The Visual Object Tracking VOT2016 Challenge Results

By Matej Kristan, Ales Leonardis, Jiri Matas, Michael Felsberg, Roman P. Pflugfelder, Luka Cehovin, Tomás Vojír, Gustav Häger, Alan Lukezic, Gustavo Javier Fernandez and 130 more. 2016

773 citations recorded by the source corpus.

Subfields: Computer Vision and Pattern Recognition

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

Generalized Intersection Over Union: A Metric and a Loss for Bounding Box Regression (2019, background): “Due to this appealing property, all performance measures used to evaluate for segmentation [2, 1, 25, 14], object detection [14, 4], and tracking [11, 10] rely on this metric.”
Distractor-aware Siamese Networks for Visual Object Tracking (2018, methodology): “Analyses results include EAO on VOT2016 [14] and AUC on UAV20L [22].”
SiamRPN++: Evolution of Siamese Visual Tracking With Very Deep Networks (2018, background): “With the wide adoption of deep learning models in visual tracking, tracking algorithms based on correlation filter with deep feature representations [9, 5] have obtained the state-of-the-art accuracy in popular tracking benchmarks [47, 48] and challenge [23, 20, 21].”
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].”
Learning Spatial-Temporal Regularized Correlation Filters for Visual Tracking (2018, methodology): “Table 3 lists the results of different trackers on VOT-2016 dataset.”
Deformable Siamese Attention Networks for Visual Object Tracking (2020, methodology): “VOT2016 [21] & VOT2018 [22].”
RGB-T Object Tracking: Benchmark and Baseline (2018, background): “In other words, it estimates how accurate the estimated bounding box is after a certain number of frames are processed since initialization [55].”
A Twofold Siamese Network for Real-Time Object Tracking (2018, methodology): “VOT2016 benchmark: We compare SA-Siam with the top real-time trackers in VOT2016 challenge [20] and Staple[2] , SiamFC[3] and ECOhc[6].”
CREST: Convolutional Residual Learning for Visual Tracking (2017, methodology): “VOT-2016 Dataset.”
Attentional Correlation Filter Network for Adaptive Visual Tracking (2017, methodology): “MDNetN is a version of MDNet [29], which is trained by the images of Image-Net [31] as described in VOT2016 [23].”
End-to-End Representation Learning for Correlation Filter Based Tracking (2017, background): “However, in order to avoid overfitting to the test set in design choices and hyperparameter selection, we consider OTB-2013, OTB-50 and OTB-100 as our test set and 129 videos from VOT2014, VOT-2016 and Temple-Color [20] as our validation set, excluding any videos which were already assigned to the t”
VITAL: VIsual Tracking via Adversarial Learning (2018, methodology): “In the VOT-2016 dataset [30], we measure the performance in terms of Expected Average Overlap (EAO), Accuracy Ranks (Ar) and Robustness Ranks (Rr).”
Meta-Tracker: Fast and Robust Online Adaptation for Visual Object Trackers (2018, methodology): “ches 60%. We ended up having 718 video sequences. In addition, for the experiments on OTB dataset, we also used an additional 58 sequences from object tracking datasets in VOT2013,VOT2014,and VOT2015 [29], excluding the videos included in OTB, following MDNet’s approach [39]. These sequences were se”
Fast Online Object Tracking and Segmentation: A Unifying Approach (2018, methodology): “Minmax: Axis-aligned box (red), MBR: minimum bounding rectangle (green) and Opt: the optimisation strategy proposed in VOT2016 [28] (blue).”
Multi-cue Correlation Filters for Robust Visual Tracking (2018, methodology): “For more information, please refer to [21].”
Visual Tracking via Adaptive Spatially-Regularized Correlation Filters (2019, methodology): “We also perform comparisons on the VOT2016 dataset [19] which contains 60 challenging sequences.”