

cs.CV2021

MemX: An Attention-Aware Smart Eyewear System for Personalized Moment Auto-capture

Yuhu Chang, Yingying Zhao, Mingzhi Dong +7

This work presents MemX: a biologically-inspired attention-aware eyewear system developed with the goal of pursuing the long-awaited vision of a personalized visual Memex. MemX cap…

cs.CV2019

Dynamic Face Video Segmentation via Reinforcement Learning

Yujiang Wang, Mingzhi Dong, Jie Shen +3

For real-time semantic video segmentation, most recent works utilised a dynamic framework with a key scheduler to make online key/non-key decisions. Some works used a fixed key sch…

cs.LG2018

Dynamic Ensemble Active Learning: A Non-Stationary Bandit with Expert Advice

Kunkun Pang, Mingzhi Dong, Yang Wu +1

Active learning aims to reduce annotation cost by predicting which samples are useful for a human teacher to label. However it has become clear there is no best active learning alg…

cs.LG2018

Meta-Learning Transferable Active Learning Policies by Deep Reinforcement Learning

Kunkun Pang, Mingzhi Dong, Yang Wu +1

Active learning (AL) aims to enable training high performance classifiers with low annotation cost by predicting which subset of unlabelled instances would be most beneficial to la…

cs.LG2018

Metric Learning via Maximizing the Lipschitz Margin Ratio

Mingzhi Dong, Xiaochen Yang, Yang Wu +1

In this paper, we propose the Lipschitz margin ratio and a new metric learning framework for classification through maximizing the ratio. This framework enables the integration of…