Robust Visual Tracking via Convolutional Networks Without Training

By Kaihua Zhang, Qingshan Liu, Yi Wu, Ming-Hsuan Yang. IEEE Transactions on Image Processing, 2015

354 citations recorded by the source corpus.

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

Visual Tracking With Weighted Adaptive Local Sparse Appearance Model via Spatio-Temporal Context Learning (2018, methodology): “To better evaluate the effectiveness of the proposed tracker, we further add six most recent trackers including DLT [24], KCF [49], DSST [60], TGPR [11], MEEM [12], CNT [17] besides the 29 trackers within the benchmark.”
Video Salient Object Detection via Fully Convolutional Networks (2017, background): “In this section, we mainly focus on famous, deep learning models for computer vision applications in dynamic scenes, including action recognition [20], [54], object segmentation [55], [22], object tracking [56], [57], [59], [60], [61], attention prediction [21] and semantic segmentation [62], and ex”
Kernel Cross-Correlator (2017, background): “Tracking by convolutional neural network without training can be found in (Zhang et al. 2016; Zhang and Suganthan 2016).”
Deep Learning for Visual Tracking: A Comprehensive Survey (2019, methodology): “To achieve the goal of learning generic representations for target modeling and constructing a more robust target models, the main contributions of methods are classified into: i) offline training of CNNs on large-scale datasets for visual tracking [63], [68], [80], [89], [97], [100], [101], [104], ”