MUlti-Store Tracker (MUSTer): A cognitive psychology inspired approach to object tracking

By Zhibin Hong, Zhe Chen, Chaohui Wang, Xue Mei, Danil V. Prokhorov, Dacheng Tao. 2015

639 citations recorded by the source corpus.

Subfields: Aerospace Engineering, Computer Vision and Pattern Recognition, Electrical and Electronic Engineering, Cognitive Science & Psychology

How researchers see this paper

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

In Aerospace Engineering

In Computer Vision and Pattern Recognition

In Electrical and Electronic Engineering

In Cognitive Science & Psychology

Citations in the corpus

Learning feed-forward one-shot learners (2016, methodology): “An elementary tracker based on learnet compares favourably against recent tracking systems, which make use of different features and online model update strategies: DAT [17], DSST [2], MEEM [22], MUSTer [6] and SO-DLT [21].”
Learning Multi-domain Convolutional Neural Networks for Visual Tracking (2015, methodology): “In recent years, correlation ﬁlters have gained attention in the area of visual tracking due to their computational ef-ﬁciency and competitive performance [3, 18, 6, 21].”
Attentional Correlation Filter Network for Adaptive Visual Tracking (2017, methodology): “In addition, the results of MDNet-N [29], MUSTer [18], MEEM [42], KCF [16], SCT [3], Struck [15], and TLD [19] were estimated using the authors’ implementations.”
A Benchmark and Simulator for UAV Tracking (2016, methodology): “SAMF [23], MUSTER [18], DSST [8], Struck [13], and ASLA [19] group into a second tier of close performing trackers, while the remaining trackers IVT [38], TLD [21], MOSSE [5], CSK [17], OAB [11], KCF [16] and DCF [16] achieve consistently lower performance.”
Learning Adaptive Discriminative Correlation Filters via Temporal Consistency Preserving Spatial Feature Selection for Robust Visual Object Tracking (2018, methodology): “In addition, DCF-based tracking methods have also been extended to support long-term memory [46], multi-kernel method [47], structural constraints [48], support vector representation [49], sparse representation [50] and enhanced robustness [51], [52], [53], [54], [55], [56].”
Context-Aware Correlation Filter Tracking (2017, methodology): “In addition, we include popular CF trackers that did not meet the selection criteria for our framework, namely DSST [5] that is very similar to SAMF but usually underperforms it, MUSTER [12] that employs a long-term/shortterm memory strategy but its source code is not available for modification, and”
Action-Decision Networks for Visual Tracking with Deep Reinforcement Learning (2017, methodology): “We compared ADNet in a comprehensive comparison with 13 state-of-the-art trackers including MDNet [24], CCOT [9], GOTURN2 [12], HDT [25], DeepSRDCF [8], SINT [31], FCNT [34], SCT [5], MUSTer [15], CNNSVM [14], MEEM [42], DSST [7], and KCF [13].”
Object Detection from Video Tubelets with Convolutional Neural Networks (2016, background): “Object tracking has been studied for decades [26, 20, 12].”
Meta-Tracker: Fast and Robust Online Adaptation for Visual Object Trackers (2018, background): “Many hard cases have been tackled by using context information [55, 38], short and long-term memory [35, 23], and scale-estimation [10], just to name a few.”
Template Matching with Deformable Diversity Similarity (2016, methodology): “Another use case is in video tracking, where Template Matching is used to detect drifts and relocate the object after losing it [9].”
Kernel Cross-Correlator (2017, background): “A biology-inspired framework where short-term processing and long-term processing are cooperated with each other in correlation filter based trackers (Hong et al. 2015).”
T-CNN: Tubelets With Convolutional Neural Networks for Object Detection From Videos (2016, background): “Object tracking has been studied for decades [27], [28], [29].”
GOT-10k: A Large High-Diversity Benchmark for Generic Object Tracking in the Wild (2018, methodology): “e efforts on the development of appearance models. Based on the appearance models used, the tracking approaches are roughly categorized as either generative [71], [72] or discriminative methods [42], [51], [52], [68]. Generative methods view tracking as a reconstruction problem and they maintain a t”
Learning Aberrance Repressed Correlation Filters for Real-Time UAV Tracking (2019, methodology): “The results are compared with 20 state-of-the-art trackers with both hand-crafted based trackers and deep-based trackers, i.e., KCF [13], DSST [8], SAMF [18], MUSTER [14], BACF [15], SRDCF [7], STAPLE CA [21], MCCT-H [27], STRCF [16], ECO-HC (with gray-scale) [5], ECO [5], CCOT [9], HCF [19], ADNet ”
Learning in high-dimensional multimedia data: the state of the art (2015, methodology): “The outputs of feature reduction approaches are taken as the inputs for supervised, semi-supervised or unsupervised learning to support multimedia real applications such as multimedia retrieval, multimedia annotation and video tracking [19, 33, 77, 88].”
UvA-DARE (Digital Academic Repository) Siamese Instance Search for Tracking (2016, methodology): “Figure 4: Per attribute comparison on AUC score of the proposed SINT with MUSTer [18].”
The Sixth Visual Object Tracking VOT2018 Challenge Results (2018, methodology): “g, [34,57,20]) have simply used the short-term average overlap performance measure from [90,61].”
Siamese Instance Search for Tracking (2016, methodology): “Figure 4: Per attribute comparison on AUC score of the proposed SINT with MUSTer [18].”