A Scale Adaptive Kernel Correlation Filter Tracker with Feature Integration

By Yang Li, Jianke Zhu. ECCV Workshops, 2014

1,463 citations recorded by the source corpus.

Subfields: Computer Vision and Pattern Recognition, Genetics

View Paper: https://www.semanticscholar.org/paper/0cae491292feccbc9ad1d864cf8b7144923ce6de

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

In Genetics

Citations in the corpus

The Visual Object Tracking VOT2016 Challenge Results (2016, methodology): “…Qi, S. Lyu { yihouxiang, cvdaviddo, lywen.cv.workbox, wbli.app, honggangqi.cas, heizi.lyu } @gmail.com GGTv2 is an improvement of GGT [55] by combining the scale adaptive kernel correlation ﬁlter [56] and the geometric structure hyper-graph searching framework to complete the object tracking task.”
Discriminative Scale Space Tracking (2016, methodology): “Recently, a multi-resolution extension of a kernelized correlation translation filter was proposed by Li and Zhu [23].”
Beyond Correlation Filters: Learning Continuous Convolution Operators for Visual Tracking (2016, methodology): “DSST SAMF TGPR MEEM LCT HCF Staple SRDCF SRDCFdecon DeepSRDCF C-COT OTB-2015 60.6 64.7 54.0 63.4 70.1 65.5 69.9 72.9 76.7 77.3 82.4 Temple-Color 47.5 56.1 51.6 62.2 52.8 58.2 63.0 62.2 65.8 65.4 70.4 0 0.2 0.4 0.6 0.8 1 Overlap threshold 0 20 40 60 80 100 O v e rl a p P re c is io n [ % ] Success pl”
Learning Adaptive Discriminative Correlation Filters via Temporal Consistency Preserving Spatial Feature Selection for Robust Visual Object Tracking (2018, methodology): “For scale detection, SAMF [43] and DSST [44] were proposed to handle scale variations by performing scale selection in a scale pool after the tracking stage.”
RGB-T Object Tracking: Benchmark and Baseline (2018, methodology): “[2] 2012 MEEM[54]+RGBT 2014 DSST[50] 2014 SAMF[51] 2014 KCF[44]+RGBT 2015 SRDCF[52] 2015 SOWP[11] 2015 SOWP[11]+RGBT 2015 CSR[6] 2016 C-COT[48] 2016 CSR-DCF[53] 2017 CSR-DCF[53]+RGBT 2017 CFnet[39] 2017 CFnet[39]+RGBT 2017 ECO[49] 2017 SGT 2017 IV.”
Reliable Patch Trackers: Robust visual tracking by exploiting reliable patches (2015, background): “Visual object tracking is a fundamental research topic in computer vision, which enjoys a wide range of applications, including video surveillance, robotics, driverless car, etc.”
Convolutional Features for Correlation Filter Based Visual Tracking (2015, methodology): “Our trackers are evaluated on the full OTB dataset (containing 50 videos) and compared with 15 stateof-the-art trackers: SRDCF [10], DSST [9], KCF [21], SAMF [28], ACT [12], TGPR [17], MEEM [40], Struck”
Visual Tracking With Weighted Adaptive Local Sparse Appearance Model via Spatio-Temporal Context Learning (2018, background): “Li and Zhu [14] improved the KCF tracker [49] by integrating a scale adaptive scheme and color-naming features.”
Deeper and Wider Siamese Networks for Real-Time Visual Tracking (2019, methodology): “The listed methods, such as EBT[41], LDP[24], nSAMF[22], TCNN[25], MLDF[36], CFWCR[36] and CFCF[11] are compared in VOT challenges [9, 16, 17].”
Large Margin Object Tracking with Circulant Feature Maps (2017, methodology): “We evaluate LMCF with 9 state-of-the-art trackers designed with conventional hand-crafted features including Struck [13], MEEM [31], TGPR [10], DLSSVM [22], Staple [2], KCF [14], RPT [20], DSST [5] and SAMF [19].”
GOT-10k: A Large High-Diversity Benchmark for Generic Object Tracking in the Wild (2018, methodology): “SAMF and DSST propose efﬁcient scale searching schemes for correlation ﬁlters tracking.”
Triplet Loss in Siamese Network for Object Tracking (2018, methodology): “For reference, we also compare with recent trackers: DSST [5], MEEM [35], SAMF [19], and DLSSVM [21].”
Context-Aware Correlation Filter Tracking (2017, methodology): “As shown in Figure 1, integrating our framework with the mediocre tracker SAMF [18] achieves better tracking results than state-of-the-art trackers by exploiting context information.”