output
20112026
most citedSupervised Learning of Semantics-Preserving Hash via Deep Convolutional Neural Networks

325 citations

Showing 2017Show all

10 papers · 1 filter

cs.SI2017★ 14 cited

Time Matters: Multi-scale Temporalization of Social Media Popularity

Bo Wu, Wen-Huang Cheng, Yongdong Zhang +1

The evolution of social media popularity exhibits rich temporality, i.e., popularities change over time at various levels of temporal granularity. This is influenced by temporal va…

cs.IT2017

State Estimation in Smart Distribution System With Low-Precision Measurements

Jung-Chieh Chen, Hwei-Ming Chung, Chao-Kai Wen +2

Efficient and accurate state estimation is essential for the optimal management of the future smart grid. However, to meet the requirements of deploying the future grid at a large…

eess.AS2017★ 149 cited

MuseGAN: Multi-track Sequential Generative Adversarial Networks for Symbolic Music Generation and Accompaniment

Hao-Wen Dong, Wen-Yi Hsiao, Li-Chia Yang +1

Generating music has a few notable differences from generating images and videos. First, music is an art of time, necessitating a temporal model. Second, music is usually composed…

eess.SY2017★ 17 cited

Local Cyber-physical Attack with Leveraging Detection in Smart Grid

Hwei-Ming Chung, Wen-Tai Li, Chau Yuen +2

A well-designed attack in the power system can cause an initial failure and then results in large-scale cascade failure. Several works have discussed power system attack through fa…

eess.SY2017

Adaptive Noise Cancellation Using Deep Cerebellar Model Articulation Controller

Yu Tsao, Hao-Chun Chu, Shih-Wei Lan +3

This paper proposes a deep cerebellar model articulation controller (DCMAC) for adaptive noise cancellation (ANC). We expand upon the conventional CMAC by stacking sin-gle-layer CM…

cs.CV2017★ 23 cited

No More Discrimination: Cross City Adaptation of Road Scene Segmenters

Yi-Hsin Chen, Wei-Yu Chen, Yu-Ting Chen +3

Despite the recent success of deep-learning based semantic segmentation, deploying a pre-trained road scene segmenter to a city whose images are not presented in the training set w…