[1] LeCun Y, Boser B, Denker J S et al. Backpropagation applied to handwritten zip code recognition[J]. Neural Computation, 1, 541-551(1989).

[2] He K M, Zhang X Y, Ren S Q et al. Deep residual learning for image recognition[C], 770-778(2016).

[3] Zheng X T, Sun H, Lu X Q et al. Rotation-invariant attention network for hyperspectral image classification[J]. IEEE Transactions on Image Processing, 31, 4251-4265(2022).

[4] Zhou W Y, Wang H, Wan Z B. Ore image classification based on improved CNN[J]. Computers and Electrical Engineering, 99, 107819(2022).

[5] Sharma N, Jain V, Mishra A. An analysis of convolutional neural networks for image classification[J]. Procedia Computer Science, 132, 377-384(2018).

[6] Szegedy C, Liu W, Jia Y Q et al. Going deeper with convolutions[C](2015).

[7] Zhang X L, Wei K L, Kang X N et al. Hybrid nonlinear convolution filters for image recognition[J]. Applied Intelligence, 51, 980-990(2021).

[8] Wang Q. Research on image recognition technology based on convolutional neural network and deep learning[C], 2628-2632(2021).

[9] Du J C, Gui L, He Y L et al. Convolution-based neural attention with applications to sentiment classification[J]. IEEE Access, 7, 27983-27992(2019).

[10] Zhang X, Rong W G, Liu J S et al. Convolution neural network based syntactic and semantic aware paraphrase identification[C], 2158-2163(2017).

[11] Liao W X, Zeng B, Xu Y Y. Natural language processing model based on one-dimensional dilated convolution and attention mechanism[J]. Computer Engineering and Applications, 57, 114-119(2021).

[12] Grigorescu S, Trasnea B, Cocias T et al. A survey of deep learning techniques for autonomous driving[J]. Journal of Field Robotics, 37, 362-386(2020).

[13] Zhang C J, Song M X, Wang J. A convolution-based grid map reconfiguration method for autonomous driving in highly constrained environments[C], 631-636(2022).

[14] Qin Y J, Luo H Y, Zhao F et al. NDGCN: network in network, dilate convolution and graph convolutional networks based transportation mode recognition[J]. IEEE Transactions on Vehicular Technology, 70, 2138-2152(2021).

[15] Liu S Z, Qin Y J, Wang C X et al. Transportation mode recognition algorithm based on multi-scale feature extraction[J]. Journal of Computer Applications, 41, 1573-1580(2021).

[16] Li Z W, Liu F, Yang W J et al. A survey of convolutional neural networks: analysis, applications, and prospects[J]. IEEE Transactions on Neural Networks and Learning Systems, 33, 6999-7019(2022).

[17] Chen C, Qi F. Review on development of convolutional neural network and its application in computer vision[J]. Computer Science, 46, 63-73(2019).

[18] Jia Y Q, Shelhamer E, Donahue J et al. Caffe: convolutional architecture for fast feature embedding[C], 675-678(2014).

[19] Paulu F, Hospodka J. Design of fully analogue artificial neural network with learning based on backpropagation[J]. Radioengineering, 30, 357-363(2021).

[20] Docheva L, Bekiarski A, Dochev I. Analysis of analog neural network model with CMOS multipliers[J]. Radioengineering, 16, 103(2007).

[21] Faiedh H, Gafsi Z, Torki K et al. Digital hardware implementation of a neural network used for classification[C], 551-554(2004).

[22] Lu W F, Wang B X, Zhang Z. Realization of robust neural network for digital logic[J]. Journal of Zhejiang University (Sciences Edition), 30, 642-645, 650(2003).

[23] Gupta V, Khare K, Singh R P. FPGA design and implementation issues of artificial neural network based PID controllers[C], 860-862(2009).

[24] Ivanov S, Stankov S, Nenov T. FPGA based neural networks for characters recognition[C](2018).

[25] Yang K L, Wang J, Wei X L et al. Morris-Lecar model neurons and neural networks: FPGA implementation and analysis[C], 639-642(2011).

[26] Chen Z J, Sludds A, Davis R et al. Deep learning with coherent VCSEL neural networks[J]. Nature Photonics, 17, 723-730(2023).

[27] Wang T Y, Sohoni M M, Wright L G et al. Image sensing with multilayer nonlinear optical neural networks[J]. Nature Photonics, 17, 408-415(2023).

[28] Wang Z, Chang L, Wang F F et al. Integrated photonic metasystem for image classifications at telecommunication wavelength[J]. Nature Communications, 13, 2131(2022).

[29] Huang C R, Fujisawa S, de Lima T F et al. A silicon photonic-electronic neural network for fibre nonlinearity compensation[J]. Nature Electronics, 4, 837-844(2021).

[30] Chen Y T, Nazhamaiti M, Xu H et al. All-analog photoelectronic chip for high-speed vision tasks[J]. Nature, 623, 48-57(2023).

[31] Fu T Z, Sun R, Huang Y Y et al. Review of on-chip integrated optical neural networks(invited)[J]. Chinese Journal of Lasers, 51, 0119002(2024).

[32] Zhou Z P, Xu P F, Dong X W. Computing on silicon photonic platform[J]. Chinese Journal of Lasers, 47, 0600001(2020).

[33] Chen H W, Yu Z M, Zhang T et al. Advances and challenges of optical neural networks[J]. Chinese Journal of Lasers, 47, 0500004(2020).

[34] Choquette J, Gandhi W, Giroux O et al. NVIDIA A100 tensor core GPU: performance and innovation[J]. IEEE Micro, 41, 29-35(2021).

[35] Jouppi N, Young C, Patil N et al. Motivation for and evaluation of the first tensor processing unit[J]. IEEE Micro, 38, 10-19(2018).

[36] Sodani A, Gramunt R, Corbal J et al. Knights landing: second-generation intel xeon phi product[J]. IEEE Micro, 36, 34-46(2016).

[37] Liao H, Tu J J, Xia J et al. DaVinci: a scalable architecture for neural network computing[C], 1-44(2019).

[38] Ouyang J, Noh M, Wang Y et al. Baidu Kunlun An AI processor for diversified workloads[C], 1-18(2020).

[39] Wetzstein G, Ozcan A, Gigan S et al. Inference in artificial intelligence with deep optics and photonics[J]. Nature, 588, 39-47(2020).

[40] Zhang D N, Tan Z W. A review of optical neural networks[J]. Applied Sciences, 12, 5338(2022).

[41] Wu J M, Lin X, Guo Y C et al. Analog optical computing for artificial intelligence[J]. Engineering, 10, 133-145(2022).

[42] Slavík R, Park Y, Kulishov M et al. Ultrafast all-optical differentiators[J]. Optics Express, 14, 10699-10707(2006).

[43] Wang M K, Zhang S J, Liu Z et al. High-frequency characterization of high-speed modulators and photodetectors in a link with low-speed photonic sampling[J]. Journal of Semiconductors, 42, 042303(2021).

[44] Zhou H L, Dong J J, Cheng J W et al. Photonic matrix multiplication lights up photonic accelerator and beyond[J]. Light: Science & Applications, 11, 30(2022).

[45] Feldmann J, Youngblood N, Karpov M et al. Parallel convolutional processing using an integrated photonic tensor core[J]. Nature, 589, 52-58(2021).

[46] Wu B, Li H K, Tong W Y et al. Low-threshold all-optical nonlinear activation function based on a Ge/Si hybrid structure in a microring resonator[J]. Optical Materials Express, 12, 970-980(2022).

[47] Zhang W K, Jiang X Y, Gu W T et al. On-chip photonic spatial-temporal descrambler[J]. Chip, 2, 100043(2023).

[48] Cao Z Y, Zhang W K, Zhou H L et al. Complex-valued matrix-vector multiplication system for a large-scale optical FFT[J]. Optics Letters, 48, 5871-5874(2023).

[49] Zhao M Y, Wu B, Dong J J. On-chip multifunctional self-configurable quadrilateral MZI network[J]. Optical Materials Express, 13, 3138-3147(2023).

[50] Zhang W K, Gu W T, Cheng J W et al. Performing photonic nonlinear computations by linear operations in a high-dimensional space[J]. Nanophotonics, 12, 3189-3197(2023).

[51] Cheng J W, Zhang W K, Gu W T et al. Photonic emulator for inverse design[J]. ACS Photonics, 10, 2173-2181(2023).

[52] Wu T W, Menarini M, Gao Z H et al. Lithography-free reconfigurable integrated photonic processor[J]. Nature Photonics, 17, 710-716(2023).

[53] Ashtiani F, Geers A J, Aflatouni F. An on-chip photonic deep neural network for image classification[J]. Nature, 606, 501-506(2022).

[54] Shen Y C, Harris N C, Skirlo S et al. Deep learning with coherent nanophotonic circuits[J]. Nature Photonics, 11, 441-446(2017).

[55] Zhou T K, Wu W, Zhang J Z et al. Ultrafast dynamic machine vision with spatiotemporal photonic computing[J]. Science Advances, 9, eadg4391(2023).

[56] Zhou T K, Lin X, Wu J M et al. Large-scale neuromorphic optoelectronic computing with a reconfigurable diffractive processing unit[J]. Nature Photonics, 15, 367-373(2021).

[57] Kung. Why systolic architectures?[J]. Computer, 15, 37-46(1982).

[58] Bozinovic N, Yue Y, Ren Y X et al. Terabit-scale orbital angular momentum mode division multiplexing in fibers[J]. Science, 340, 1545-1548(2013).

[59] Luo L W, Ophir N, Chen C P et al. WDM-compatible mode-division multiplexing on a silicon chip[J]. Nature Communications, 5, 3069(2014).

[60] Richardson D J, Fini J M, Nelson L E. Space-division multiplexing in optical fibres[J]. Nature Photonics, 7, 354-362(2013).

[61] Zhang S J, Zhou H J, Wu B et al. Redundancy-free integrated optical convolver for optical neural networks based on arrayed waveguide grating[J]. Nanophotonics, 13, 19-28(2024).

[62] Winzer P J. Making spatial multiplexing a reality[J]. Nature Photonics, 8, 345-348(2014).

[63] Bai Y P, Xu X Y, Tan M X et al. Photonic multiplexing techniques for neuromorphic computing[J]. Nanophotonics, 12, 795-817(2023).

[64] Xu X, Tan M, Corcoran B et al. Photonic perceptron based on a kerr microcomb for high-speed, scalable, optical neural networks[J]. Laser & Photonics Reviews, 14, 2000070(2020).

[65] Xu S F, Wang J, Yi S C et al. High-order tensor flow processing using integrated photonic circuits[J]. Nature Communications, 13, 7970(2022).

[66] Bai B W, Yang Q P, Shu H W et al. Microcomb-based integrated photonic processing unit[J]. Nature Communications, 14, 66(2023).

[67] Xu X Y, Tan M X, Corcoran B et al. 11 TOPS photonic convolutional accelerator for optical neural networks[J]. Nature, 589, 44-51(2021).

[68] Meng X Y, Zhang G J, Shi N N et al. Compact optical convolution processing unit based on multimode interference[J]. Nature Communications, 14, 3000(2023).

[69] Cheng J W, Zhou H L, Dong J J. Photonic matrix computing: from fundamentals to applications[J]. Nanomaterials, 11, 1683(2021).

[70] Ma G Q, Yu J J, Zhu R et al. Optical multi-imaging-casting accelerator for fully parallel universal convolution computing[J]. Photonics Research, 11, 299-312(2023).

[71] Ma G Q, Yu J J, Zhu R W et al. Dammann gratings-based truly parallel optical matrix multiplication accelerator[J]. Optics Letters, 48, 2301-2304(2023).

[72] Fei Y H, Sui X B, Wang Q B et al. Optically realize convolution operation of microlens array[J]. Infrared and Laser Engineering, 51, 20210887(2022).

[73] Zhang Z K, Kong D P, Da Z S et al. Compact lensless convolution processor for an optoelectronic convolutional neural network[J]. Journal of Physics D: Applied Physics, 56, 355103(2023).

[74] Moughames J, Porte X, Thiel M et al. Three-dimensional waveguide interconnects for scalable integration of photonic neural networks[J]. Optica, 7, 640-646(2020).

[75] Cheng J W, Zhao Y H, Zhang W K et al. A small microring array that performs large complex-valued matrix-vector multiplication[J]. Frontiers of Optoelectronics, 15, 15(2022).

[76] Yin R Y, Xiao H F, Jiang Y H et al. Integrated WDM-compatible optical mode division multiplexing neural network accelerator[J]. Optica, 10, 1709-1718(2023).

[77] Wu C M, Yu H S, Lee S et al. Programmable phase-change metasurfaces on waveguides for multimode photonic convolutional neural network[J]. Nature Communications, 12, 96(2021).

[78] Bagherian H, Skirlo S, Shen Y C et al. On-chip optical convolutional neural networks[EB/OL]. https:∥arxiv.org/abs/1808.03303

[79] Xu X F, Zhu L Q, Zhuang W et al. A convolution neural network implemented by three 3×3 photonic integrated reconfigurable linear processors[J]. Photonics, 9, 80(2022).

[80] Xu S F, Wang J, Shu H W et al. Optical coherent dot-product chip for sophisticated deep learning regression[J]. Light: Science & Applications, 10, 221(2021).

[81] Cheng J W, Zhou H L, Dong J J. Photonic matrix computing: from fundamentals to applications[J]. Nanomaterials, 11, 1683(2021).

[82] Xu P F, Zhou Z P. Silicon-based optoelectronics for general-purpose matrix computation: a review[J]. Advanced Photonics, 4, 044001(2022).

[83] Peserico N, Shastri B J, Sorger V J. Integrated photonic tensor processing unit for a matrix multiply: a review[J]. Journal of Lightwave Technology, 41, 3704-3716(2023).

[84] Jiang Y, Zhang W J, Yang F et al. Photonic convolution neural network based on interleaved time-wavelength modulation[J]. Journal of Lightwave Technology, 39, 4592-4600(2021).

[85] Bangari V, Marquez B A, Miller H et al. Digital electronics and analog photonics for convolutional neural networks (DEAP-CNNs)[J]. IEEE Journal of Selected Topics in Quantum Electronics, 26, 7701213(2020).

[86] Xu S F, Wang J, Wang R et al. High-accuracy optical convolution unit architecture for convolutional neural networks by cascaded acousto-optical modulator arrays: erratum[J]. Optics Express, 28, 21854-21864(2020).

[87] Mehrabian A, Al-Kabani Y, Sorger V J et al. PCNNA: a photonic convolutional neural network accelerator[C], 169-173(2018).

[88] Zhang Y H, Robertson J, Xiang S Y et al. All-optical neuromorphic binary convolution with a spiking VCSEL neuron for image gradient magnitudes[J]. Photonics Research, 9, B201-B209(2021).

[89] Qu Y R, Zhu H Z, Shen Y C et al. Inverse design of an integrated-nanophotonics optical neural network[J]. Science Bulletin, 65, 1177-1183(2020).

[90] Marquez B A, Singh J, Morison H et al. Fully-integrated photonic tensor core for image convolutions[J]. Nanotechnology, 34, 395201(2023).

[91] Huang Y Y, Fu T Z, Huang H H et al. Sophisticated deep learning with on-chip optical diffractive tensor processing[J]. Photonics Research, 11, 1125-1138(2023).

[92] Xu Z, Zhou T, Ma M et al. Large-scale photonic chiplet Taichi empowers 160-TOPS/W artificial general intelligence[J]. Science, 384, 202-209(2024).

[93] Xu X F, Zhu L Q, Zhuang W et al. Optimization of optical convolution kernel of optoelectronic hybrid convolution neural network[J]. Optoelectronics Letters, 18, 181-186(2022).

[94] Tait A N, de Lima T F, Zhou E et al. Neuromorphic photonic networks using silicon photonic weight banks[J]. Scientific Reports, 7, 7430(2017).

[95] Wu B, Zhang W K, Zhou H L et al. Chip-to-chip optical multimode communication with universal mode processors[J]. PhotoniX, 4, 37(2023).

[96] Wu B, Liu S J, Cheng J W et al. Real-valued optical matrix computing with simplified MZI mesh[J]. Intelligent Computing, 2, 47(2023).

[97] Reck M, Zeilinger A, Bernstein H J et al. Experimental realization of any discrete unitary operator[J]. Physical Review Letters, 73, 58-61(1994).

[98] Miller D A B. Self-configuring universal linear optical component[J]. Photonics Research, 1, 1-15(2013).

[99] Clements W R, Humphreys P C, Metcalf B J et al. Optimal design for universal multiport interferometers[J]. Optica, 3, 1460-1465(2016).

[100] Bell B A, Walmsley I A. Further compactifying linear optical unitaries[J]. APL Photonics, 6, 070804(2021).

[101] Zhou H L, Zhao Y H, Wang X et al. Self-configuring and reconfigurable silicon photonic signal processor[J]. ACS Photonics, 7, 792-799(2020).

[102] Jiang X Y, He Z M, Wu B et al. Programmable photonic solver for computationally complex problems[J]. ACS Photonics, 10, 4340-4348(2023).

[103] Cheng J W, He Z M, Guo Y H et al. Self-calibrating microring synapse with dual-wavelength synchronization[J]. Photonics Research, 11, 347-356(2023).

[104] Zhang W P, Huang C R, Peng H T et al. Silicon microring synapses enable photonic deep learning beyond 9-bit precision[J]. Optica, 9, 579-584(2022).

[105] Huang C R, Bilodeau S, de Lima T F et al. Demonstration of scalable microring weight bank control for large-scale photonic integrated circuits[J]. APL Photonics, 5, 040803(2020).

[106] Tait A N, Jayatilleka H, De Lima T F et al. Feedback control for microring weight banks[J]. Optics Express, 26, 26422-26443(2018).

[107] Ma G Q, Zhou C H, Zhu R W et al. Future of optical computing: analog or digital?[J]. Chinese Journal of Lasers, 50, 0500001(2023).

[108] Zhang J H, Wu B, Cheng J W et al. Compact, efficient, and scalable nanobeam core for photonic matrix-vector multiplication[J]. Optica, 11, 190-196(2024).

[109] Chang J L, Sitzmann V, Dun X et al. Hybrid optical-electronic convolutional neural networks with optimized diffractive optics for image classification[J]. Scientific Reports, 8, 12324(2018).

[110] Colburn S, Chu Y, Shilzerman E et al. Optical frontend for a convolutional neural network[J]. Applied Optics, 58, 3179-3186(2019).

[111] Miscuglio M, Hu Z B, Li S R et al. Massively parallel amplitude-only Fourier neural network[J]. Optica, 7, 1812-1819(2020).

[112] Peserico N, Meng J W, Yang H B et al. Design and testing of silicon photonic 4F system for convolutional neural networks[J]. Proceedings of SPIE, 12424, 124240L(2023).

[113] George J K, Nejadriahi H, Sorger V J. Towards on-chip optical FFTs for convolutional neural networks[C](2017).

[114] Pad P, Narduzzi S, Kündig C et al. Efficient neural vision systems based on convolutional image acquisition[C], 12282-12291(2020).

[115] Zhu H H, Zou J, Zhang H et al. Space-efficient optical computing with an integrated chip diffractive neural network[J]. Nature Communications, 13, 1044(2022).

[116] Abdollahramezani S, Hemmatyar O, Adibi A. Meta-optics for spatial optical analog computing[J]. Nanophotonics, 9, 4075-4095(2020).

[117] Chen H, Jayasuriya S, Yang J Y et al. ASP vision: optically computing the first layer of convolutional neural networks using angle sensitive pixels[C], 903-912(2016).

[118] Fu W W, Zhao D, Li Z Q et al. Ultracompact meta-imagers for arbitrary all-optical convolution[J]. Light: Science & Applications, 11, 62(2022).

[119] Wang H W, Jin W L, Guo C et al. Design of compact meta-crystal slab for general optical convolution[J]. ACS Photonics, 9, 1358-1365(2022).

[120] Peserico N, Li S R, Yang H B et al. PhotoFourier: silicon photonics joint transfer correlator for convolution neural network[J]. Proceedings of SPIE, 12673, 1267307(2023).

[121] Liao K, Gan T Y, Hu X Y et al. AI-assisted on-chip nanophotonic convolver based on silicon metasurface[J]. Nanophotonics, 9, 3315-3322(2020).

[122] Tang A, Xiong G Y, Shen F. Optical vortex convolution generator and quasi-Talbot effect[J]. Optics Letters, 48, 1866-1869(2023).

[123] Shi W X, Huang Z, Huang H H et al. LOEN: Lensless opto-electronic neural network empowered machine vision[J]. Light: Science & Applications, 11, 121(2022).

[124] Yan T, Wu J M, Zhou T K et al. Fourier-space diffractive deep neural network[J]. Physical Review Letters, 123, 023901(2019).

[125] Zhang J, Tao Z L, Yan Q Q et al. Dual optical frequency comb neuron: co-developing hardware and algorithm[J]. Advanced Intelligent Systems, 5, 33-36(2023).

[126] Zhu Y, Zhang X, Hua X et al. Optoelectronic neuromorphic accelerator at 523.27 GOPS based on coherent optical devices[C](2023).

[127] Fan L L, Zhao Z X, Wang K et al. Multidimensional convolution operation with synthetic frequency dimensions in photonics[J]. Physical Review Applied, 18, 034088(2022).

[128] Fan L L, Wang K, Wang H M et al. Experimental realization of convolution processing in photonic synthetic frequency dimensions[J]. Science Advances, 9, eadi4956(2023).

[129] Lassonde P, Ibrahim H, Leblanc A et al. Information transfer via temporal convolution in nonlinear optics[J]. Scientific Reports, 10, 14969(2020).

[130] Hong L, Guo H X, Qiu X D et al. Experimental optical computing of complex vector convolution with twisted light[J]. Advanced Photonics Nexus, 2, 046008(2023).

[131] Fang X Y, Hu X N, Li B L et al. Orbital angular momentum-mediated machine learning for high-accuracy mode-feature encoding[J]. Light: Science & Applications, 13, 49(2024).

[132] Gu W T, Gao X Y, Dong W C et al. All-optical complex-valued convolution based on four-wave mixing[J]. Optica, 11, 64-72(2024).

[133] Verbytskyi I. A double Fourier series implementation for modulated signal with the arbitrary modulation[C], 518-521(2017).

[134] Sarmavuori J, Sarkka S. Fourier-Hermite Kalman filter[J]. IEEE Transactions on Automatic Control, 57, 1511-1515(2012).

[135] Mishra R, Saxena R, Jain R. Filtering with FRFT convolution[C], 1482, 431-436(2012).

[136] Zhu L, Liu Y, Zhang L et al. Optical fiber interferometer for Fourier Transform spectral analysis[C](2009).

[137] Torres-Company V, Weiner A M. Optical frequency comb technology for ultra-broadband radio-frequency photonics[J]. Laser & Photonics Reviews, 8, 368-393(2014).

[138] Zhang M, Buscaino B, Wang C et al. Broadband electro-optic frequency comb generation in a lithium niobate microring resonator[J]. Nature, 568, 373-377(2019).

[139] Diddams S A, Vahala K, Udem T. Optical frequency combs: Coherently uniting the electromagnetic spectrum[J]. Science, 369, eaay3676(2020).

[140] Chang L, Liu S T, Bowers J E. Integrated optical frequency comb technologies[J]. Nature Photonics, 16, 95-108(2022).

[141] Cheng J W, Xie Y Z, Liu Y et al. Human emotion recognition with a microcomb-enabled integrated optical neural network[J]. Nanophotonics, 12, 3883-3894(2023).

[142] Zhao B H, Cheng J W, Wu B et al. Integrated photonic convolution acceleration core for wearable devices[J]. Opto-Electronic Science, 2, 230017(2023).

[143] He Z M, Cheng J W, Liu X Y et al. Microcomb-driven optical convolution for car plate recognition[J]. Photonics, 10, 972(2023).

[144] Han D X, Chen J, Sun J. A parallel spatiotemporal deep learning network for highway traffic flow forecasting[J]. International Journal of Distributed Sensor Networks, 15, 155014771983279(2019).

[145] Zhang Q X, Zhou D, Zeng X. HeartID: a multiresolution convolutional neural network for ECG-based biometric human identification in smart health applications[J]. IEEE Access, 5, 11805-11816(2017).

[146] Abdeljaber O, Sassi S, Avci O et al. Fault detection and severity identification of ball bearings by online condition monitoring[J]. IEEE Transactions on Industrial Electronics, 66, 8136-8147(2019).

[147] Harbola S, Coors V. One dimensional convolutional neural network architectures for wind prediction[J]. Energy Conversion and Management, 195, 70-75(2019).

[148] Xu S, Liu B, Yi S et al. Analog spatiotemporal feature extraction for cognitive radio-frequency sensing with integrated photonics[J]. Light: Science & Applications, 13, 50(2024).

[149] Maturana D, Scherer S. VoxNet: a 3D convolutional neural network for real-time object recognition[C], 922-928(2015).

[150] Stergiou A, Poppe R. Spatio-temporal FAST 3D convolutions for human action recognition[C], 183-190(2019).