Empowering Things With Intelligence: A Survey of the Progress, Challenges, and Opportunities in Artificial Intelligence of Things

In the paper

“There has recently been rapid progress in deep learning, with these positive effects also impacting IoT data processing, e.g., streaming data analysis [55], mobile multimedia processing [56], manufacturing inspection [57], and health monitoring.”

What the sources say

• ?Not matched

  Couldn’t be matched to a paper in Crossref, so it can’t be checked.

  cites [55] [55] M. Mohammadi, A. Al-Fuqaha, S. Sorour, and M. Guizani, 'Deep learning for iot big data and streaming analytics: A survey,' IEEE Communications Surveys & Tutorials , vol. 20, no. 4, pp. 2923-2960, 2018. -
• Not checked yetcites [56] [56] K. Ota, M. S. Dao, V. Mezaris, and F. G. D. Natale, 'Deep learning for mobile multimedia: A survey,' ACM Transactions on Multimedia Computing, Communications, and Applications , vol. 13, no. 3s, pp. 1-22, 2017. - source
• Supported

  The citation [57] is attached to manufacturing inspection, not the other listed applications. The paper’s abstract (p. 2) describes a deep-learning-based inspection system for industrial IoT sensor data, and the Introduction (p. 2) identifies manufacture inspection as its application. (LLM, conf=0.93)

  cites [57] [57] L. Li, K. Ota, and M. Dong, 'Deep learning for smart industry: Efficient manufacture inspection system with fog computing,' IEEE Transactions on Industrial Informatics , vol. 14, no. 10, pp. 4665-4673, 2018. - source

In the paper

“These application scenarios could benefit from recent advances in causal inference and discovery [39], graphbased reasoning [40], reinforcement learning [41], and speech recognition and synthesis [24], [42].”

What the sources say

• ?Not matched

  Couldn’t be matched to a paper in Crossref, so it can’t be checked.

  cites [39] [39] Y. Zhang, S. Qian, Q. Fang, and C. Xu, 'Multi-modal knowledgeaware hierarchical attention network for explainable medical question answering,' in Proceedings of the 27th ACM International Conference on Multimedia , 2019, pp. 1089-1097. -
• Supported

  The citation [40] is attached to “graphbased reasoning,” not to the other listed advances. The Introduction (p. 2) describes the paper’s method as reasoning over paths in a knowledge graph to infer user preferences, so it is an example of the cited advance. The suggestion that the application scenarios could benefit is the citing authors’ framing. (LLM, conf=0.88)

  cites [40] [40] X. Wang, D. Wang, C. Xu, X. He, Y. Cao, and T.-S. Chua, 'Explainable reasoning over knowledge graphs for recommendation,' in Proceedings of the AAAI Conference on Artificial Intelligence , vol. 33, 2019, pp. 5329-5336. - source
• Partly supported

  Citation [41] is attached to reinforcement learning, not the other techniques in the sentence. The Related Work and Performance Analysis sections describe a hierarchical reinforcement-learning method that improves MOOC course recommendations, supporting the reference to an advance in reinforcement learning. The paper does not address smart parking or establish that such applications could benefit from the method. (LLM, conf=0.84)

  cites [41] [41] J. Zhang, B. Hao, B. Chen, C. Li, H. Chen, and J. Sun, 'Hierarchical reinforcement learning for course recommendation in moocs,' in Proceedings of the AAAI Conference on Artificial Intelligence , vol. 33, 2019, pp. 435-442. - sourceExperimental — accuracy not yet measured

In the paper

“The fully CNN with an encoder-decoder structure has become the de facto paradigm for semantic segmentation [75], [76], since it can learn discriminative and multi-resolution features through cascaded convolution blocks while preserving spatial correspondence.”

What the sources say

• Partly supported

  Split into 2 atoms — 1 confirmed, 1 partially supported, 0 disputed, 0 misattributed, 0 unverifiable. Expand the claim to see per-atom verdicts.

  cites [75] [75] O. Ronneberger, P. Fischer, and T. Brox, 'U-net: Convolutional networks for biomedical image segmentation,' in Proceedings of the International Conference on Medical Image Computing and ComputerAssisted Intervention , 2015, pp. 234-241. - sourceExperimental — accuracy not yet measured
• Partly supported

  Split into 2 atoms — 1 confirmed, 1 partially supported, 0 disputed, 0 misattributed, 0 unverifiable. Expand the claim to see per-atom verdicts.

  cites [76] [76] J. Long, E. Shelhamer, and T. Darrell, 'Fully convolutional networks for semantic segmentation,' in Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition , 2015, pp. 3431-3440. - sourceExperimental — accuracy not yet measured

In the paper

“For example, the recently proposed SimCLR method defines a context-based contrasting task for self-supervised learning [34], obtaining comparable performance as fully supervised models.”

What the sources say

• Partly supported

  Section 2.1 (p. 2) describes SimCLR as a self-supervised contrastive task using augmented views of the same image. The Abstract (p. 1) says its ImageNet result matches a supervised ResNet-50. The description “context-based” is imprecise: Appendix C (p. 20) distinguishes SimCLR from methods that explicitly define a context-prediction task. (LLM, conf=0.83)

  cites [34] [34] T. Chen, S. Kornblith, M. Norouzi, and G. Hinton, 'A simple framework for contrastive learning of visual representations,' arXiv preprint arXiv:2002.05709 , 2020. - sourceExperimental — accuracy not yet measured

In the paper

“In real-world AIoT systems, there are always many related tasks involved, e.g., object detection and tracking, and semantic segmentation in video surveillance. Therefore, finding the transfer learning dependencies across these tasks and leveraging such prior knowledge to learn better models, are of practical value for AIoT [199], [200], [201], [202].”

What the sources say

• Not checked yetcites [199] [199] X. Liang, Y. Liu, T. Chen, M. Liu, and Q. Yang, 'Federated transfer reinforcement learning for autonomous driving,' arXiv preprint arXiv:1910.06001 , 2019. - source
• Not checked yetcites [200] [200] M. D'Incecco, S. Squartini, and M. Zhong, 'Transfer learning for nonintrusive load monitoring,' IEEE Transactions on Smart Grid , vol. 11, no. 2, pp. 1419-1429, 2019. - source
• Partly supported

  Split into 2 atoms — 0 confirmed, 2 partially supported, 0 disputed, 0 misattributed, 0 unverifiable. Expand the claim to see per-atom verdicts.

  cites [201] [201] S. Bargoti and J. Underwood, 'Deep fruit detection in orchards,' in Proceedings of the IEEE International Conference on Robotics and Automation , 2017, pp. 3626-3633. - sourceExperimental — accuracy not yet measured

In the paper

“Besides, the architecture of the network matters. Even with fewer model parameters and computational complexity, the recently proposed networks such as ResNet and DenseNet outperform previous ones such as VGGNet.”

In the paper

“As can be seen, with the increase of network depth and the number of parameters, the representation capacity also increases, leading to lower top1 classification error on the ImageNet dataset.”

In the paper

“Transmitting this huge amount of data requires massive bandwidth, and cloud processing and sending the results back to end devices leads to high latency.”

In the paper

“The IoT represents a key infrastructure for supporting various applications [4], e.g., smart homes [5], [6], smart transportation [7], [8], smart grids [9], and smart healthcare [10], [11].”

What the sources say

• Not checked yetcites [4] [4] L. Da Xu, W. He, and S. Li, 'Internet of things in industries: A survey,' IEEE Transactions on Industrial Informatics , vol. 10, no. 4, pp. 22332243, 2014. -
• Not checked yetcites [5] [5] X. Li, R. Lu, X. Liang, X. Shen, J. Chen, and X. Lin, 'Smart community: An internet of things application,' IEEE Communications Magazine , vol. 49, no. 11, pp. 68-75, 2011. -
• Not checked yetcites [6] [6] B. L. R. Stojkoska and K. V. Trivodaliev, 'A review of internet of things for smart home: Challenges and solutions,' Journal of Cleaner Production , vol. 140, pp. 1454-1464, 2017. -

In the paper

“Based on reports from Cisco [14] and IDC [15], 50 billion devices will be IoT connected by 2025, generating 79.4 zettabytes of data.”

What the sources say

• ?Not matched

  Couldn’t be matched to a paper in Crossref, so it can’t be checked.

  cites [14] [14] J. Macaulay, L. Buckalew, and G. Chung, 'Internet of things in logistics: A collaborative report by dhl and cisco on implications and use cases for the logistics industry,' DHL Trend Research and Cisco Consulting Services , 2015. -
• ?Not matched

  Couldn’t be matched to a paper in Crossref, so it can’t be checked.

  cites [15] [15] M. Shirer and C. MacGillivray, 'The growth in connected iot devices is expected to generate 79.4 zb of data in 2025, according to a new idc forecast,' 2019. -

In the paper

“To address this issue, 'fog computing', coined by Cisco [16], aims to bring storage, computation, and networking capacity to the edge of the network (e.g., to distributed fog nodes such as routers) in proximity to the devices.”

What the sources say

• ?Not matched

  Couldn’t be matched to a paper in Crossref, so it can’t be checked.

  cites [16] [16] F. Bonomi, 'Connected vehicles, the internet of things, and fog computing,' in The Eighth ACM International Workshop on Vehicular Inter-Networking , 2011, pp. 13-15. -

In the paper

“A typical IoT architecture has three layers [13]: a perception layer, a network layer, and an application layer.”

What the sources say

• ?Not matched

  Couldn’t be matched to a paper in Crossref, so it can’t be checked.

  cites [13] [13] J. Lin, W. Yu, N. Zhang, X. Yang, H. Zhang, and W. Zhao, 'A survey on internet of things: Architecture, enabling technologies, security and privacy, and applications,' IEEE Internet of Things Journal , vol. 4, no. 5, pp. 1125-1142, 2017. -

In the paper

“In conventional IoT solutions, data collected from sensors are transmitted to the cloud computing platform through the networks for further processing and analysis before delivering the results/commands to end devices/actuators.”

In the paper

“For example, edge cases exist in the real world that may not be seen in the training set nor defined in the label set, resulting in degeneration of a pre-trained model.”

In the paper

“This heralds the era of the artificial intelligence of things (AIoT), where AI encounters IoT.”

In the paper

“Fog computing offers the advantages of low latency and high computational capacity for IoT applications [17], [18].”

What the sources say

• Not checked yetcites [17] [17] M. Chiang and T. Zhang, 'Fog and iot: An overview of research opportunities,' IEEE Internet of Things Journal , vol. 3, no. 6, pp. 854864, 2016. - source
• Not checked yetcites [18] [18] J. Ni, K. Zhang, X. Lin, and X. S. Shen, 'Securing fog computing for internet of things applications: Challenges and solutions,' IEEE Communications Surveys & Tutorials , vol. 20, no. 1, pp. 601-628, 2017. - source

In the paper

“Furthermore, IoT applications based on specific things, e.g., the Internet of Vehicles (IoV) [7] and Internet of Video Things (IoVT) [23] have also been rapidly developed.”

What the sources say

• Not checked yetcites [7] [7] J. Contreras-Castillo, S. Zeadally, and J. A. Guerrero-Iba˜ nez, 'Internet of vehicles: Architecture, protocols, and security,' IEEE Internet of Things Journal , vol. 5, no. 5, pp. 3701-3709, 2017. - source
• Not checked yetcites [23] [23] C. W. Chen, 'Internet of video things: Next generation iot with visual sensors,' IEEE Internet of Things Journal , 2020. - source

In the paper

“'Edge computing' has also recently been proposed by further deploying computing capacity on edge devices in proximity to sensors and actuators [19], [20].”

What the sources say

• ?Not matched

  Couldn’t be matched to a paper in Crossref, so it can’t be checked.

  cites [19] [19] N. Abbas, Y. Zhang, A. Taherkordi, and T. Skeie, 'Mobile edge computing: A survey,' IEEE Internet of Things Journal , vol. 5, no. 1, pp. 450-465, 2017. -
• ?Not matched

  Couldn’t be matched to a paper in Crossref, so it can’t be checked.

  cites [20] [20] J. Pan and J. McElhannon, 'Future edge cloud and edge computing TABLE IX LIST OF ABBREVIATIONS. | Abbreviation | Description | |----------------|------------------------------------------| | 5G | 5th Generation Mobile Networks | | AI | Artificial Intelligence | | AIoT | Artificial Intelligence of Things | | AR/VR | Augmented Reality / Virtual Reality | | ASIC | Application-Specific Integrated Circuit | | ASR | Automatic Speech Recognition | | CNN | Convolutional Neural Networks | | CTC | Connectionist Temporal Classification | | DA | Domain Adaptation | | DNN | Deep Neural Network | | DRL

In the paper

“Massive sensor data must be processed to extract useful information before being used for further analysis and decision-making.”

In the paper

“Deep learning has facilitated progress in these areas, suggesting that deep learning can be similarly leveraged to improve IoT system learning.”

In the paper

“Moreover, the context of IoT sensors can provide auxiliary information to help understand sensor data. Therefore, various context-aware computing methods have been proposed for IoT [54].”

What the sources say

• Not checked yetcites [54] [54] C. Perera, A. Zaslavsky, P. Christen, and D. Georgakopoulos, 'Context aware computing for the internet of things: A survey,' IEEE Communications Surveys & Tutorials , vol. 16, no. 1, pp. 414-454, 2013. - source

In the paper

“Another example is in industry, where the operating modes of machines may drift or change due to fatigue or wear and tear. Consequently, models trained for the initial mode cannot adapt to this variation, leading to a performance loss.”

In the paper

“First, multimedia sensor data are high-dimensional and unstructured (semantics are unavailable without additional processing), so it is difficult to design handcrafted features for them without domain knowledge.”

In the paper

“Perceiving and understanding dynamic and complex environments from sensor data is fundamental to IoT applications providing useful services to users.”

In the paper

“According to Cisco's white paper [43], 99.4% of physical objects are still unconnected.”

What the sources say

• ?Not matched

  Couldn’t be matched to a paper in Crossref, so it can’t be checked.

  cites [43] [43] J. Bradley, J. Barbier, and D. Handler, 'Embracing the internet of everything to capture your share of $14.4 trillion,' White Paper, Cisco , vol. 318, 2013. -

In the paper

“Furthermore, to interact with the environment and humans, an IoT system should be able to reason and behave.”

In the paper

“These issues are related to some well-known machine learning research topics including fewshot learning [31], zero-shot learning [32], meta-learning [33], unsupervised learning [34], semi-supervised learning [35], transfer learning [36], and domain adaptation [37], [38].”

What the sources say

• ?Not matched

  Couldn’t be matched to a paper in Crossref, so it can’t be checked.

  cites [31] [31] Y. Wang, Q. Yao, J. T. Kwok, and L. M. Ni, 'Generalizing from a few examples: A survey on few-shot learning,' ACM Computing Surveys , vol. 53, no. 3, pp. 1-34, 2020. -
• Not checked yetcites [32] [32] W. Wang, V. W. Zheng, H. Yu, and C. Miao, 'A survey of zero-shot learning: Settings, methods, and applications,' ACM Transactions on Intelligent Systems and Technology , vol. 10, no. 2, pp. 1-37, 2019. - source
• Not checked yetcites [33] [33] C. Finn, P. Abbeel, and S. Levine, 'Model-agnostic meta-learning for fast adaptation of deep networks,' in Proceedings of the 34th International Conference on Machine Learning , 2017. - source

In the paper

“These data may contain some biometric information such as faces, voice, or fingerprints.”

In the paper

“Edge computing can process and analyze data on premises and make decisions instantly, thereby benefitting latency-sensitive IoT applications.”

In the paper

“Deep neural networks (DNNs) have been widely used in many areas and have achieved excellent performance in many applications including speech recognition [24], face recognition [25], image classification [26], object detection [27], semantic segmentation [28], natural language processing [29]”

What the sources say

• Not checked yetcites [24] [24] H. Sak, A. Senior, and F. Beaufays, 'Long short-term memory recurrent neural network architectures for large scale acoustic modeling,' in Proceedings of the Fifteenth Annual Conference of the International Speech Communication Association , 2014. - source
• Not checked yetcites [25] [25] Y. Taigman, M. Yang, M. Ranzato, and L. Wolf, 'Deepface: Closing the gap to human-level performance in face verification,' in Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition , 2014, pp. 1701-1708. - source
• ?Not matched

  Couldn’t be matched to a paper in Crossref, so it can’t be checked.

  cites [26] [26] A. Krizhevsky, I. Sutskever, and G. E. Hinton, 'Imagenet classification with deep convolutional neural networks,' in Advances in Neural Information Processing Systems , 2012, pp. 1097-1105. -

In the paper

“Cyberattacks on IoT systems may result in data leakage, so data security and privacy have become a critical concern in IoT applications [18].”

What the sources say

• Not checked yetcites [18] [18] J. Ni, K. Zhang, X. Lin, and X. S. Shen, 'Securing fog computing for internet of things applications: Challenges and solutions,' IEEE Communications Surveys & Tutorials , vol. 20, no. 1, pp. 601-628, 2017. -

In the paper

“Although an IoT's perception system is a critical component of the architecture, simply adapting to and interacting with the dynamic and complex world is insufficient.”

In the paper

“Data mining and machine learning approaches have been used for IoT data processing and analysis [52], [53].”

What the sources say

• Not checked yetcites [52] [52] C.-W. Tsai, C.-F. Lai, M.-C. Chiang, and L. T. Yang, 'Data mining for internet of things: A survey,' IEEE Communications Surveys & Tutorials , vol. 16, no. 1, pp. 77-97, 2013. - source
• ?Not matched

  Couldn’t be matched to a paper in Crossref, so it can’t be checked.

  cites [53] [53] M. S. Mahdavinejad, M. Rezvan, M. Barekatain, P. Adibi, P. Barnaghi, and A. P. Sheth, 'Machine learning for internet of things data analysis: A survey,' Digital Communications and Networks , vol. 4, no. 3, pp. 161-175, 2018. -

In the paper

“Massive user data are collected via ubiquitous connected sensors, which may be transmitted and stored in the cloud through IoT networks.”

In the paper

“Recently, access control [58] and trust management [59] approaches have been reviewed to protect the security and privacy of IoT.”

What the sources say

• Not checked yetcites [58] [58] J. Qiu, Z. Tian, C. Du, Q. Zuo, S. Su, and B. Fang, 'A survey on access control in the age of internet of things,' IEEE Internet of Things Journal , 2020. - source
• Not checked yetcites [59] [59] Z. Yan, P. Zhang, and A. V. Vasilakos, 'A survey on trust management for internet of things,' Journal of Network and Computer Applications , vol. 42, pp. 120-134, 2014. - source

In the paper

“The last few years has witnessed a renaissance in artificial intelligence (AI) assisted by deep learning.”

In the paper

“The Open Neural Network Exchange (ONNX) 5 offers this feature by defining an open format built to represent machine learning models, which has been supported by TensorFlow and Pytorch.”

In the paper

“State-of-the-art methods can be categorized into two groups: two-stage methods and one-stage methods.”

In the paper

“Besides, Field-Programmable Gate Arrays (FPGA) have also been used for DNN acceleration due to their low power consumption and high throughput.”

In the paper

“Besides, fog computing can provide continuity of service without the need for the Internet, which is important for specific AIoT applications with an unstable Internet connection, e.g., in agriculture, mining, and shipping domains.”

In the paper

“Its performance can be improved further by exploiting and enhancing the feature hierarchy of deep convolutional networks [80], employing non-local attention [81], and leveraging the reciprocal relationship between detection and segmentation via hybrid task cascade [82].”

What the sources say

• Not checked yetcites [80] [80] T.-Y. Lin, P. Doll´ ar, R. Girshick, K. He, B. Hariharan, and S. Belongie, 'Feature pyramid networks for object detection,' in Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition , 2017, pp. 2117-2125. - source
• Not checked yetcites [81] [81] X. Wang, R. Girshick, A. Gupta, and K. He, 'Non-local neural networks,' in Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition , 2018, pp. 7794-7803. - source
• Not checked yetcites [82] [82] K. Chen, J. Pang, J. Wang, Y. Xiong, X. Li, S. Sun, W. Feng, Z. Liu, J. Shi, W. Ouyang et al. , 'Hybrid task cascade for instance segmentation,' in Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition , 2019, pp. 4974-4983. - source

In the paper

“Besides, some popular applications in smartphones also benefit from the advances in this area for recognizing flowers and birds, and food items and calories.”

In the paper

“Lightweight networks are appealing to AIoT applications where DNNs are deployed on edge devices.”

In the paper

“Although functioning similarly to cloud computing, fog computing offers a key advantage, i.e., low latency, since it is closer to devices.”

In the paper

“It is noteworthy that the edge things and fog nodes are always distributed while the cloud is centralized in the AIoT network topology.”

In the paper

“Recently, some computationally efficient networks like MobileNet have been proposed by leveraging depth-wise convolutions [65], point-wise convolutions [66], or binary operations [67].”

What the sources say

• Not checked yetcites [65] [65] A. G. Howard, M. Zhu, B. Chen, D. Kalenichenko, W. Wang, T. Weyand, M. Andreetto, and H. Adam, 'Mobilenets: Efficient convolutional neural networks for mobile vision applications,' arXiv preprint arXiv:1704.04861 , 2017. - source
• Not checked yetcites [66] [66] J. Zhang, Y. Cao, Y. Wang, C. Wen, and C. W. Chen, 'Fully pointwise convolutional neural network for modeling statistical regularities in natural images,' in Proceedings of the 26th ACM international conference on Multimedia , 2018, pp. 984-992. - source
• Not checked yetcites [67] [67] M. Rastegari, V. Ordonez, J. Redmon, and A. Farhadi, 'Xnor-net: Imagenet classification using binary convolutional neural networks,' in Proceedings of the European Conference on Computer Vision . Springer, 2016, pp. 525-542. - source

In the paper

“Empowering things with the perceiving ability, i.e., understanding the environment using various sensors, is fundamental for AIoT systems.”

In the paper

“With the off-the-shelf deep learning tools and scalable computing hardware, it is easy to set up the production environment on the cloud, where deep neural networks are trained and deployed to process the massive amounts of data.”

In the paper

“To this end, different open-source deep learning frameworks have been developed, from the beginners like Caffe 1 and MatConvNet 2 to the popular TensorFlow 3 and PyTorch 4 .”

In the paper

“Caffe2 improves it accordingly, which has been later merged into PyTorch.”

In the paper

“Caffe is implemented in C++ with Python and Matlab interfaces and well-known for its speed but does not support distributed computation and mobile deployment.”

In the paper

“The cloud enables AIoT enterprises to use computing resources virtually via the Internet instead of building their physical infrastructure on premises.”

In the paper

“Several machine learning processors have also been developed for fog and edge computing, e.g., Google Edge TPU and NVIDIA Jetson Nano.”

In the paper

“Detection of specific category of objects such as pedestrian, car, traffic-sign, and the license plate has been widely studied, which are useful for improving the perceiving ability of AIoT systems for traffic and public safety surveillance and autonomous driving [70].”

What the sources say

• Not checked yetcites [70] [70] C. Chen, A. Seff, A. Kornhauser, and J. Xiao, 'Deepdriving: Learning affordance for direct perception in autonomous driving,' in Proceedings of the IEEE International Conference on Computer Vision , 2015, pp. 2722-2730. -

In the paper

“A well-known baseline model is Mask R-CNN which adopts an extra branch for object mask prediction in parallel with the existing one for bounding box regression [79].”

What the sources say

• Not checked yetcites [79] [79] K. He, G. Gkioxari, P. Doll´ ar, and R. Girshick, 'Mask r-cnn,' in Proceedings of the IEEE International Conference on Computer Vision , 2017, pp. 2961-2969. - source

In the paper

“They also support for deploying models into mobile devices by enabling model compression/quantization and hardware acceleration.”

In the paper

“Besides, object detection is a crucial technique for video data structuring in many AIoT systems using visual sensors, which aims to extract and organize compact structured semantic information from video data for further retrieval, verification, statistics, and analysis at low transmission, storage, and computation cost.”

In the paper

“The edge computing layer may function like the perception layer in [13] and smart visual sensing block in [23]. It also supports control and execution over sensors and actuators. Thereby, this layer aims to empower AIoT systems with the ability to perceive and behave.”

What the sources say

• Not checked yetcites [13] [13] J. Lin, W. Yu, N. Zhang, X. Yang, H. Zhang, and W. Zhao, 'A survey on internet of things: Architecture, enabling technologies, security and privacy, and applications,' IEEE Internet of Things Journal , vol. 4, no. 5, pp. 1125-1142, 2017. - source
• Not checked yetcites [23] [23] C. W. Chen, 'Internet of video things: Next generation iot with visual sensors,' IEEE Internet of Things Journal , 2020. - source

In the paper

“In practice, it is common to deploy multiple different models into cloud platforms, fog nodes, and edge devices in an AIoT system to build an intelligent hybrid computing architecture.”

In the paper

“While GPU is initially developed for accelerating image rendering on display devices, the generalpurpose GPU turns the massive computational power of its shader pipeline into general-purpose computing power (e.g., for massive vector operations), which has sparked the deep learning revolution along with DNN and big data.”

In the paper

“A great advantage of edge computing over fog and cloud computing is the reduction of latency and network bandwidth since it can process data into compact structured information on-site before transmission, which is especially useful for AIoT applications using multimedia sensors.”

In the paper

“The other advantage of fog computing is the protection of data security and privacy since data can be held within the LAN.”

In the paper

“Boundary refinement aims to obtain sharp boundaries between different categories in the segmentation map, which can be achieved by using conditional random field as the postprocessing technique on the predicted probability maps [28].”

What the sources say

• Not checked yetcites [28] [28] L.-C. Chen, G. Papandreou, I. Kokkinos, K. Murphy, and A. L. Yuille, 'Deeplab: Semantic image segmentation with deep convolutional nets, atrous convolution, and fully connected crfs,' IEEE Transactions on Pattern Analysis and Machine Intelligence , vol. 40, no. 4, pp. 834848, 2017. - source

In the paper

“It can provide flexible, scalable, and reliable resources including computation, storage, and network for enabling various AIoT applications.”

In the paper

“However, due to its limited computation capacity, only lightweight DNNs can run on edge devices.”

In the paper

“The features like dynamic computation graphs and automatic computation of gradients in TensorFlow and PyTorch have made them easy to use and popular.”

In the paper

“By intelligently offloading part of the computation workload from edge devices to the fog nodes and cloud, it is expected to achieve low latency while leveraging deep learning capacities for processing massive amounts of data.”

In the paper

“Therefore, research topics including neural network architecture design or search for mobile setting and network pruning/compression/quantization have attracted increasing attention recently.”

In the paper

“Classical machine learning methods based on hand-crafted features have been surpassed by DNNs [26] on large-scale benchmark datasets like ImageNet [30], sparking a wave of research on the architecture of DNNs.”

What the sources say

• ?Not matched

  Couldn’t be matched to a paper in Crossref, so it can’t be checked.

  cites [26] [26] A. Krizhevsky, I. Sutskever, and G. E. Hinton, 'Imagenet classification with deep convolutional neural networks,' in Advances in Neural Information Processing Systems , 2012, pp. 1097-1105. -
• Not checked yetcites [30] [30] J. Deng, W. Dong, R. Socher, L.-J. Li, K. Li, and L. Fei-Fei, 'Imagenet: A large-scale hierarchical image database,' in Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition , 2009, pp. 248-255. - source

In the paper

“Recently, an application-specific integrated circuit (ASIC) named TPU is designed by Google specifically for neural network machine learning.”

In the paper

“The fog and cloud computing layers mainly aim to empower AIoT systems with the ability of learning and reasoning since they can access massive amounts of data and have vast computation resources.”

In the paper

“Another feature is that it can leverage all the data from the registered devices in an AIoT application, which is useful for training deep models with better representation and generalization ability.”

In the paper

“Image recognition can be very useful in many AIoT applications, such as smart education tools or toys, which help and teach children to explore the world with cameras.”

In the paper

“There are other deep learning frameworks like MXNet 6 , Theano 7 , PaddlePaddle 8 , and neural network inference computing framework for mobile devices like ncnn 9 .”

In the paper

“A simple but strong baseline model is proposed in [84], which adds a semantic segmentation branch into the Mask R-CNN framework and uses a shared feature pyramid network backbone [80].”

What the sources say

• ?Not matched

  Couldn’t be matched to a paper in Crossref, so it can’t be checked.

  cites [84] [84] A. Kirillov, R. Girshick, K. He, and P. Doll´ ar, 'Panoptic feature pyramid networks,' in Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition , 2019, pp. 6399-6408. -
• Not checked yetcites [80] [80] T.-Y. Lin, P. Doll´ ar, R. Girshick, K. He, B. Hariharan, and S. Belongie, 'Feature pyramid networks for object detection,' in Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition , 2017, pp. 2117-2125. - source

In the paper

“The methods for object detection from images have been revolutionized by DNNs.”

In the paper

“Lots of operations in the neural network such as convolution can be computed in parallel on GPU, significantly reducing the training and inference time.”

In the paper

“Besides, network compression such as pruning and quantization can be used to obtain lightweight models from heavy models, which will be reviewed in Section III-A17.”

In the paper

“An image can be decomposed into the reflectance map and illumination map based on the Retinex theory [145].”

What the sources say

• Not checked yetcites [145] [145] E. H. Land, 'The retinex theory of color vision,' Scientific american , vol. 237, no. 6, pp. 108-129, 1977. - source

In the paper

“Recently, a differentiable architecture named neural graph optimizer is proposed for global pose graph optimization [136]. Together with a local pose estimation model, it achieves a complete end-to-end neural network solution for SLAM.”

What the sources say

• Not checked yetcites [136] [136] E. Parisotto, D. Singh Chaplot, J. Zhang, and R. Salakhutdinov, 'Global pose estimation with an attention-based recurrent network,' in Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition Workshops , 2018, pp. 237-246. - source

In the paper

“Nevertheless, due to the prevalence of cameras and great progress in deep learning and computer vision, visual hand gesture recognition has the vast potential, which can be categorized into two groups, i.e., static ones and dynamic ones.”

In the paper

“Estimation of human pose and recognition of action can be very useful in many real-world AIoT scenarios, such as rehabilitation exercises monitoring and assessment [120], dangerous behavior monitoring [121], and human-machine interaction (HMI).”

What the sources say

• ?Not matched

  Couldn’t be matched to a paper in Crossref, so it can’t be checked.

  cites [120] [120] D. Gonz´ alez-Ortega, F. D´ ıaz-Pernas, M. Mart´ ınez-Zarzuela, and M. Ant´ on-Rodr´ ıguez, 'A kinect-based system for cognitive rehabilitation exercises monitoring,' Computer Methods and Programs in Biomedicine , vol. 113, no. 2, pp. 620-631, 2014. -
• Not checked yetcites [121] [121] A. Kashevnik, I. Lashkov, and A. Gurtov, 'Methodology and mobile application for driver behavior analysis and accident prevention,' IEEE Transactions on Intelligent Transportation Systems , vol. 21, no. 6, pp. 2427-2436, 2019. - source

In the paper

“Face detection, as a specific subarea of object detection, benefits from the recent success of deep learning in generic object detection.”

In the paper

“Different geometric cues have been exploited for formulating the optimization constraints in optimization-based methods or loss functions in learning-based methods [157], such as lines and vanishing points.”

What the sources say

• Not checked yetcites [157] [157] Z. Xue, N. Xue, G.-S. Xia, and W. Shen, 'Learning to calibrate straight lines for fisheye image rectification,' in Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition , 2019, pp. 1643-1651. -

In the paper

“Although CNN has powerful representation capacity, special effort has to be made to address the challenges including occlusions and dynamic objects, as well as the scale issue (per-frame ambiguity and temporally inconsistent).”

In the paper

“Hand gesture recognition can be very useful for interactions with things in AIoT systems, e.g., non-contact control of television and car infotainment system, and communication with the speech and hearing impaired [125].”

What the sources say

• Not checked yetcites [125] [125] T. Starner, J. Weaver, and A. Pentland, 'Real-time american sign language recognition using desk and wearable computer based video,' IEEE Transactions on Pattern Analysis and Machine Intelligence , vol. 20, no. 12, pp. 1371-1375, 1998. - source

In the paper

“Recently, generative adversarial networks (GAN) have been used to generate style-transferred images for bridging the domain gap between different datasets [111].”

What the sources say

• Not checked yetcites [111] [111] L. Wei, S. Zhang, W. Gao, and Q. Tian, 'Person transfer gan to bridge domain gap for person re-identification,' in Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition , 2018, pp. 79-88. - source

In the paper

“Besides, a DCNN-based palmprint verification system named DeepMPV is proposed for mobile payment in [104].”

What the sources say

• Not checked yetcites [104] [104] Y. Zhang, L. Zhang, X. Liu, S. Zhao, Y. Shen, and Y. Yang, 'Pay by showing your palm: A study of palmprint verification on mobile platforms,' in Proceedings of the IEEE International Conference on Multimedia and Expo . IEEE, 2019, pp. 862-867. - source

In the paper

“Therefore, most CNN-based methods directly regress the crowd density map, in which the ground truth is constructed by placing Gaussian density maps at the head regions.”

In the paper

“Although extra efforts are needed to build practical person re-identification systems, one can leverage the idea of humanin-the-loop artificial intelligence to achieve high performance with low labor effort.”

In the paper

“Compared with fingerprint, palmprint has abundant features and can be captured using common built-in cameras of mobile phones rather than sensitive sensors.”

In the paper

“In practice, the choice of a specific biometric recognition solution depends on sensors, usage scenarios, latency, and power consumption.”

In the paper

“The widely used calibration method is proposed by Z. Zhang in [156] based on planar patterns at a few different orientations, where radial lens distortion is modelled.”

What the sources say

• Not checked yetcites [156] [156] Z. Zhang, 'A flexible new technique for camera calibration,' IEEE Transactions on Pattern Analysis and Machine Intelligence , vol. 22, no. 11, pp. 1330-1334, 2000. - source

In the paper

“When images are captured in the low-light and haze environment, it comes to the more challenging case, i.e., nighttime image dehazing.”

In the paper

“Depth estimation, pose estimation, VO/VIO, and SLAM constitute the important 3D perceiving ability of AIoT, which could be very useful in smart transportation [137], smart industry [138], smart agriculture [139], [140], [141], smart cities and homes [142], [143], [144].”

What the sources say

• Not checked yetcites [137] [137] X. Shao, L. Zhang, T. Zhang, Y. Shen, H. Li, and Y. Zhou, 'A tightlycoupled semantic slam system with visual, inertial and surround-view sensors for autonomous indoor parking,' in Proceedings of the 28th ACM International Conference on Multimedia , 2020. - source
• Not checked yetcites [138] [138] R. Krug, T. Stoyanov, V. Tincani, H. Andreasson, R. Mosberger, G. Fantoni, and A. J. Lilienthal, 'The next step in robot commissioning: Autonomous picking and palletizing,' IEEE Robotics and Automation Letters , vol. 1, no. 1, pp. 546-553, 2016. - source
• Not checked yetcites [139] [139] F. A. Cheein, G. Steiner, G. P. Paina, and R. Carelli, 'Optimized eif-slam algorithm for precision agriculture mapping based on stems detection,' Computers and Electronics in Agriculture , vol. 78, no. 2, pp. 195-207, 2011. - source

In the paper

“Images captured in a haze environment are in low contrast due to the haze attenuation and scattering effects.”

In the paper

“Recovering the clear image from a single hazy input is also an illposed problem, which can be addressed by both prior-based and learning-based methods [149], [150], [151].”

What the sources say

• Not checked yetcites [149] [149] K. He, J. Sun, and X. Tang, 'Single image haze removal using dark channel prior,' IEEE Transactions on Pattern Analysis and Machine Intelligence , vol. 33, no. 12, pp. 2341-2353, 2010. - source
• Not checked yetcites [150] [150] B. Cai, X. Xu, K. Jia, C. Qing, and D. Tao, 'Dehazenet: An end-to-end system for single image haze removal,' IEEE Transactions on Image Processing , vol. 25, no. 11, pp. 5187-5198, 2016. - source
• Not checked yetcites [151] [151] J. Zhang and D. Tao, 'Famed-net: A fast and accurate multi-scale endto-end dehazing network,' IEEE Transactions on Image Processing , vol. 29, pp. 72-84, 2019. - source

In the paper

“Deep learning has advanced this area by learning more representative feature [87], devising better representation of text proposals [88], and using large-scale synthetic dataset [89].”

What the sources say

• Not checked yetcites [87] [87] M. Jaderberg, A. Vedaldi, and A. Zisserman, 'Deep features for text spotting,' in Proceedings of the European Conference on Computer Vision , 2014, pp. 512-528. - source
• Not checked yetcites [88] [88] X. Liu, D. Liang, S. Yan, D. Chen, Y. Qiao, and J. Yan, 'Fots: Fast oriented text spotting with a unified network,' in Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition , 2018, pp. 5676-5685. - source
• ?Not matched

  Couldn’t be matched to a paper in Crossref, so it can’t be checked.

  cites [89] [89] A. Gupta, A. Vedaldi, and A. Zisserman, 'Synthetic data for text localisation in natural images,' in Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition , 2016, pp. 2315-2324. -

In the paper

“Cai et al. propose the first deep CNN model for image dehazing, which outperforms traditional prior-based methods by leveraging the powerful representation capacity of CNNs [150].”

What the sources say

• Not checked yetcites [150] [150] B. Cai, X. Xu, K. Jia, C. Qing, and D. Tao, 'Dehazenet: An end-to-end system for single image haze removal,' IEEE Transactions on Image Processing , vol. 25, no. 11, pp. 5187-5198, 2016. - source

In the paper

“Since lowlight images usually contain noises that will be amplified after enhancement, some robust Retinex models have been proposed to account for noise and estimate reflectance, illumination, and noise simultaneously [147], [148].”

What the sources say

• Not checked yetcites [147] [147] M. Li, J. Liu, W. Yang, X. Sun, and Z. Guo, 'Structure-revealing lowlight image enhancement via robust retinex model,' IEEE Transactions on Image Processing , vol. 27, no. 6, pp. 2828-2841, 2018. - source
• Not checked yetcites [148] [148] A. Zhu, L. Zhang, Y. Shen, Y. Ma, S. Zhao, and Y. Zhou, 'Zero-shot restoration of underexposed images via robust retinex decomposition,' - in Proceedings of 2020 IEEE International Conference on Multimedia and Expo . IEEE, 2020, pp. 1-6. - source

In the paper

“For face recognition, significant progress has been achieved in the last decade, mainly owing to deep representation learning and metric learning.”

In the paper

“However, it is a typical ill-posed problem to obtain the reflectance and illumination from a single image.”

In the paper

“To address this issue, a representation learning method using triplet loss is proposed to directly learn discriminative and compact face embedding [99].”

What the sources say

• Not checked yetcites [99] [99] F. Schroff, D. Kalenichenko, and J. Philbin, 'Facenet: A unified embedding for face recognition and clustering,' in Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition , 2015, pp. 815-823. - source

In the paper

“Person re-identification has vast potential for AIoT applications such as smart security in an uncontrolled and non-contact environment, where other biometric recognition techniques are not applicable.”

In the paper

“Images captured in a low-light environment are in low visibility and difficult to see details due to insufficient incident light or underexposure.”