Hongmei Song — accepted AI-conference papers

2019

Learning Unsupervised Video Object Segmentation Through Visual Attention

Wenguan Wang, Hongmei Song, Shuyang Zhao, Jianbing Shen, Sanyuan Zhao, Steven C. H. Hoi +1

CVPR 2019poster

This paper conducts a systematic study on the role of visual attention in Unsupervised Video Object Segmentation (UVOS) tasks. By elaborately annotating three popular video segmentation datasets (DAVIS, Youtube-Objects and SegTrack V2) with dynamic eye-tracking data in the UVOS setting, for the firs…

Cited by 277 PDF ↗code ↗Scholar ↗

2018

Pyramid Dilated Deeper ConvLSTM for Video Salient Object Detection

Hongmei Song, Wenguan Wang, Sanyuan Zhao, Jianbing Shen, Kin-Man Lam

ECCV 2018poster

This paper proposes a fast video salient object detection model, based on a novel recurrent network architecture, named Pyramid Dilated Bidirectional ConvLSTM (PDB-ConvLSTM). A Pyramid Dilated Convolution (PDC) module is first designed for simultaneously extracting spatial features at multiple scale…

Cited by 593 Source ↗PDF ↗Scholar ↗