Book ChapterDOI
The Eighth Visual Object Tracking VOT2020 Challenge Results
Matej Kristan,Ales Leonardis,Jiří Matas,Michael Felsberg,Roman Pflugfelder,Roman Pflugfelder,Joni-Kristian Kamarainen,Martin Danelljan,Luka Čehovin Zajc,Alan Lukežič,Ondrej Drbohlav,Linbo He,Yushan Zhang,Yushan Zhang,Song Yan,Jinyu Yang,Gustavo Fernandez,Alexander G. Hauptmann,Alireza Memarmoghadam,Alvaro Garcia-Martin,Andreas Robinson,Anton Varfolomieiev,Awet Haileslassie Gebrehiwot,Bedirhan Uzun,Bin Yan,Bing Li,Chen Qian,Chi-Yi Tsai,Christian Micheloni,Dong Wang,Fei Wang,Fei Xie,Felix Järemo Lawin,Fredrik K. Gustafsson,Gian Luca Foresti,Goutam Bhat,Guangqi Chen,Haibin Ling,Haitao Zhang,Hakan Cevikalp,Haojie Zhao,Haoran Bai,Hari Chandana Kuchibhotla,Hasan Saribas,Heng Fan,Hossein Ghanei-Yakhdan,Houqiang Li,Houwen Peng,Huchuan Lu,Hui Li,Javad Khaghani,Jesús Bescós,Jianhua Li,Jianlong Fu,Jiaqian Yu,Jingtao Xu,Josef Kittler,Jun Yin,Junhyun Lee,Kaicheng Yu,Kaiwen Liu,Kang Yang,Kenan Dai,Li Cheng,Li Zhang,Lijun Wang,Linyuan Wang,Luc Van Gool,Luca Bertinetto,Matteo Dunnhofer,Miao Cheng,Mohana Murali Dasari,Ning Wang,Pengyu Zhang,Philip H. S. Torr,Qiang Wang,Radu Timofte,Rama Krishna Sai Subrahmanyam Gorthi,Seokeon Choi,Seyed Mojtaba Marvasti-Zadeh,Shaochuan Zhao,Shohreh Kasaei,Shoumeng Qiu,Shuhao Chen,Thomas B. Schön,Tianyang Xu,Wei Lu,Weiming Hu,Wengang Zhou,Xi Qiu,Xiao Ke,Xiaojun Wu,Xiaolin Zhang,Xiaoyun Yang,Xue-Feng Zhu,Yingjie Jiang,Yingming Wang,Yiwei Chen,Yu Ye,Yuezhou Li,Yuncon Yao,Yunsung Lee,Yuzhang Gu,Zezhou Wang,Zhangyong Tang,Zhen-Hua Feng,Zhijun Mai,Zhipeng Zhang,Zhirong Wu,Ziang Ma +109 more
- pp 547-601
TLDR
A significant novelty is introduction of a new VOT short-term tracking evaluation methodology, and introduction of segmentation ground truth in the VOT-ST2020 challenge – bounding boxes will no longer be used in theVDT challenges.Abstract:
The Visual Object Tracking challenge VOT2020 is the eighth annual tracker benchmarking activity organized by the VOT initiative. Results of 58 trackers are presented; many are state-of-the-art trackers published at major computer vision conferences or in journals in the recent years. The VOT2020 challenge was composed of five sub-challenges focusing on different tracking domains: (i) VOT-ST2020 challenge focused on short-term tracking in RGB, (ii) VOT-RT2020 challenge focused on “real-time” short-term tracking in RGB, (iii) VOT-LT2020 focused on long-term tracking namely coping with target disappearance and reappearance, (iv) VOT-RGBT2020 challenge focused on short-term tracking in RGB and thermal imagery and (v) VOT-RGBD2020 challenge focused on long-term tracking in RGB and depth imagery. Only the VOT-ST2020 datasets were refreshed. A significant novelty is introduction of a new VOT short-term tracking evaluation methodology, and introduction of segmentation ground truth in the VOT-ST2020 challenge – bounding boxes will no longer be used in the VOT-ST challenges. A new VOT Python toolkit that implements all these novelites was introduced. 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 (http://votchallenge.net).read more
Citations
More filters
Journal ArticleDOI
RFN-Nest: An end-to-end residual fusion network for infrared and visible images
Hui Li,Xiaojun Wu,Josef Kittler +2 more
TL;DR: A residual fusion network (RFN) which is based on a residual architecture to replace the traditional fusion approach is proposed which delivers a better performance than the state-of-the-art methods in both subjective and objective evaluation.
Posted Content
Alpha-Refine: Boosting Tracking Performance by Precise Bounding Box Estimation
TL;DR: This work proposes a novel, flexible, and accurate refinement module called Alpha-Refine (AR), which can significantly improve the base trackers’ box estimation quality and leads to a series of strengthened trackers, among which the ARSiamRPN (AR strengthened Siam RPNpp) and the ARDiMP50 ( AR strengthened DiMP50) achieve good efficiency-precision trade-off.
Proceedings ArticleDOI
STMTrack: Template-free Visual Tracking with Space-time Memory Networks
TL;DR: Zhang et al. as mentioned in this paper proposed a novel tracking framework built on top of a space-time memory network that is competent to make full use of historical information related to the target for better adapting to appearance variations during tracking.
Posted Content
STMTrack: Template-free Visual Tracking with Space-time Memory Networks
TL;DR: A novel tracking framework built on top of a space-time memory network that is competent to make full use of historical information related to the target for better adapting to appearance variations during tracking is proposed.
Proceedings ArticleDOI
MixFormer: End-to-End Tracking with Iterative Mixed Attention
TL;DR: This paper proposes a compact tracking framework, termed as MixFormer, built upon transformers, to utilize the flexibility of attention operations, and proposes a Mixed Attention Module (MAM) for simultaneous feature extraction and target information integration.
References
More filters
Book ChapterDOI
U-Net: Convolutional Networks for Biomedical Image Segmentation
TL;DR: Neber et al. as discussed by the authors proposed a network and training strategy that relies on the strong use of data augmentation to use the available annotated samples more efficiently, which can be trained end-to-end from very few images and outperforms the prior best method (a sliding-window convolutional network) on the ISBI challenge for segmentation of neuronal structures in electron microscopic stacks.
Journal ArticleDOI
ImageNet Large Scale Visual Recognition Challenge
Olga Russakovsky,Jia Deng,Hao Su,Jonathan Krause,Sanjeev Satheesh,Sean Ma,Zhiheng Huang,Andrej Karpathy,Aditya Khosla,Michael S. Bernstein,Alexander C. Berg,Li Fei-Fei +11 more
TL;DR: The ImageNet Large Scale Visual Recognition Challenge (ILSVRC) as mentioned in this paper is a benchmark in object category classification and detection on hundreds of object categories and millions of images, which has been run annually from 2010 to present, attracting participation from more than fifty institutions.
Book ChapterDOI
Microsoft COCO: Common Objects in Context
Tsung-Yi Lin,Michael Maire,Serge Belongie,James Hays,Pietro Perona,Deva Ramanan,Piotr Dollár,C. Lawrence Zitnick +7 more
TL;DR: A new dataset with the goal of advancing the state-of-the-art in object recognition by placing the question of object recognition in the context of the broader question of scene understanding by gathering images of complex everyday scenes containing common objects in their natural context.
Posted Content
U-Net: Convolutional Networks for Biomedical Image Segmentation
TL;DR: It is shown that such a network can be trained end-to-end from very few images and outperforms the prior best method (a sliding-window convolutional network) on the ISBI challenge for segmentation of neuronal structures in electron microscopic stacks.
Book ChapterDOI
Encoder-Decoder with Atrous Separable Convolution for Semantic Image Segmentation
TL;DR: This work extends DeepLabv3 by adding a simple yet effective decoder module to refine the segmentation results especially along object boundaries and applies the depthwise separable convolution to both Atrous Spatial Pyramid Pooling and decoder modules, resulting in a faster and stronger encoder-decoder network.