The Visual Object Tracking VOT2017 Challenge Results

By Matej Kristan, Ales Leonardis, Jiri Matas, Michael Felsberg, Roman P. Pflugfelder, Luka Cehovin, Zajc, Tomás Vojír, Gustav Häger, Alan Lukezic and 101 more. 2017 IEEE International Conference on Computer Vision Workshops (ICCVW), 2017

301 citations recorded by the source corpus.

The Visual Object Tracking challenge VOT2017 is the fifth annual tracker benchmarking activity organized by the VOT initiative. Results of 51 trackers are presented; many are state-of-the-art published at major computer vision conferences or journals in recent years. The evaluation included the standard VOT and other popular methodologies and a new "real-time" experiment simulating a situation where a tracker processes images as if provided by a continuously running sensor. Performance of the tested trackers typically by far exceeds standard baselines. The source code for most of the trackers is publicly available from the VOT page. The VOT2017 goes beyond its predecessors by (i) improving the VOT public dataset and introducing a separate VOT2017 sequestered dataset, (ii) introducing a realtime tracking experiment and (iii) releasing a redesigned toolkit that supports complex experiments. The dataset, the evaluation kit and the results are publicly available at the challenge website1.

Subfields: Computer Vision and Pattern Recognition, Ecology, Global and Planetary Change

View Paper: https://www.semanticscholar.org/paper/53329e5c79c1128c7b252a12b182c472a3413bfa

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 Ecology

In Global and Planetary Change

Citations in the corpus

Siamese Cascaded Region Proposal Networks for Real-Time Visual Tracking (2018, methodology): “In extensive experiments on six benchmarks, including OTB-2013 [52], OTB-2015 [53], VOT-2016 [20], VOT2017 [21], LaSOT [10] and TrackingNet [34], our C-RPN achieves the state-of-the-art results and runs in real-time1.”
Memory Based Online Learning of Deep Representations from Video Streams (2017, background): “ re-learning should be done in real time while tracking, without the availability of labels and with data coming from a stream which is often nonstationary. On the other hand, classic object tracking [8] has substantially divergent goals from continuous incremental learning. While in tracking the ob”
Visual Tracking via Adaptive Spatially-Regularized Correlation Filters (2019, methodology): “In Table 3(b), we compare our method with top-10 trackers in the VOT2017 [20] of-ﬁcial report.”
High Performance Visual Tracking with Siamese Region Proposal Network (2018, methodology): “In experiments, our method can achieve leading performance in VOT2015, VOT2016 and VOT2017 real-time challenges while operating at 160 FPS.”
Learning Attentions: Residual Attentional Siamese Network for High Performance Online Visual Tracking (2018, methodology): “We report all these metrics compared with a number of the latest state-of-the-art trackers on VOT2015 [15] and VOT2017 [28].”
Opening up Open World Tracking (2021, background): “The related tasks of visual object tracking (VOT) [48, 47, 46] and segmentation (VOS) [82, 81, 14, 15] focus on tracking generic targets whose classes are not known a-priori, but are pre-localized as bounding box [48] or a segmentation mask [82] in the first frame.”
GOT-10k: A Large High-Diversity Benchmark for Generic Object Tracking in the Wild (2018, methodology): “VOT [4], [5], [8] is an annual visual object tracking challenge held every year in conjunction”
LaSOT: A High-Quality Benchmark for Large-Scale Single Object Tracking (2018, unknown): “VOT-2017 [27] 60 41 356 293 1,500 21K 11.”
Distractor-aware Siamese Networks for Visual Object Tracking (2018, methodology): “We validate the eﬀectiveness of proposed DaSiamRPN framework on extensive short-term and long-term tracking benchmarks: VOT2016 [14], VOT2017 [12], OTB2015 [38], UAV20L and UAV123 [22].”
Unveiling the Power of Deep Tracking (2018, methodology): “The evaluation metrics are computed as an average over 15 runs (see [6] for further details).”
Is First Person Vision Challenging for Object Tracking? (2020, unknown): “Since many FPV tasks require real-time computation, we evaluated the ability of trackers to provide their object localization in such a setting by following the RTE protocol [14, 16].”
Learning Adaptive Discriminative Correlation Filters via Temporal Consistency Preserving Spatial Feature Selection for Robust Visual Object Tracking (2018, methodology): “Recently, considering the joint circular structure of sliding candidates, Discriminative Correlation Filter (DCF) based tracking methods [7], [8] have achieved outstanding performance in many challenging benchmarks and competitions [5], [9], [10].”
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].”
TrackingNet: A Large-Scale Dataset and Benchmark for Object Tracking in the Wild (2018, methodology): “Third, we show that challenges in OTB100 [5] and VOT17 [11] focus on objects with slightly larger motion, while TrackingNet shows a more natural motion distribution over the fastest moving instances in YT-BB.”