Multi-access edge computing (MEC) is an emerging ecosystem, which aims at converging telecommunication and IT services, providing a cloud computing platform at the edge of the radio access network MEC offers storage and computational resources at the edge, reducing latency for mobile end users and utilizing more efficiently the mobile backhaul and core networks This paper introduces a survey on MEC and focuses on the fundamental key enabling technologies It elaborates MEC orchestration considering both individual services and a network of MEC platforms supporting mobility, bringing light into the different orchestration deployment options In addition, this paper analyzes the MEC reference architecture and main deployment scenarios, which offer multi-tenancy support for application developers, content providers, and third parties Finally, this paper overviews the current standardization activities and elaborates further on open research challenges

/pdf/on-multi-access-edge-computing-a-survey-of-the-emerging-5g-q09cwte3qi.pdf

On Multi-Access Edge Computing: A Survey of the Emerging 5G Network Edge Cloud Architecture and Orchestration

In this paper we illustrate how to perform both visual object tracking and semi-supervised video object segmentation, in real-time, with a single simple approach. Our method, dubbed SiamMask, improves the offline training procedure of popular fully-convolutional Siamese approaches for object tracking by augmenting their loss with a binary segmentation task. Once trained, SiamMask solely relies on a single bounding box initialisation and operates online, producing class-agnostic object segmentation masks and rotated bounding boxes at 55 frames per second. Despite its simplicity, versatility and fast speed, our strategy allows us to establish a new state-of-the-art among real-time trackers on VOT-2018, while at the same time demonstrating competitive performance and the best speed for the semi-supervised video object segmentation task on DAVIS-2016 and DAVIS-2017.

/pdf/fast-online-object-tracking-and-segmentation-a-unifying-3vbx1hwsno.pdf

Fast Online Object Tracking and Segmentation: A Unifying Approach

We introduce here a large tracking database that offers an unprecedentedly wide coverage of common moving objects in the wild, called GOT-10k. Specifically, GOT-10k is built upon the backbone of WordNet structure [1] and it populates the majority of over 560 classes of moving objects and 87 motion patterns, magnitudes wider than the most recent similar-scale counterparts [19] , [20] , [23] , [26] . By releasing the large high-diversity database, we aim to provide a unified training and evaluation platform for the development of class-agnostic, generic purposed short-term trackers. The features of GOT-10k and the contributions of this article are summarized in the following. (1) GOT-10k offers over 10,000 video segments with more than 1.5 million manually labeled bounding boxes, enabling unified training and stable evaluation of deep trackers. (2) GOT-10k is by far the first video trajectory dataset that uses the semantic hierarchy of WordNet to guide class population, which ensures a comprehensive and relatively unbiased coverage of diverse moving objects. (3) For the first time, GOT-10k introduces the one-shot protocol for tracker evaluation, where the training and test classes are zero-overlapped . The protocol avoids biased evaluation results towards familiar objects and it promotes generalization in tracker development. (4) GOT-10k offers additional labels such as motion classes and object visible ratios, facilitating the development of motion-aware and occlusion-aware trackers. (5) We conduct extensive tracking experiments with 39 typical tracking algorithms and their variants on GOT-10k and analyze their results in this paper. (6) Finally, we develop a comprehensive platform for the tracking community that offers full-featured evaluation toolkits, an online evaluation server, and a responsive leaderboard. The annotations of GOT-10k’s test data are kept private to avoid tuning parameters on it.

GOT-10k: A Large High-Diversity Benchmark for Generic Object Tracking in the Wild

The current strive towards end-to-end trainable computer vision systems imposes major challenges for the task of visual tracking. In contrast to most other vision problems, tracking requires the learning of a robust target-specific appearance model online, during the inference stage. To be end-to-end trainable, the online learning of the target model thus needs to be embedded in the tracking architecture itself. Due to the imposed challenges, the popular Siamese paradigm simply predicts a target feature template, while ignoring the background appearance information during inference. Consequently, the predicted model possesses limited target-background discriminability. We develop an end-to-end tracking architecture, capable of fully exploiting both target and background appearance information for target model prediction. Our architecture is derived from a discriminative learning loss by designing a dedicated optimization process that is capable of predicting a powerful model in only a few iterations. Furthermore, our approach is able to learn key aspects of the discriminative loss itself. The proposed tracker sets a new state-of-the-art on 6 tracking benchmarks, achieving an EAO score of 0.440 on VOT2018, while running at over 40 FPS. The code and models are available at https://github.com/visionml/pytracking.

/pdf/learning-discriminative-model-prediction-for-tracking-1j3pep3phf.pdf

Learning Discriminative Model Prediction for Tracking

While recent years have witnessed astonishing improvements in visual tracking robustness, the advancements in tracking accuracy have been limited. As the focus has been directed towards the development of powerful classifiers, the problem of accurate target state estimation has been largely overlooked. In fact, most trackers resort to a simple multi-scale search in order to estimate the target bounding box. We argue that this approach is fundamentally limited since target estimation is a complex task, requiring high-level knowledge about the object. We address this problem by proposing a novel tracking architecture, consisting of dedicated target estimation and classification components. High level knowledge is incorporated into the target estimation through extensive offline learning. Our target estimation component is trained to predict the overlap between the target object and an estimated bounding box. By carefully integrating target-specific information, our approach achieves previously unseen bounding box accuracy. We further introduce a classification component that is trained online to guarantee high discriminative power in the presence of distractors. Our final tracking framework sets a new state-of-the-art on five challenging benchmarks. On the new large-scale TrackingNet dataset, our tracker ATOM achieves a relative gain of 15% over the previous best approach, while running at over 30 FPS. Code and models are available at https://github.com/visionml/pytracking.

/pdf/atom-accurate-tracking-by-overlap-maximization-3a7pnc24a1.pdf

ATOM: Accurate Tracking by Overlap Maximization

In this paper, we address automatic license plate recognition (ALPR) in the wild. Such an ALPR system takes an arbitrary image as input and outputs the recognized license plate numbers. In the detection stage, we adopt a cascade structure comprising of a fast region proposal network and a R-CNN network. The R-CNN network not only eliminates false alarms but also regresses corner positions for each detected plate. This allows us to estimate an affine transformation matrix to rectify the extracted plates. In the recognition stage, we propose an innovative structure composed of parallel spatial transform networks and shared-weight recognizers. The system is trained and evaluated on a Chinese license plate dataset with over 18K images. Results show that our detector performs better than faster R-CNN (VGG) which is 1.5x slower in testing and 57x larger in model size. The recognizer is also significantly better than existing solutions, reducing 57.5% of the errors of a state-of-the-art character sequence encoding scheme.

/pdf/a-cnn-based-approach-for-automatic-license-plate-recognition-2lgc94gr77.pdf

A CNN-Based Approach for Automatic License Plate Recognition in the Wild.

For single-channel speech enhancement, both timedomain and time-frequency-domain methods have their respective pros and cons. In this paper, we present a cross-domain framework named TFTNet, which takes time-frequency spectrogram as input and produces time-domain waveform as output. Such a framework takes advantage of the knowledge we have about spectrogram and avoids some of the drawbacks that T-F-domain methods have been suffering from. In TFT-Net, we design an innovative dual-path attention block (DAB) to fully exploit correlations along the time and frequency axes. We further discover that a sampleindependent DAB (SDAB) achieves a good tradeoff between enhanced speech quality and complexity. Ablation studies show that both the crossdomain design and the SDAB block bring large performance gain. When logarithmic MSE is used as the training criteria, TFT-Net achieves the highest SDR and SSNR among state-of-the-art methods on two major speech enhancement benchmarks.

/pdf/joint-time-frequency-and-time-domain-learning-for-speech-2iwfzmkygj.pdf

Joint Time-Frequency and Time Domain Learning for Speech Enhancement.

Transmission optimization for application-level multicast is described. For each member of a video conference, a multicast tree is generated that represents a data communication configuration of a data source and the other members of a video conference which are data recipients that receive video and audio data from the data source. An end-to-end transmission delay from each data source to each of the respective data recipients is determined, and the available bandwidth between each data source and the respective data recipients is determined. One or more of the multicast trees, each corresponding to a data source, are refined according to the end-to-end transmission delay and available bandwidth for a particular data source to optimize the data communication configuration of the data source in the video conference.

Transmission optimization for application-level multicast

This paper challenges the conventional wisdom that video redundancy should be removed as much as possible for efficient communications. We discover that, by keeping spatial redundancy at the sender and properly utilizing it at the receiver, we can build a more robust and even more efficient wireless video communication system than existing ones. In the proposed framework, inter-frame (temporal) redundancy in video is removed at the encoder, but intra-frame (spatial) redundancy is retained. In doing so, pixel values after a transform-domain scaling are directly transmitted with amplitude modulation. At the receiver, spatial redundancy is utilized by image denoising. Note that denoising in our decoder is not a post-processing, but have to be immediately performed on channel output. We implement the video communication system called Cactus on SORA platform, and make the denoising processing real-time through GPU implementation. Cactus is evaluated in 802.11a/g WLAN environment. On average, Cactus outperforms SoftCast by 4.7 dB in video PSNR and is robust to packet losses.

/pdf/cactus-a-hybrid-digital-analog-wireless-video-communication-6q76lnjnun.pdf

Cactus: a hybrid digital-analog wireless video communication system

Hybrid digital-analog (HDA) transmission has gained increasing attention recently in the context of wireless video delivery , for its ability to simultaneously achieve high transmission efficiency and smooth quality adaptation However, previous systems are optimized solely based on the mean squared error criterion without taking the perceptual video quality into consideration In this work, we propose a structure-preserving HDA video delivery system, named SharpCast, to improve both the objective and subjective visual quality SharpCast decomposes a video into a content part and structure part The latter is important to the human perception and therefore is protected with a robust digital transmission scheme Then, the energy-intensive part in the content information is extracted and transmitted in digital for energy efficiency while the residual is transmitted in analog to achieve the desired smooth adaptation We formulate the resource (power and bandwidth) allocation problem in SharpCast and solve the problem with a greedy strategy Evaluations over nine standard 720p video sequences show that the proposed SharpCast system outperforms the state-of-the-art digital, analog, and HDA schemes by a notable margin in both peak signal-to-noise ratio (PSNR) and structural similarity (SSIM)

Chong Luo

Papers

A CNN-Based Approach for Automatic License Plate Recognition in the Wild.

Joint Time-Frequency and Time Domain Learning for Speech Enhancement.

Transmission optimization for application-level multicast

Cactus: a hybrid digital-analog wireless video communication system

Structure-Preserving Hybrid Digital-Analog Video Delivery in Wireless Networks