MeMu: Metric correlation Siamese network and multi-class negative sampling for visual tracking

Xiao, Yafu; Li, Jing; Du, Bo; Wu, Jia; Chang, Jun; Zhang, Wenfan

doi:10.1016/j.patcog.2019.107170

Cited by 19 publications

(3 citation statements)

References 21 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…[15] and [16] respectively use context-adaptive and accelerated correlation filters for tracking. In the deep tracking methods, [17,18,19] adopt attention or Siamese neural networks for tracking. Compared with the conventional tracking methods, event-based tracking methods [20,21,22] show their superiority under fast motions and HDR scenes.…”

Section: Related Workmentioning

confidence: 99%

Event Data Association via Robust Model Fitting for Event-based Object Tracking

Chen¹,

Lin²,

Suter³

et al. 2021

Preprint

View full text Add to dashboard Cite

Event-based approaches, which are based on bio-inspired asynchronous event cameras, have achieved promising performance on various computer vision tasks.However, the study of the fundamental event data association problem is still in its infancy. In this paper, we propose a novel Event Data Association approach (called EDA) to explicitly address the data association problem. The proposed EDA seeks for event trajectories that best fit the event data, in order to perform unifying data association. In EDA, we first asynchronously gather the event data, based on its information entropy. Then, we introduce a deterministic model hypothesis generation strategy, which effectively generates model hypotheses from the gathered events, to represent the corresponding event trajectories. After that, we present a two-stage weighting algorithm, which robustly weighs and selects true models from the generated model hypotheses, through multi-structural geometric model fitting. Meanwhile, we also propose an adaptive model selection strategy to automatically determine the number of the true models. Finally, we use the selected true models to associate the event data, without being affected by sensor noise and irrelevant structures. We evaluate the performance of the proposed EDA on the object tracking task. The experimental results show the effectiveness of EDA under challenging scenarios, such as high speed, motion blur, and high dynamic range conditions.

show abstract

Section: Related Workmentioning

confidence: 99%

Event Data Association via Robust Model Fitting for Event-based Object Tracking

Chen¹,

Lin²,

Suter³

et al. 2021

Preprint

View full text Add to dashboard Cite

show abstract

“…Nowadays, the Siamese neural network has become a popular method in image recognition, partly due to the advantage that it does not require a large amount of data in the inference phase [14][15][16][17][18]. The Siamese neural network takes two samples as the input and outputs the spatial features after dimensionality reduction.…”

Section: Introductionmentioning

confidence: 99%

3D Expression-Invariant Face Verification Based on Transfer Learning and Siamese Network for Small Sample Size

Sun

et al. 2021

Electronics

View full text Add to dashboard Cite

Three-dimensional (3D) face recognition has become a trending research direction in both industry and academia. However, traditional facial recognition methods carry high computational costs and face data storage costs. Deep learning has led to a significant improvement in the recognition rate, but small sample sizes represent a new problem. In this paper, we present an expression-invariant 3D face recognition method based on transfer learning and Siamese networks that can resolve the small sample size issue. First, a landmark detection method utilizing the shape index was employed for facial alignment. Then, a convolutional network (CNN) was constructed with transfer learning and trained with the aligned 3D facial data for face recognition, enabling the CNN to recognize faces regardless of facial expressions. Following that, the weighted trained CNN was shared by a Siamese network to build a 3D facial recognition model that can identify faces even with a small sample size. Our experimental results showed that the proposed method reached a recognition rate of 0.977 on the FRGC database, and the network can be used for facial recognition with a single sample.

show abstract

“…More recently, research on visual tracking has focused on deep learning based methods , , Danelljan et al [2020]. Much attention has been paid into siamese networks Xiao et al [2020], which always extract deep features and then locate the target by measuring the similarity of extracted features. Although trained through the large scale datasets, the early siamese trackers have not been able to achieve state-of-the-art (SOTA) performance.…”

Section: Introductionmentioning

confidence: 99%

DCF-ASN: Coarse-to-fine Real-time Visual Tracking via Discriminative Correlation Filter and Attentional Siamese Network

Xue¹,

Liu²,

Yin³

et al. 2021

Preprint

View full text Add to dashboard Cite

Discriminative correlation filters (DCF) and siamese networks have achieved promising performance on visual tracking tasks thanks to their superior computational efficiency and reliable similarity metric learning, respectively. However, how to effectively take advantages of powerful deep networks, while maintaining the real-time response of DCF, remains a challenging problem. Embedding the cross-correlation operator as a separate layer into siamese networks is a popular choice to enhance the tracking accuracy. Being a key component of such a network, the correlation layer is updated online together with other parts of the network. Yet, when facing serious disturbance, fused trackers may still drift away from the target completely due to accumulated errors. To address these issues, we propose a coarse-to-fine tracking framework, which roughly infers the target state via an online-updating DCF module first and subsequently, finely locates the target through an offline-training asymmetric siamese network (ASN). Benefitting from the guidance of DCF and the learned channel weights obtained through exploiting the given ground-truth template, ASN refines feature representation and implements precise target localization. Systematic experiments on five popular tracking datasets demonstrate that the proposed DCF-ASN achieves the state-of-the-art performance while exhibiting good tracking efficiency.

show abstract

MeMu: Metric correlation Siamese network and multi-class negative sampling for visual tracking

Cited by 19 publications

References 21 publications

Event Data Association via Robust Model Fitting for Event-based Object Tracking

Event Data Association via Robust Model Fitting for Event-based Object Tracking

3D Expression-Invariant Face Verification Based on Transfer Learning and Siamese Network for Small Sample Size

DCF-ASN: Coarse-to-fine Real-time Visual Tracking via Discriminative Correlation Filter and Attentional Siamese Network

Contact Info

Product

Resources

About