Skip to main content
main-content

Tipp

Weitere Artikel dieser Ausgabe durch Wischen aufrufen

13.08.2022

A Lightweight Neural Learning Algorithm for Real-Time Facial Feature Tracking System via Split-Attention and Heterogeneous Convolution

verfasst von: Yuandong Ma, Qing Song, Mengjie Hu, Xiaotong Zhu

Erschienen in: Neural Processing Letters

Einloggen, um Zugang zu erhalten
share
TEILEN

Abstract

Object tracking has made remarkable progress in the past few years. But most advanced trackers are becoming more expensive, which limits their deployment in mobile devices with limited resources. In addition, the current popular tracker realizes similarity learning through the feature correlation between multiple branches. Some of these cross-correlation methods lost a lot of face information, and some introduced a lot of unfavorable background information. Based on this motivation, this paper is committed to reducing the number of algorithm parameters and enhancing the ability of feature extraction. Heterogeneous convolution is introduced into the backbone network to reduce the convolution kernel parameters. Add a search box mechanism to dynamically adjust the network receiving domain to generate more feature maps with cheap operations. Furthermore, we also integrate the split-attention mechanism into the backbone network to standardize the arrangement of heterogeneous convolution. To evaluate the model, we conducted experiments on challenging VTB datasets and actual shooting datasets, which contain 82,351 facial features. Experimental results show that our method distance precision (DP) and overlap success precision (OP) are 93.5% and 67.5% respectively, which are comparable with the state-of-the-art object tracking methods and reduce about one-third of the parameters. Meanwhile, the feature mapping of each convolution module is explored, and the interpretation of lightweight convolution is given.
Literatur
1.
Zurück zum Zitat S, Aydın.: Deep Learning Classification of Neuro-Emotional Phase Domain Complexity Levels Induced by Affective Video Film Clips.IEEE Journal of Biomedical and Health Informatics. 24 (6), pp.1695–1702 S, Aydın.: Deep Learning Classification of Neuro-Emotional Phase Domain Complexity Levels Induced by Affective Video Film Clips.IEEE Journal of Biomedical and Health Informatics. 24 (6), pp.1695–1702
3.
Zurück zum Zitat Yu X, Li Y, Zhang S, Xue C, Yu W (2020) Estimation of human impedance and motion intention for constrained human–robot interaction. Neurocomputing 37(6):390–403 Yu X, Li Y, Zhang S, Xue C, Yu W (2020) Estimation of human impedance and motion intention for constrained human–robot interaction. Neurocomputing 37(6):390–403
4.
Zurück zum Zitat Eduardo SLG, Manuel MO (2011) Domain transform for edge-aware image and video processing. ACM SIGGRAPH 2011 papers (SIGGRAPH ‘11). Association for Computing Machinery, New York, NY, USA, pp 1–12 Eduardo SLG, Manuel MO (2011) Domain transform for edge-aware image and video processing. ACM SIGGRAPH 2011 papers (SIGGRAPH ‘11). Association for Computing Machinery, New York, NY, USA, pp 1–12
5.
Zurück zum Zitat Wu J, Ji Y, Sun X et al (2020) Price Regulation Mechanism of Travelers’ Travel Mode Choice in the Driverless Transportation Network. J Adv Transp 20(3):1–9 Wu J, Ji Y, Sun X et al (2020) Price Regulation Mechanism of Travelers’ Travel Mode Choice in the Driverless Transportation Network. J Adv Transp 20(3):1–9
6.
Zurück zum Zitat Zolfaghari M, Ghanei-Yakhdan H, Yazdi M (2020) Real-time object tracking based on an adaptive transition model and extended Kalman filter to handle full occlusion. Vis Comput 36:701–715 CrossRef Zolfaghari M, Ghanei-Yakhdan H, Yazdi M (2020) Real-time object tracking based on an adaptive transition model and extended Kalman filter to handle full occlusion. Vis Comput 36:701–715 CrossRef
7.
Zurück zum Zitat Islam MN, Loo CK, Seera M (2017) Incremental Clustering-Based Facial Feature Tracking Using Bayesian ART. Neural Process Lett 45:887–911 CrossRef Islam MN, Loo CK, Seera M (2017) Incremental Clustering-Based Facial Feature Tracking Using Bayesian ART. Neural Process Lett 45:887–911 CrossRef
8.
Zurück zum Zitat Sheng L, Cai J, Cham T et al (2019) Visibility Constrained Generative Model for Depth-Based 3D Facial Pose Tracking. IEEE Trans Pattern Anal Mach Intell 41(8):2614–2623 CrossRef Sheng L, Cai J, Cham T et al (2019) Visibility Constrained Generative Model for Depth-Based 3D Facial Pose Tracking. IEEE Trans Pattern Anal Mach Intell 41(8):2614–2623 CrossRef
9.
Zurück zum Zitat Marcone G, Martinelli G, Lancetti L (1998) Eye Tracking in Image Sequences by Competitive Neural Networks. Neural Process Lett 7:133–138 CrossRef Marcone G, Martinelli G, Lancetti L (1998) Eye Tracking in Image Sequences by Competitive Neural Networks. Neural Process Lett 7:133–138 CrossRef
10.
Zurück zum Zitat Zhang W, Du Y, Chen Z et al (2021) Robust adaptive learning with siamese network architecture for visual tracking. Vis Comput 37:881–894 CrossRef Zhang W, Du Y, Chen Z et al (2021) Robust adaptive learning with siamese network architecture for visual tracking. Vis Comput 37:881–894 CrossRef
12.
Zurück zum Zitat Ren Z, Li J, Zhang X et al (2018) A Face Tracking Method in Videos Based on Convolutional Neural. Networks Int J Pattern Recognit Artif Intell 32(12):749–762 Ren Z, Li J, Zhang X et al (2018) A Face Tracking Method in Videos Based on Convolutional Neural. Networks Int J Pattern Recognit Artif Intell 32(12):749–762
13.
Zurück zum Zitat Danelljan M, Robinson A, Khan FS et al (2016) : Beyond correlation filters: learning continuous convolution operators for visual tracking. In: European conference on computer vision (ECCV), pp. 472–488.Springer, Cham Danelljan M, Robinson A, Khan FS et al (2016) : Beyond correlation filters: learning continuous convolution operators for visual tracking. In: European conference on computer vision (ECCV), pp. 472–488.Springer, Cham
14.
Zurück zum Zitat Danelljan M, Bhat G, Shahbaz KF et al (2017) : ECO: efficient convolution operators for tracking. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 6638–6646 Danelljan M, Bhat G, Shahbaz KF et al (2017) : ECO: efficient convolution operators for tracking. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 6638–6646
15.
Zurück zum Zitat Luca B, Jack V, Jo˜ao FH, Andrea V, Philip HST (2016) : Fully-convolutional siamese networks for object tracking. In: European conference on computer vision (ECCV), pp. 850–865. Springer, Cham Luca B, Jack V, Jo˜ao FH, Andrea V, Philip HST (2016) : Fully-convolutional siamese networks for object tracking. In: European conference on computer vision (ECCV), pp. 850–865. Springer, Cham
16.
Zurück zum Zitat Makhura OJ, Woods JC (2019) Learn-select-track: an approach to multi-object tracking. Signal Process Image Commun 74:153–161 CrossRef Makhura OJ, Woods JC (2019) Learn-select-track: an approach to multi-object tracking. Signal Process Image Commun 74:153–161 CrossRef
17.
Zurück zum Zitat Lin L, Liu B, Xiao Y (2020) COB method with online learning for object tracking. Neurocomputing 393(14):142–155 CrossRef Lin L, Liu B, Xiao Y (2020) COB method with online learning for object tracking. Neurocomputing 393(14):142–155 CrossRef
18.
Zurück zum Zitat Tu B, Kuang W, Shang Y et al (2019) A multi-view object tracking using triplet model. J visual communication image representation 60(Apra):64–68 CrossRef Tu B, Kuang W, Shang Y et al (2019) A multi-view object tracking using triplet model. J visual communication image representation 60(Apra):64–68 CrossRef
19.
Zurück zum Zitat Li B, Yan J, Wu W, Zhu Z, Hu X (2018) : High performance visual tracking with siamese region proposal network. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp.8971–8980 Li B, Yan J, Wu W, Zhu Z, Hu X (2018) : High performance visual tracking with siamese region proposal network. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp.8971–8980
20.
Zurück zum Zitat Li B, Wu W, Wang Q, Zhang F, Xing J, Yan J (2019) : SiamRPN++: Evolution of siamese visual tracking with very deep networks. In: IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp.1–7 Li B, Wu W, Wang Q, Zhang F, Xing J, Yan J (2019) : SiamRPN++: Evolution of siamese visual tracking with very deep networks. In: IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp.1–7
21.
Zurück zum Zitat Xu Y, Wang Z, Li Z, Yu, Gang (2020) : SiamFC++: towards robust and accurate visual tracking with target estimation guidelines. In: Association for the Advance of Artificial Intelligence (AAAI), pp.256–267 Xu Y, Wang Z, Li Z, Yu, Gang (2020) : SiamFC++: towards robust and accurate visual tracking with target estimation guidelines. In: Association for the Advance of Artificial Intelligence (AAAI), pp.256–267
22.
Zurück zum Zitat Guo D, Wang J, Cui Y, Wang Z, Chen S (2020) : SiamCAR: Siamese fully convolutional classification and regression for visual tracking. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 6268–6276 Guo D, Wang J, Cui Y, Wang Z, Chen S (2020) : SiamCAR: Siamese fully convolutional classification and regression for visual tracking. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 6268–6276
23.
Zurück zum Zitat Held D, Thrun S, Savarese S (2016) : Learning to track at 100 fps with deep regression networks. In: European conference on computer vision (ECCV), pp. 749–765. Springer, Cham Held D, Thrun S, Savarese S (2016) : Learning to track at 100 fps with deep regression networks. In: European conference on computer vision (ECCV), pp. 749–765. Springer, Cham
24.
Zurück zum Zitat Wei S, Ren J (2016) : Real-time tracking of non-rigid objects. In: International Conference on Communication and Information Systems pp.11–15 Wei S, Ren J (2016) : Real-time tracking of non-rigid objects. In: International Conference on Communication and Information Systems pp.11–15
25.
Zurück zum Zitat Zheng WL, Shen SC, Lu BL (2017) Online Depth Image-Based Object Tracking with Sparse Representation and Object Detection. Neural Process Lett 45:745–758 CrossRef Zheng WL, Shen SC, Lu BL (2017) Online Depth Image-Based Object Tracking with Sparse Representation and Object Detection. Neural Process Lett 45:745–758 CrossRef
26.
Zurück zum Zitat Lian Z, Shao S, Huang C (2020) A real-time face tracking system based on multiple information fusion. Multimedia Tools and Applications 79(23):16751–16769 CrossRef Lian Z, Shao S, Huang C (2020) A real-time face tracking system based on multiple information fusion. Multimedia Tools and Applications 79(23):16751–16769 CrossRef
27.
Zurück zum Zitat Osuna E, Freund R, Girosit F (1997) : Training support vector machines: an application to face detection. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 130–136 Osuna E, Freund R, Girosit F (1997) : Training support vector machines: an application to face detection. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 130–136
28.
Zurück zum Zitat Sarwar Murshed MG, Murphy C, Hou DQ, Khan N, Ganesh A, Hussain F (2022) Machine Learning at the Network Edge: A Survey. ACM Comput Surv 54(8):1–37 CrossRef Sarwar Murshed MG, Murphy C, Hou DQ, Khan N, Ganesh A, Hussain F (2022) Machine Learning at the Network Edge: A Survey. ACM Comput Surv 54(8):1–37 CrossRef
29.
Zurück zum Zitat Chen J, Ran X (2019) : Deep Learning With Edge Computing: A Review. in Proceedings of the IEEE, 107 (8), 1655–1674 Chen J, Ran X (2019) : Deep Learning With Edge Computing: A Review. in Proceedings of the IEEE, 107 (8), 1655–1674
30.
Zurück zum Zitat Zhou Z, Chen X, Li E, Zeng L, Luo K, Zhang J (2019) : Edge Intelligence: Paving the Last Mile of Artificial Intelligence With Edge Computing. in Proceedings of the IEEE, 107 (8), 1738–1762 Zhou Z, Chen X, Li E, Zeng L, Luo K, Zhang J (2019) : Edge Intelligence: Paving the Last Mile of Artificial Intelligence With Edge Computing. in Proceedings of the IEEE, 107 (8), 1738–1762
31.
Zurück zum Zitat Zhang Z, Peng H (2019) : Deeper and wider siamese networks for real-time visual tracking. In: IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp.678–685 Zhang Z, Peng H (2019) : Deeper and wider siamese networks for real-time visual tracking. In: IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp.678–685
33.
Zurück zum Zitat He K, Zhang X, Ren S, Sun J (2016) : Deep residual learning for image recognition. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 770–778 He K, Zhang X, Ren S, Sun J (2016) : Deep residual learning for image recognition. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 770–778
34.
Zurück zum Zitat Hwang Y, Jeong MH, Oh SR, Yoon C (2017) Adaptive mean shift based face tracking by coupled support map. Int J Fuzzy Logic Intell Syst 17(2):114–120 CrossRef Hwang Y, Jeong MH, Oh SR, Yoon C (2017) Adaptive mean shift based face tracking by coupled support map. Int J Fuzzy Logic Intell Syst 17(2):114–120 CrossRef
35.
Zurück zum Zitat Mentzelopoulos M, Psarrou A, Angelopoulou A et al (2013) Active Foreground Region Extraction and Tracking for Sports Video Annotation. Neural Process Lett 37:33–46 CrossRef Mentzelopoulos M, Psarrou A, Angelopoulou A et al (2013) Active Foreground Region Extraction and Tracking for Sports Video Annotation. Neural Process Lett 37:33–46 CrossRef
36.
Zurück zum Zitat Huang DY, Chen CH, Chen TY, Hu WC, Guo ZB, Wen CK (2021) High-efficiency face detection and tracking method for numerous pedestrians through face candidate generation. Multimedia Tools and Applications 80(1):1247–1272 CrossRef Huang DY, Chen CH, Chen TY, Hu WC, Guo ZB, Wen CK (2021) High-efficiency face detection and tracking method for numerous pedestrians through face candidate generation. Multimedia Tools and Applications 80(1):1247–1272 CrossRef
37.
Zurück zum Zitat Tao R, Gavves E, Smeulders AWM (2016) : Siamese instance search for tracking. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 1420–1429 Tao R, Gavves E, Smeulders AWM (2016) : Siamese instance search for tracking. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 1420–1429
38.
Zurück zum Zitat Chen Z, Zhong B, Li G, Zhang S, Ji R (2020) : Siamese box adaptive network for visual tracking. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp.6667–6676 Chen Z, Zhong B, Li G, Zhang S, Ji R (2020) : Siamese box adaptive network for visual tracking. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp.6667–6676
39.
Zurück zum Zitat Paul V, Jonathon L, Philip HST, Bastian L (2020) : Siam R-CNN: Visual tracking by re-detection. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp.6577–6587 Paul V, Jonathon L, Philip HST, Bastian L (2020) : Siam R-CNN: Visual tracking by re-detection. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp.6577–6587
40.
Zurück zum Zitat Zhang Z, Peng H, Fu J, Li B, Hu W (2020) : Ocean: Object-aware anchor-free tracking. In: European conference on computer vision (ECCV), pp.771–787 Zhang Z, Peng H, Fu J, Li B, Hu W (2020) : Ocean: Object-aware anchor-free tracking. In: European conference on computer vision (ECCV), pp.771–787
41.
Zurück zum Zitat Cai H, Gan C, Wang T, Zhang Z, Han S (2020) : Once-for-all: Train one network and specialize it for efficient deployment. In: International Conference on Learning Representations (ICLR),.751–762 Cai H, Gan C, Wang T, Zhang Z, Han S (2020) : Once-for-all: Train one network and specialize it for efficient deployment. In: International Conference on Learning Representations (ICLR),.751–762
42.
Zurück zum Zitat Lu J, Xiong C, Parikh D, Socher R (2017) : Knowing when to look: adaptive attention via a visual sentinel for image captioning. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp.3242–3250 Lu J, Xiong C, Parikh D, Socher R (2017) : Knowing when to look: adaptive attention via a visual sentinel for image captioning. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp.3242–3250
43.
Zurück zum Zitat Chen L, Yang Y, Wang J, Xu W, Yuille AL (2016) : Attention to scale: scale-aware semantic image segmentation. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp.3640–3649 Chen L, Yang Y, Wang J, Xu W, Yuille AL (2016) : Attention to scale: scale-aware semantic image segmentation. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp.3640–3649
44.
Zurück zum Zitat Fan H, Mei X, Prokhorov D, Ling H (2018) Multi-level contextual RNNs with attention model for scene labeling. Intell Transp Syst IEEE Trans on 19(11):3475–3485 CrossRef Fan H, Mei X, Prokhorov D, Ling H (2018) Multi-level contextual RNNs with attention model for scene labeling. Intell Transp Syst IEEE Trans on 19(11):3475–3485 CrossRef
45.
Zurück zum Zitat Xu H, Saenko K (2016) : Ask, attend and answer: exploring question-guided spatial attention for visual question answering. In: European conference on computer vision (ECCV), pp.451–466 Xu H, Saenko K (2016) : Ask, attend and answer: exploring question-guided spatial attention for visual question answering. In: European conference on computer vision (ECCV), pp.451–466
46.
Zurück zum Zitat Choi J, Chang HJ, Yun S, Fischer T, Demiris Y, Choi JY (2017) : Attentional correlation filter network for adaptive visual tracking. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp.4828–4837 Choi J, Chang HJ, Yun S, Fischer T, Demiris Y, Choi JY (2017) : Attentional correlation filter network for adaptive visual tracking. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp.4828–4837
47.
Zurück zum Zitat Szegedy C, Liu W, Jia Y, Sermanet P, Reed S, Anguelov D, Erhan D, Vanhoucke V, Rabinovich A (2015) : Going deeper with convolutions. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 1–9 Szegedy C, Liu W, Jia Y, Sermanet P, Reed S, Anguelov D, Erhan D, Vanhoucke V, Rabinovich A (2015) : Going deeper with convolutions. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 1–9
48.
Zurück zum Zitat Xie S, Girshick R, Doll´ ar P, Tu Z, He K (2017) : Aggregated residual transformations for deep neural networks. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 1492–1500 Xie S, Girshick R, Doll´ ar P, Tu Z, He K (2017) : Aggregated residual transformations for deep neural networks. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 1492–1500
49.
Zurück zum Zitat Hu J, Shen L, Sun G (2020) Squeeze-and-excitation networks. IEEE Trans Pattern Anal Mach Intell 42(8):2011–2023 CrossRef Hu J, Shen L, Sun G (2020) Squeeze-and-excitation networks. IEEE Trans Pattern Anal Mach Intell 42(8):2011–2023 CrossRef
50.
Zurück zum Zitat Li X, Wang W, Hu X, Yang J (2019) : Selective kernel networks. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp.1011–1022 Li X, Wang W, Hu X, Yang J (2019) : Selective kernel networks. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp.1011–1022
51.
Zurück zum Zitat Han S, Mao H, Dally WJ (2016) : Deep compression: Compressing deep neural networks with pruning, trained quantization and huff man coding. In: International Conference on Learning Representations (ICLR), pp. 458–467 Han S, Mao H, Dally WJ (2016) : Deep compression: Compressing deep neural networks with pruning, trained quantization and huff man coding. In: International Conference on Learning Representations (ICLR), pp. 458–467
52.
Zurück zum Zitat Louizos C, Ullrich K, Welling M (2017) Bayesian compression for deep learning. In: NeurIPS, pp 3288–3298 Louizos C, Ullrich K, Welling M (2017) Bayesian compression for deep learning. In: NeurIPS, pp 3288–3298
53.
Zurück zum Zitat Rastegari M, Ordonez V, Redmon J, Farhadi A (2016) : Xnor-net: ImageNet classification using binary convolutional neural networks. In: European conference on computer vision (ECCV), pp.525–542 Rastegari M, Ordonez V, Redmon J, Farhadi A (2016) : Xnor-net: ImageNet classification using binary convolutional neural networks. In: European conference on computer vision (ECCV), pp.525–542
54.
Zurück zum Zitat Ding X, Ding G, Han J, Tang S (2018) : Auto-balanced filter pruning for efficient convolutional neural networks. In: Association for the Advance of Artificial Intelligence (AAAI), pp. 6665–6673 Ding X, Ding G, Han J, Tang S (2018) : Auto-balanced filter pruning for efficient convolutional neural networks. In: Association for the Advance of Artificial Intelligence (AAAI), pp. 6665–6673
55.
Zurück zum Zitat Howard AG, Zhu M, Chen B, Kalenichenko D, Wang W, Weyand T, Andreetto M, Adam H (2017) : MobileNets: Efficient convolutional neural networks for mobile vision applications. arXiv preprint arXiv:1704.04861, Howard AG, Zhu M, Chen B, Kalenichenko D, Wang W, Weyand T, Andreetto M, Adam H (2017) : MobileNets: Efficient convolutional neural networks for mobile vision applications. arXiv preprint arXiv:1704.04861,
56.
Zurück zum Zitat Ma N, Zhang X, Zheng HT, Sun J (2018) : Shufflenet v2: Practical guidelines for efficient CNN architecture design. In: European conference on computer vision (ECCV), pp.122–138 Ma N, Zhang X, Zheng HT, Sun J (2018) : Shufflenet v2: Practical guidelines for efficient CNN architecture design. In: European conference on computer vision (ECCV), pp.122–138
57.
Zurück zum Zitat Tan M, Le Q (2019) : Efficientnet: Rethinking model scaling for convolutional neural networks. In: International Conference on Machine Learning (ICML), pp.6105–6114 Tan M, Le Q (2019) : Efficientnet: Rethinking model scaling for convolutional neural networks. In: International Conference on Machine Learning (ICML), pp.6105–6114
58.
Zurück zum Zitat Tan M, Le QV (2019) : Mixconv: Mixed depthwise convolutional kernels. In: British Machine Vision Conference (BMVC), pp. 275–283 Tan M, Le QV (2019) : Mixconv: Mixed depthwise convolutional kernels. In: British Machine Vision Conference (BMVC), pp. 275–283
59.
Zurück zum Zitat Bromley J, Guyon I, Lecun Y, Sackinger E, Shah R (1993) Signature verification using a siamese time delay neural network. Pattern Recognit Artif Intell 7(4):669–688 CrossRef Bromley J, Guyon I, Lecun Y, Sackinger E, Shah R (1993) Signature verification using a siamese time delay neural network. Pattern Recognit Artif Intell 7(4):669–688 CrossRef
60.
Zurück zum Zitat Kingma D, Ba J (2015) : Adam: A method for stochastic optimization. In International Conference on Learning Representations (ICLR), pp. 492–507 Kingma D, Ba J (2015) : Adam: A method for stochastic optimization. In International Conference on Learning Representations (ICLR), pp. 492–507
61.
Zurück zum Zitat Xie S, Girshick R, Doll´ ar P, Tu Z, He K (2017) : Aggregated residual transformations for deep neural networks. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 1492–1500 Xie S, Girshick R, Doll´ ar P, Tu Z, He K (2017) : Aggregated residual transformations for deep neural networks. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 1492–1500
64.
Zurück zum Zitat Bertinetto L, Valmadre J, Golodetz S et al (2016) : Staple: complementary learners for real-time tracking. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 1401–1409 Bertinetto L, Valmadre J, Golodetz S et al (2016) : Staple: complementary learners for real-time tracking. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 1401–1409
65.
Zurück zum Zitat Valmadre J, Bertinetto L, Henriques J et al (2017) : End-to-end representation learning for correlation filter based tracking. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 2805–2813 Valmadre J, Bertinetto L, Henriques J et al (2017) : End-to-end representation learning for correlation filter based tracking. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 2805–2813
66.
Zurück zum Zitat Guo Q, Feng W, Zhou C, Huang R, Wan L, Wang S (2017) : Learning dynamic siamese network for visual object tracking. In: IEEE International Conference on Computer Vision (ICCV), pp.1491 – 1420 Guo Q, Feng W, Zhou C, Huang R, Wan L, Wang S (2017) : Learning dynamic siamese network for visual object tracking. In: IEEE International Conference on Computer Vision (ICCV), pp.1491 – 1420
67.
Zurück zum Zitat Yu Y, Xiong Y, Huang W, Scott MR (2020) : Deformable siamese attention networks for visual object tracking. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 6727–6736 Yu Y, Xiong Y, Huang W, Scott MR (2020) : Deformable siamese attention networks for visual object tracking. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 6727–6736
Metadaten
Titel
A Lightweight Neural Learning Algorithm for Real-Time Facial Feature Tracking System via Split-Attention and Heterogeneous Convolution
verfasst von
Yuandong Ma
Qing Song
Mengjie Hu
Xiaotong Zhu
Publikationsdatum
13.08.2022
Verlag
Springer US
Erschienen in
Neural Processing Letters
Print ISSN: 1370-4621
Elektronische ISSN: 1573-773X
DOI
https://doi.org/10.1007/s11063-022-10951-1