Struck: Structured output tracking with kernels

By Sam Hare, Stuart Golodetz, Amir Saffari, Vibhav Vineet, Ming-Ming Cheng, Stephen L. Hicks, Philip H. S. Torr. Vision, 2011

1,796 citations recorded by the source corpus.

Subfields: Computer Vision and Pattern Recognition

View Paper: https://www.semanticscholar.org/paper/546d6c4b46708374e7bb90d8d32e4cefa18f83b8

How researchers see this paper

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

In Computer Vision and Pattern Recognition

Citations in the corpus

A survey of appearance models in visual object tracking (2013, neutral): “One is based on a structured output support vector machine (SVM) [Hare et al. 2011; Yao et al. 2012], and the other is based on ranking SVM [Bai and Tang 2012].”
Modeling and Propagating CNNs in a Tree Structure for Visual Tracking (2016, methodology): “By the similar motivation, an approach based on structured SVM has been proposed in [12].”
Staple: Complementary Learners for Real-Time Tracking (2015, methodology): “Sta-ple performs signiﬁcantly better than all the methods re-ported in [39], with an average relative improvement of 23% with respect to the best tracker evaluated in the original benchmark (Struck [16]).”
Reliable Patch Trackers: Robust visual tracking by exploiting reliable patches (2015, neutral): “Our method fails since the negative samples are not on 148 556 166 387 181 92 263 221 332 388 RPT Struck KCF TGPR SCM Figure 4.”
Visual Tracking With Weighted Adaptive Local Sparse Appearance Model via Spatio-Temporal Context Learning (2018, neutral): “In [48], Hare et al.”
Exploiting the Circulant Structure of Tracking-by-Detection with Kernels (2012, neutral): “Struck [4] achieves very good results (over 0.”
Siam R-CNN: Visual Tracking by Re-Detection (2019, methodology): “Many classical methods use an online learned classifier to re-detect the object of interest over the full image [1, 21, 2, 56, 23, 57, 32].”
Meta-Tracker: Fast and Robust Online Adaptation for Visual Object Trackers (2018, background): “Pioneered by [26], many learning techniques have been suggested, e.g. multiple instance learning [3], structured output SVMs [19], online boosting [18], and model ensembles [4].”
Exploring Causal Relationships in Visual Object Tracking (2015, methodology): “An obvious scenario is tracking by detection [2, 12, 17], a popular method for visual object tracking.”
The Visual Object Tracking VOT2016 Challenge Results (2016, methodology): “Submitted by VOT Committee Struck [103] is a framework for adaptive visual object tracking based on structured output prediction.”
Accurate Scale Estimation for Robust Visual Tracking (2014, methodology): “In recent years, tracking-by-detection methods [3, 9, 11, 19] have shown to provide excellent tracking performance.”
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.”
The Visual Object Tracking VOT2015 Challenge Results (2015, background): “Out for these, three were based on structured SVM learning, i.e., Struck (A.11), Rob-Struck (A.16), SRAT (A.38), one was based on Gaussian process regression, TGPR (A.51), one on logistic regression HRP (A.23) and one on kernelized-least-squares ACT (A.55).”
Probabilistic Regression for Visual Tracking (2020, methodology): “The formulation (1), (2) is explicitly utilized in the theory of Structural SVMs [42], employed in the well-known Struck tracker [19].”
Learning Adaptive Discriminative Correlation Filters via Temporal Consistency Preserving Spatial Feature Selection for Robust Visual Object Tracking (2018, background): “Moreover, in order to exploit the labelled and unlabelled data more effectively, Struck [32] proposed to train a structural supervised classiﬁer for visual object tracking.”
TrackingNet: A Large-Scale Dataset and Benchmark for Object Tracking in the Wild (2018, methodology): “Last, we include some baseline trackers such as TLD [51], Struck [22], ASLA [19] and IVT [20] for reference.”
Adaptive Color Attributes for Real-Time Visual Tracking (2014, methodology): “CT [27] LSST [24] Frag [1] L1APG [2] LOT [18] ASLA [10] TLD [11] SCM [28] EDFT [6] CSK [9] DFT [20] CXT [5] CPF [19] LSHT [8] Struck [7] CN2 CN Median CLE 78.”