Z
Zhibin Hong
Researcher at Baidu
Publications - 35
Citations - 1784
Zhibin Hong is an academic researcher from Baidu. The author has contributed to research in topics: Computer science & Video tracking. The author has an hindex of 14, co-authored 26 publications receiving 1377 citations. Previous affiliations of Zhibin Hong include Toyota Motor Engineering & Manufacturing North America & University of Technology, Sydney.
Papers
More filters
Proceedings ArticleDOI
MUlti-Store Tracker (MUSTer): A cognitive psychology inspired approach to object tracking
TL;DR: Inspired by the well-known Atkinson-Shiffrin Memory Model, this work proposes MUlti-Store Tracker (MUSTer), a dual-component approach consisting of short- and long-term memory stores to process target appearance memories.
Proceedings ArticleDOI
Tracking via Robust Multi-task Multi-view Joint Sparse Representation
TL;DR: This paper cast tracking as a novel multi-task multi-view sparse learning problem and exploit the cues from multiple views including various types of visual features, such as intensity, color, and edge, where each feature observation can be sparsely represented by a linear combination of atoms from an adaptive feature dictionary.
Proceedings ArticleDOI
ACFNet: Attentional Class Feature Network for Semantic Segmentation
TL;DR: ACFNet as mentioned in this paper proposes a coarse-to-fine segmentation network, which can be composed of an ACF module and any off-the-shell segmentation networks (base network).
Posted Content
ACFNet: Attentional Class Feature Network for Semantic Segmentation
TL;DR: This paper presents the concept of class center which extracts the global context from a categorical perspective, and proposes a novel module, named Attentional Class Feature (ACF) module, to calculate and adaptively combine different class centers according to each pixel.
Posted Content
An Experimental Survey on Correlation Filter-based Tracking.
Zhe Chen,Zhibin Hong,Dacheng Tao +2 more
TL;DR: The experimental results have shown that state-of-art performance, in terms of robustness, speed and accuracy, can be achieved by several recent CFTs, such as MUSTer and SAMF.