activity
20182021
collaborators
Showing cs.CVShow all

7 papers · 1 filter

cs.CV2021

Real-time Image Enhancer via Learnable Spatial-aware 3D Lookup Tables

Tao Wang, Yong Li, Jingyang Peng +4

Recently, deep learning-based image enhancement algorithms achieved state-of-the-art (SOTA) performance on several publicly available datasets. However, most existing methods fail…

cs.CV2019

Learning Cascaded Siamese Networks for High Performance Visual Tracking

Peng Gao, Yipeng Ma, Ruyue Yuan +2

Visual tracking is one of the most challenging computer vision problems. In order to achieve high performance visual tracking in various negative scenarios, a novel cascaded Siames…

cs.CV2019

Siamese Attentional Keypoint Network for High Performance Visual Tracking

Peng Gao, Ruyue Yuan, Fei Wang +3

In this paper, we investigate the impacts of three main aspects of visual tracking, i.e., the backbone network, the attentional mechanism, and the detection component, and propose…

cs.CV2018

Efficient Multi-level Correlating for Visual Tracking

Yipeng Ma, Chun Yuan, Peng Gao +1

Correlation filter (CF) based tracking algorithms have demonstrated favorable performance recently. Nevertheless, the top performance trackers always employ complicated optimizatio…

cs.CV2018

High Performance Visual Tracking with Circular and Structural Operators

Peng Gao, Yipeng Ma, Ke Song +4

In this paper, a novel circular and structural operator tracker (CSOT) is proposed for high performance visual tracking, it not only possesses the powerful discriminative capabilit…

cs.CV2018

A Complementary Tracking Model with Multiple Features

Peng Gao, Yipeng Ma, Chao Li +3

Discriminative Correlation Filters based tracking algorithms exploiting conventional handcrafted features have achieved impressive results both in terms of accuracy and robustness.…