The Seventh Visual Object Tracking VOT2019 Challenge Results

By Matej Kristan, Jiri Matas, Ales Leonardis, Michael Felsberg, Roman P. Pflugfelder, Joni-Kristian, Kämäräinen, L. Č. Zajc, O. Drbohlav, Alan Lukezic and 188 more. 2019 IEEE/CVF International Conference on Computer Vision Workshop (ICCVW), 2019

486 citations recorded by the source corpus.

The Visual Object Tracking challenge VOT2019 is the seventh annual tracker benchmarking activity organized by the VOT initiative. Results of 81 trackers are presented; many are state-of-the-art trackers published at major computer vision conferences or in journals in the recent years. The evaluation included the standard VOT and other popular methodologies for short-term tracking analysis as well as the standard VOT methodology for long-term tracking analysis. The VOT2019 challenge was composed of five challenges focusing on different tracking domains: (i) VOTST2019 challenge focused on short-term tracking in RGB, (ii) VOT-RT2019 challenge focused on "real-time" shortterm tracking in RGB, (iii) VOT-LT2019 focused on longterm tracking namely coping with target disappearance and reappearance. Two new challenges have been introduced: (iv) VOT-RGBT2019 challenge focused on short-term tracking in RGB and thermal imagery and (v) VOT-RGBD2019 challenge focused on long-term tracking in RGB and depth imagery. The VOT-ST2019, VOT-RT2019 and VOT-LT2019 datasets were refreshed while new datasets were introduced for VOT-RGBT2019 and VOT-RGBD2019. The VOT toolkit has been updated to support both standard shortterm, long-term tracking and tracking with multi-channel imagery. 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 dataset, the evaluation kit and the results are publicly available at the challenge website.

Subfields: Aerospace Engineering, Computer Vision and Pattern Recognition

View Paper: https://www.semanticscholar.org/paper/786577081e00d69eeac8e9612eaf2dad59765e73

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

Citations in the corpus

MDLatLRR: A Novel Decomposition Method for Infrared and Visible Image Fusion (2018, methodology): “As described in VOT2019 [12], the visual objecting tracking”
Is First Person Vision Challenging for Object Tracking? (2020, unknown): “Nowadays, the state-of-the-art tracking solutions achieve excellent results on a large variety of tracking domains [85, 60, 31, 46].”
Track Anything: Segment Anything Meets Videos (2023, background): “On the other hand, tracking or segmenting in videos faces challenges from scale variation, target deformation, motion blur, camera motion, similar objects, and so on [4, 8, 10, 7, 9, 6].”
LasHeR: A Large-Scale High-Diversity Benchmark for RGBT Tracking (2021, methodology): “With increasing interests of RGBT tracking, the VOT challenges [2] take RGBT tracking as a new challenge and introduce the VOT-RGBTIR2019 dataset elaborately designed based on RGBT234.”
Ocean: Object-aware Anchor-free Tracking (2020, methodology): “ty of our model. We report the average performance of the three-time runs in the following comparisons. Evaluation datasets and metrics. We use ve benchmark datasets including VOT-2018 [17], VOT-2019 [18], OTB-100 [44], GOT-10k [14] and LaSOT [8] for tracking performance evaluation. In particular, V”
Siamese Box Adaptive Network for Visual Tracking (2020, background): “SA SIAM R [18] SiamCRF RT [18] SPM [39] SiamRPN++ [20] SiamMask [42] ARTCS [18] SiamDW ST [49] DCFST [18] DiMP [2] Ours”
NestFuse: An Infrared and Visible Image Fusion Architecture Based on Nest Connection and Spatial/Channel Attention Models (2020, methodology): “Current state-of-the-art fusion algorithms are widely employed in many applications, such as in selfdriving vehicles, visual tracking [2] [3] [4] and video surveil-”
Learning Target Candidate Association to Keep Track of What Not to Track (2021, methodology): “So do KeepTrack and KeepTrackFast that perform similarly to the top methods, with a 0.8% and 1.1% AUC gain over the SuperDiMP baseline.”
RFN-Nest: An end-to-end residual fusion network for infrared and visible images (2021, methodology): “In addition to the base tracker (AFAT), we choose two further trackers for each dataset (VOT2019, VOT2020) to analyze the tracking performance of RFN-based AFAT.”
Visual Prompt Multi-Modal Tracking (2023, methodology): “CA3DMS [31] SiamM Ds [18] Siam LTD [17] LTDSEd [18] DAL [37] CLGS D [17] LTMU B [17] ATCAIS [17] DDiMP [17] DeT [47] OSTrack [49] SPT [60] ProTrack [48] ViPT [47].”
Learning Spatio-Temporal Transformer for Visual Tracking (2021, methodology): “Different from previous reset-based evaluations [26], VOT2020 [25] proposes a new anchor-based evaluation protocol and uses binary segmentation masks as the groundtruth.”