Convolutional neural network with structural input for visual object tracking

Fiaz, Mustansar; Mahmood, Arif; Jung, Soon Ki

doi:10.1145/3297280.3297416

Cited by 8 publications

(8 citation statements)

References 45 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…We compared our method with 30 state-of-the-art trackers including SiamTri [ 55 ], CSRDCF [ 48 ], CNNSI [ 56 ], SRDCF [ 57 ], Staple [ 58 ], TRACA [ 59 ], SiameseFC [ 15 ], CFNet [ 10 ], ACFN [ 24 ], SiamFc-lu [ 60 ], HASiam [ 61 ], SiamFCRes22 [ 62 ], Kuai et al [ 63 ], MSN [ 64 ], MLT [ 65 ], KCF [ 66 ], SCT [ 67 ], OA-LSTM [ 68 ], ECOhc [ 23 ], DSiam [ 69 ], MEEM [ 70 ], CCOT [ 40 ], SAMF [ 71 ], CMKCF [ 72 ], SATIN [ 73 ], GradNet [ 74 ], SiameseRPN [ 75 ] DSST [ 76 ], MemTrack [ 14 ], MemDTC [ 77 ], and UDT [ 78 ].…”

Section: Methodsmentioning

confidence: 99%

“…We validate the proposed IRCA-Siam tracker over TC128 benchmark dataset and showed the precision and success in Table 2 . We compared our method with UDT [ 78 ], Kuai et al [ 63 ], KC [ 66 ], MLT [ 65 ], SCT [ 67 ], SiameseFC [ 15 ], CFNet [ 10 ], Staple [ 58 ], CNNSI [ 56 ], OA-LSTM [ 68 ], and SRDCF [ 57 ]. The proposed method secured the first rank compared to other trackers with maximum precision score 74.5 and success 55.0.…”

Section: Methodsmentioning

confidence: 99%

See 1 more Smart Citation

Improving Object Tracking by Added Noise and Channel Attention

Fiaz

Mahmood

Baek

et al. 2020

Sensors

Self Cite

View full text Add to dashboard Cite

CNN-based trackers, especially those based on Siamese networks, have recently attracted considerable attention because of their relatively good performance and low computational cost. For many Siamese trackers, learning a generic object model from a large-scale dataset is still a challenging task. In the current study, we introduce input noise as regularization in the training data to improve generalization of the learned model. We propose an Input-Regularized Channel Attentional Siamese (IRCA-Siam) tracker which exhibits improved generalization compared to the current state-of-the-art trackers. In particular, we exploit offline learning by introducing additive noise for input data augmentation to mitigate the overfitting problem. We propose feature fusion from noisy and clean input channels which improves the target localization. Channel attention integrated with our framework helps finding more useful target features resulting in further performance improvement. Our proposed IRCA-Siam enhances the discrimination of the tracker/background and improves fault tolerance and generalization. An extensive experimental evaluation on six benchmark datasets including OTB2013, OTB2015, TC128, UAV123, VOT2016 and VOT2017 demonstrate superior performance of the proposed IRCA-Siam tracker compared to the 30 existing state-of-the-art trackers.

show abstract

Section: Methodsmentioning

confidence: 99%

Section: Methodsmentioning

confidence: 99%

Improving Object Tracking by Added Noise and Channel Attention

Fiaz

Mahmood

Baek

et al. 2020

Sensors

Self Cite

View full text Add to dashboard Cite

show abstract

“…Fiaz et al [56] proposed CNN with structural input (CNNSI) to exploit the deep discriminative features to learn the similarity between the target and candidate patches as shown in Figure 6. The target and candidate images are stacked together and feed-forwarded to the network to get the similarity and dissimilarity scores.…”

Section: Cnnsimentioning

confidence: 99%

“…For comparison of different Siamese architectures, we carefully selected Siamese trackers such that at least one tracker is selected from each category. The selected trackers are SINT [51], SiameseFC [46], CFNet [52], SIAMRPN [53], GOTURN [45], and CNNSI [56]. All results are reported from the original authors except, the GOTURN because the authors did not report results over the selected benchmarks.…”

Section: Experimental Analysismentioning

confidence: 99%

Deep Siamese Networks toward Robust Visual Tracking

Fiaz¹,

Mahmood²,

Jung³

2019

Visual Object Tracking With Deep Neural Networks

Self Cite

View full text Add to dashboard Cite

Recently, Siamese neural networks have been widely used in visual object tracking to leverage the template matching mechanism. Siamese network architecture contains two parallel streams to estimate the similarity between two inputs and has the ability to learn their discriminative features. Various deep Siamese-based tracking frameworks have been proposed to estimate the similarity between the target and the search region. In this chapter, we categorize deep Siamese networks into three categories by the position of the merging layers as late merge, intermediate merge and early merge architectures. In the late merge architecture, inputs are processed as two separate streams and merged at the end of the network, while in the intermediate merge architecture, inputs are initially processed separately and merged intermediate well before the final layer. Whereas in the early merge architecture, inputs are combined at the start of the network and a unified data stream is processed by a single convolutional neural network. We evaluate the performance of deep Siamese trackers based on the merge architectures and their output such as similarity score, response map, and bounding box in various tracking challenges. This chapter will give an overview of the recent development in deep Siamese trackers and provide insights for the new developments in the tracking field.

show abstract

“…Recently, due to the powerful feature representation ability of the Convolutional neural networks (CNNs), have gained considerable research attention recently in many computer vision fields, such as semantic segmentation [13], object detection [14], and activity recognition [15]. Deep features are exploited within DCF based trackers to address these challenges, including HDT [16], deepSRDCF [17], and ECO [18]; or deep tracking frameworks MDNet [19], CNNSI [20], and FCNT [21]. However, using the pre-trained model as the tracker backbone for feature extraction is unsuitable due to inconsistencies between tracking and other visual tasks.…”

Section: Introductionmentioning

confidence: 99%

Efficient Visual Tracking With Stacked Channel-Spatial Attention Learning

2020

Self Cite

View full text Add to dashboard Cite

Template based learning, particularly Siamese networks, has recently become popular due to balancing accuracy and speed. However, preserving tracker robustness against challenging scenarios with real-time speed is a primary concern for visual object tracking. Siamese trackers confront difficulties handling target appearance changes continually due to less discrimination ability learning between target and background information. This paper presents stacked channel-spatial attention within Siamese networks to improve tracker robustness without sacrificing fast-tracking speed. The proposed channel attention strengthens target-specific channels increasing their weight while reducing the importance of irrelevant channels with lower weights. Spatial attention is focusing on the most informative region of the target feature map. We integrate the proposed channel and spatial attention modules to enhance tracking performance with end-to-end learning. The proposed tracking framework learns what and where to highlight important target information for efficient tracking. Experimental results on widely used OTB100, OTB50, VOT2016, VOT2017/18, TC-128, and UAV123 benchmarks verified the proposed tracker achieved outstanding performance compared with state-of-the-art trackers. INDEX TERMS Deep learning, Siamese architecture, stacked channel-spatial attention, visual object tracking.

show abstract

Convolutional neural network with structural input for visual object tracking

Cited by 8 publications

References 45 publications

Improving Object Tracking by Added Noise and Channel Attention

Improving Object Tracking by Added Noise and Channel Attention

Deep Siamese Networks toward Robust Visual Tracking

Efficient Visual Tracking With Stacked Channel-Spatial Attention Learning

Contact Info

Product

Resources

About