Search Results - "Shengfeng He"

RGBD Salient Object Detection via Deep Fusion by Qu, Liangqiong, He, Shengfeng, Zhang, Jiawei, Tian, Jiandong, Tang, Yandong, Yang, Qingxiong

“…Numerous efforts have been made to design various low-level saliency cues for RGBD saliency detection, such as color and depth contrast features as well as…”
Get full text

Self-Supervised Spatio-Temporal Representation Learning for Videos by Predicting Motion and Appearance Statistics by Wang, Jiangliu, Jiao, Jianbo, Bao, Linchao, He, Shengfeng, Liu, Yunhui, Liu, Wei

“…We address the problem of video representation learning without human-annotated labels. While previous efforts address the problem by designing novel…”
Get full text

Real-Time Salient Object Detection with a Minimum Spanning Tree by Wei-Chih Tu, Shengfeng He, Qingxiong Yang, Shao-Yi Chien

“…In this paper, we present a real-time salient object detection system based on the minimum spanning tree. Due to the fact that background regions are typically…”
Get full text

Projecting Your View Attentively: Monocular Road Scene Layout Estimation via Cross-view Transformation by Yang, Weixiang, Li, Qi, Liu, Wenxi, Yu, Yuanlong, Ma, Yuexin, He, Shengfeng, Pan, Jia

“…HD map reconstruction is crucial for autonomous driving. LiDAR-based methods are limited due to the deployed expensive sensors and time-consuming computation…”
Get full text

DeshadowNet: A Multi-context Embedding Deep Network for Shadow Removal by Liangqiong Qu, Jiandong Tian, Shengfeng He, Yandong Tang, Lau, Rynson W. H.

“…Shadow removal is a challenging task as it requires the detection/annotation of shadows as well as semantic understanding of the scene. In this paper, we…”
Get full text

Visual Tracking via Locality Sensitive Histograms by Shengfeng He, Qingxiong Yang, Lau, Rynson W. H., Jiang Wang, Ming-Hsuan Yang

“…This paper presents a novel locality sensitive histogram algorithm for visual tracking. Unlike the conventional image histogram that counts the frequency of…”
Get full text

Deformable Object Tracking With Gated Fusion by Wenxi Liu, Yibing Song, Dengsheng Chen, Shengfeng He, Yuanlong Yu, Tao Yan, Hancke, Gehard P., Lau, Rynson W. H.

“…The tracking-by-detection framework receives growing attention through the integration with the convolutional neural networks (CNNs). Existing…”
Get full text

Spatially-invariant Style-codes Controlled Makeup Transfer by Deng, Han, Han, Chu, Cai, Hongmin, Han, Guoqiang, He, Shengfeng

“…Transferring makeup from the misaligned reference image is challenging. Previous methods overcome this barrier by computing pixel-wise correspondences between…”
Get full text

Fast Weighted Histograms for Bilateral Filtering and Nearest Neighbor Searching by Shengfeng He, Qingxiong Yang, Lau, Rynson W. H., Ming-Hsuan Yang

“…The locality sensitive histogram (LSH) injects spatial information into the local histogram in an efficient manner, and has been demonstrated to be very…”
Get full text

L -Regularized Image Downscaling by Junjie Liu, Shengfeng He, Lau, Rynson W. H.

“…In this paper, we propose a novel L 0 -regularized optimization framework for image downscaling. The optimization is driven by two L 0 -regularized priors. The…”
Get full text

Delving into Salient Object Subitizing and Detection by Shengfeng He, Jianbo Jiao, Xiaodan Zhang, Guoqiang Han, Lau, Rynson W. H.

“…Subitizing (i.e., instant judgement on the number) and detection of salient objects are human inborn abilities. These two tasks influence each other in the…”
Get full text

Egocentric Temporal Action Proposals by Shao Huang, Weiqiang Wang, Shengfeng He, Lau, Rynson W. H.

“…We present an approach to localize generic actions in egocentric videos, called temporal action proposals (TAPs), for accelerating the action recognition step…”
Get full text

Saliency-Guided Color-to-Gray Conversion Using Region-Based Optimization by Du, Hao, He, Shengfeng, Sheng, Bin, Ma, Lizhuang, Lau, Rynson W. H.

“…Image decolorization is a fundamental problem for many real-world applications, including monochrome printing and photograph rendering. In this paper, we…”
Get full text

Discovering Interpretable Latent Space Directions of GANs Beyond Binary Attributes by Yang, Huiting, Chai, Liangyu, Wen, Qiang, Zhao, Shuang, Sun, Zixun, He, Shengfeng

“…Generative adversarial networks (GANs) learn to map noise latent vectors to high-fidelity image outputs. It is found that the input latent space shows semantic…”
Get full text

Invertible Grayscale via Dual Features Ensemble by Ye, Taizhong, Du, Yong, Deng, Junjie, He, Shengfeng

“…Grayscale image colorization is known as an ill-posed problem because of the imbalanced matching between intensity and color values. Even given prior hints…”
Get full text

Proposal-Driven Segmentation for Videos by Li, Junliang, He, Shengfeng, Wong, Hon-Cheng, Lo, Sio-Long

“…Effectively utilizing the common information in a set of video frames is a vital aspect in video segmentation. However, existing methods that transport the…”
Get full text

Robust Object Tracking via Locality Sensitive Histograms by Shengfeng He, Lau, Rynson W. H., Qingxiong Yang, Jiang Wang, Ming-Hsuan Yang

“…This paper presents a novel locality sensitive histogram (LSH) algorithm for visual tracking. Unlike the conventional image histogram that counts the frequency…”
Get full text

Exemplar-Driven Top-Down Saliency Detection via Deep Association by Shengfeng He, Lau, Rynson W. H.

“…Top-down saliency detection is a knowledge-driven search task. While some previous methods aim to learn this "knowledge" from category-specific data, others…”
Get full text

Stereo Object Proposals by Shao Huang, Weiqiang Wang, Shengfeng He, Lau, Rynson W. H.

“…Object proposal detection is an effective way of accelerating object recognition. Existing proposal methods are mostly based on detecting object boundaries,…”
Get full text

Coupled Rain Streak and Background Estimation via Separable Element-Wise Attention by Tan, Yinjie, Wen, Qiang, Qin, Jing, Jiao, Jianbo, Han, Guoqiang, He, Shengfeng

“…Single image de-raining is challenging especially in the scenarios with dense rain streaks. Existing methods resolve this problem by predicting the rain…”
Get full text