The Visual Object Tracking VOT2013 Challenge Results

Kristan, Matej; Pflugfelder, Roman; Leonardis, Ale; Matas, Jiřı́; Porikli, Fatih; Čehovin, Luka; Nebehay, Georg; Fernández, Gustavo J.; Vojir, Toma; Gatt, Adam; Khajenezhad, Ahmad; Salahledin, Ahmed; Soltani-Farani, Ali; Zarezade, Ali; Petrosino, Alfredo; Milton, Anthony; Bozorgtabar, Behzad; Li, Bo; Chan, Chee Seng; Heng, Cherkeng; Ward, Dale; Kearney, David; Monekosso, Dorothy; Karaimer, Hakkı Can; Rabiee, Hamid R.; Zhu, Jing; Gao, Jin; Xiao, Jingjing; Zhang, Junge; Xing, Junliang; Huang, Kaiqi; Lebeda, Karel; Cao, Lijun; Maresca, Mario Edoardo; Lim, Mei Kuan; Helw, Mohamed El; Felsberg, Michael; Remagnino, Paolo; Bowden, Richard; Goecke, Roland; Stolkin, Rustam; Lim, Samantha YueYing; Maher, Sara; Poullot, Sébastien; Wong, Sebastien C.; Satoh, Shin’ichi; Chen, Weihua; Hu, Weiming; Zhang, Xiaoqin; Li, Yang; Niu, Zhiheng

doi:10.1109/iccvw.2013.20

Cited by 265 publications

(302 citation statements)

References 44 publications

Supporting

Mentioning

264

Contrasting

Unclassified

Order By: Relevance

“…Some researchers have also attempted to use neural networks for tracking within the traditional online training framework [26,27,34,37,35,30,39,7,24,16], showing state-of-the-art results [30,7,21]. Unfortunately, neural networks are very slow to train, and if online training is required, then the resulting tracker will be very slow at test time.…”

Section: Related Workmentioning

confidence: 99%

“…Unfortunately, neural networks are very slow to train, and if online training is required, then the resulting tracker will be very slow at test time. Such trackers range from 0.8 fps [26] to 15 fps [37], with the top performing neural-network trackers running at 1 fps on a GPU [30,7,21]. Hence, these trackers are not usable for most practical applications.…”

Section: Related Workmentioning

confidence: 99%

“…We could not test our method on the VOT 2015 challenge [21] because there would be too much overlap between the test set and our training set. However, we expect the general trends of our method to still hold.…”

Section: Test Setmentioning

confidence: 99%

“…Unfortunately, such trackers are very slow to train, ranging from 0.8 fps [26] to 15 fps [37], with the top performing neuralnetwork trackers running at 1 fps [30,7,21]. Our tracker is trained offline in a generic manner, so no online training of our tracker is required.…”

Section: B Online Trainingmentioning

confidence: 99%

“…Online training of neural networks tends to be very slow, preventing real-time performance. Online-trained neural network trackers range from 0.8 fps [26] to 15 fps [37], with the top performing trackers running at 1 fps on a GPU [30,7,21]. Second, most trackers evaluate a finite number of samples and choose the highest scoring one as the tracking output [26,27,37,30,39,24,33].…”

Section: Overall Performancementioning

confidence: 99%

See 4 more Smart Citations

Learning to Track at 100 FPS with Deep Regression Networks

Held

Thrun

Savarese

2016

Lecture Notes in Computer Science

994

786

View full text Add to dashboard Cite

Abstract. Machine learning techniques are often used in computer vision due to their ability to leverage large amounts of training data to improve performance. Unfortunately, most generic object trackers are still trained from scratch online and do not benefit from the large number of videos that are readily available for offline training. We propose a method for offline training of neural networks that can track novel objects at test-time at 100 fps. Our tracker is significantly faster than previous methods that use neural networks for tracking, which are typically very slow to run and not practical for real-time applications. Our tracker uses a simple feed-forward network with no online training required. The tracker learns a generic relationship between object motion and appearance and can be used to track novel objects that do not appear in the training set. We test our network on a standard tracking benchmark to demonstrate our tracker's state-of-the-art performance. Further, our performance improves as we add more videos to our offline training set. To the best of our knowledge, our tracker 1 is the first neural-network tracker that learns to track generic objects at 100 fps.

show abstract

Section: Related Workmentioning

confidence: 99%

Section: Related Workmentioning

confidence: 99%

Section: Test Setmentioning

confidence: 99%

Section: B Online Trainingmentioning

confidence: 99%

Section: Overall Performancementioning

confidence: 99%

See 3 more Smart Citations

Learning to Track at 100 FPS with Deep Regression Networks

Held

Thrun

Savarese

2016

Lecture Notes in Computer Science

994

786

View full text Add to dashboard Cite

show abstract

Visual Tracking via Spatially Aligned Correlation Filters Network

Zhang

Wang

Gao

et al. 2018

Computer Vision – ECCV 2018

Self Cite

View full text Add to dashboard Cite

Correlation filters based trackers rely on a periodic assumption of the search sample to efficiently distinguish the target from the background. This assumption however yields undesired boundary effects and restricts aspect ratios of search samples. To handle these issues, an end-to-end deep architecture is proposed to incorporate geometric transformations into a correlation filters based network. This architecture introduces a novel spatial alignment module, which provides continuous feedback for transforming the target from the border to the center with a normalized aspect ratio. It enables correlation filters to work on well-aligned samples for better tracking. The whole architecture not only learns a generic relationship between object geometric transformations and object appearances, but also learns robust representations coupled to correlation filters in case of various geometric transformations. This lightweight architecture permits real-time speed. Experiments show our tracker effectively handles boundary effects and aspect ratio variations, achieving state-of-the-art tracking results on recent benchmarks.

show abstract

Real-Time MDNet

Jung

Son

Baek

et al. 2018

Lecture Notes in Computer Science

300

211

View full text Add to dashboard Cite

We present a fast and accurate visual tracking algorithm based on the multi-domain convolutional neural network (MDNet). The proposed approach accelerates feature extraction procedure and learns more discriminative models for instance classification; it enhances representation quality of target and background by maintaining a high resolution feature map with a large receptive field per activation. We also introduce a novel loss term to differentiate foreground instances across multiple domains and learn a more discriminative embedding of target objects with similar semantics. The proposed techniques are integrated into the pipeline of a well known CNN-based visual tracking algorithm, MDNet. We accomplish approximately 25 times speed-up with almost identical accuracy compared to MDNet. Our algorithm is evaluated in multiple popular tracking benchmark datasets including OTB2015, UAV123, and TempleColor, and outperforms the state-of-the-art real-time tracking methods consistently even without dataset-specific parameter tuning.

show abstract

The Visual Object Tracking VOT2013 Challenge Results

Cited by 265 publications

References 44 publications

Learning to Track at 100 FPS with Deep Regression Networks

Learning to Track at 100 FPS with Deep Regression Networks

Visual Tracking via Spatially Aligned Correlation Filters Network

Real-Time MDNet

Contact Info

Product

Resources

About