activity
20152017
most citedBeyond Part Models: Person Retrieval with Refined Part Pooling (and a Strong Convolutional Baseline)

152 citations · 428 across the 8 of their papers we have counts for

collaborators

9 papers

cs.CV20179 cited

DeepDeblur: Fast one-step blurry face images restoration

Lingxiao Wang, Yali Li, Shengjin Wang

We propose a very fast and effective one-step restoring method for blurry face images. In the last decades, many blind deblurring algorithms have been proposed to restore latent sh…

cs.CV2017152 cited

Beyond Part Models: Person Retrieval with Refined Part Pooling (and a Strong Convolutional Baseline)

Yifan Sun, Liang Zheng, Yi Yang +2

Employing part-level features for pedestrian image description offers fine-grained information and has been verified as beneficial for person retrieval in very recent literature. A…

cs.CV20171 cited

Progressive Representation Adaptation for Weakly Supervised Object Localization

Dong Li, Jia-Bin Huang, Yali Li +2

We address the problem of weakly supervised object localization where only image-level annotations are available for training object detectors. Numerous methods have been proposed…

cs.CV201748 cited

SegFlow: Joint Learning for Video Object Segmentation and Optical Flow

Jingchun Cheng, Yi-Hsuan Tsai, Shengjin Wang +1

This paper proposes an end-to-end trainable network, SegFlow, for simultaneously predicting pixel-wise object segmentation and optical flow in videos. The proposed SegFlow has two…

cs.CV201719 cited

Learning to Segment Instances in Videos with Spatial Propagation Network

Jingchun Cheng, Sifei Liu, Yi-Hsuan Tsai +6

We propose a deep learning-based framework for instance-level object segmentation. Our method mainly consists of three steps. First, We train a generic model based on ResNet-101 fo…

cs.CV201710 cited

Learning Structured Semantic Embeddings for Visual Recognition

Dong Li, Hsin-Ying Lee, Jia-Bin Huang +2

Numerous embedding models have been recently explored to incorporate semantic knowledge into visual recognition. Existing methods typically focus on minimizing the distance between…