GOT-10k: A Large High-Diversity Benchmark for Generic Object Tracking in the Wild

Huang, Lianghua; Zhao, Xin; Huang, Kaiqi

doi:10.1109/tpami.2019.2957464

Cited by 1,178 publications

(868 citation statements)

References 91 publications

(208 reference statements)

Supporting

Mentioning

863

Contrasting

Order By: Relevance

“…The benchmarks are divided into two categories, the validation set including OTB2013 [43] and OTB2015 [44], and the testing set including VOT2017 [20], VOT2018 [19], and GOT10k [17]. We introduce the implementation details in the next sub-section and then we compare the proposed tracker to the state-ofthe-art trackers.…”

Section: Resultsmentioning

confidence: 99%

DomainSiam: Domain-Aware Siamese Network for Visual Object Tracking

Abdelpakey

Shehata

2019

Advances in Visual Computing

View full text Add to dashboard Cite

Visual object tracking is a fundamental task in the field of computer vision. Recently, Siamese trackers have achieved state-of-theart performance on recent benchmarks. However, Siamese trackers do not fully utilize semantic and objectness information from pre-trained networks that have been trained on the image classification task. Furthermore, the pre-trained Siamese architecture is sparsely activated by the category label which leads to unnecessary calculations and overfitting. In this paper, we propose to learn a Domain-Aware, that is fully utilizing semantic and objectness information while producing a class-agnostic using a ridge regression network. Moreover, to reduce the sparsity problem, we solve the ridge regression problem with a differentiable weighteddynamic loss function. Our tracker, dubbed DomainSiam, improves the feature learning in the training phase and generalization capability to other domains. Extensive experiments are performed on five tracking benchmarks including OTB2013 and OTB2015 for a validation set; as well as the VOT2017, VOT2018, LaSOT, TrackingNet, and GOT10k for a testing set. DomainSiam achieves a state-of-the-art performance on these benchmarks while running at 53 FPS.

show abstract

Section: Resultsmentioning

confidence: 99%

DomainSiam: Domain-Aware Siamese Network for Visual Object Tracking

Abdelpakey

Shehata

2019

Advances in Visual Computing

View full text Add to dashboard Cite

show abstract

“…To obtain tracking demonstrations, we ran SiamFC on the training set of GOT-10k dataset [18]. The implemented SiamFC was trained on the ImageNet VID dataset [8].…”

Section: Implementation Detailsmentioning

confidence: 99%

“…Training Dataset. To train A3CT and A3CTD we leveraged of the training set of the GOT-10k dataset [18]. This is a large-scale dataset containing 9335 training videos, 180 validation videos and other 180 videos for testing.…”

Section: Implementation Detailsmentioning

confidence: 99%

See 1 more Smart Citation

Visual Tracking by Means of Deep Reinforcement Learning and an Expert Demonstrator

Dunnhofer

Martinel

Foresti

et al. 2019

2019 IEEE/CVF International Conference on Computer Vision Workshop (ICCVW)

View full text Add to dashboard Cite

In the last decade many different algorithms have been proposed to track a generic object in videos. Their execution on recent large-scale video datasets can produce a great amount of various tracking behaviours. New trends in Reinforcement Learning showed that demonstrations of an expert agent can be efficiently used to speed-up the process of policy learning. Taking inspiration from such works and from the recent applications of Reinforcement Learning to visual tracking, we propose two novel trackers, A3CT, which exploits demonstrations of a state-of-the-art tracker to learn an effective tracking policy, and A3CTD, that takes advantage of the same expert tracker to correct its behaviour during tracking. Through an extensive experimental validation on the GOT-10k, OTB-100, LaSOT, UAV123 and VOT benchmarks, we show that the proposed trackers achieve state-of-the-art performance while running in real-time. arXiv:1909.08487v1 [cs.CV] 18 Sep 2019 =

show abstract

“…First column: appearance target. Because our method does not require keypoint-annotations or class information, it can be readily applied on video datasets [23,14]. Besides intra-species analogies, our approach can also imagine inter-species analogies: How does a cow look like in a pose specified by a horse?…”

Section: Introductionmentioning

confidence: 99%

Unsupervised Robust Disentangling of Latent Characteristics for Image Synthesis

Esser

Haux

Ommer

2019

2019 IEEE/CVF International Conference on Computer Vision (ICCV)

View full text Add to dashboard Cite

Deep generative models come with the promise to learn an explainable representation for visual objects that allows image sampling, synthesis, and selective modification. The main challenge is to learn to properly model the independent latent characteristics of an object, especially its appearance and pose. We present a novel approach that learns disentangled representations of these characteristics and explains them individually. Training requires only pairs of images depicting the same object appearance, but no pose annotations. We propose an additional classifier that estimates the minimal amount of regularization required to enforce disentanglement. Thus both representations together can completely explain an image while being independent of each other. Previous methods based on adversarial approaches fail to enforce this independence, while methods based on variational approaches lead to uninformative representations. In experiments on diverse object categories, the approach successfully recombines pose and appearance to reconstruct and retarget novel synthesized images. We achieve significant improvements over stateof-the-art methods which utilize the same level of supervision, and reach performances comparable to those of posesupervised approaches. However, we can handle the vast body of articulated object classes for which no pose models/annotations are available.

show abstract

GOT-10k: A Large High-Diversity Benchmark for Generic Object Tracking in the Wild

Cited by 1,178 publications

References 91 publications

DomainSiam: Domain-Aware Siamese Network for Visual Object Tracking

DomainSiam: Domain-Aware Siamese Network for Visual Object Tracking

Visual Tracking by Means of Deep Reinforcement Learning and an Expert Demonstrator

Unsupervised Robust Disentangling of Latent Characteristics for Image Synthesis

Contact Info

Product

Resources

About