Despite the recent success of video object detection on Desktop GPUs, its architecture is still far too heavy for mobiles. It is also unclear whether the key principles of sparse feature propagation and multi-frame feature aggregation apply at very limited computational resources. In this paper, we present a light weight network architecture for video object detection on mobiles. Light weight image object detector is applied on sparse key frames. A very small network, Light Flow, is designed for establishing correspondence across frames. A flow-guided GRU module is designed to effectively aggregate features on key frames. For non-key frames, sparse feature propagation is performed. The whole network can be trained end-to-end. The proposed system achieves 60.2% mAP score at speed of 25.6 fps on mobiles (e.g., HuaWei Mate 8).
This paper introduces an online model for object detection in videos designed to run in real-time on low-powered mobile and embedded devices. Our approach combines fast single-image object detection with convolutional long short term memory (LSTM) layers to create an interweaved recurrent-convolutional architecture. Additionally, we propose an efficient Bottleneck-LSTM layer that significantly reduces computational cost compared to regular LSTMs. Our network achieves temporal awareness by using Bottleneck-LSTMs to refine and propagate feature maps across frames. This approach is substantially …
With a single eye fixation lasting a fraction of a second, the human visual system is capable of forming a rich representation of a complex environment, reaching a holistic understanding which facilitates object recognition and detection. This phenomenon is known as recognizing the "gist" of the scene and is accomplished by relying on relevant prior knowledge. This paper addresses the analogous question of whether using memory in computer vision systems can not only improve the accuracy of object detection in video streams, but also reduce the computation time. By interleaving conventional fea…
Purdue University（普渡大学）；Nanjing University（南京大学）；Adobe Research（奥多比研究院）；University of Wisconsion-Madison（威斯康星大学麦迪逊分校）
Advanced video analytic systems, including scene classification and object detection, have seen widespread success in various domains such as smart cities and autonomous transportation. With an ever-growing number of powerful client devices, there is incentive to move these heavy video analytics workloads from the cloud to mobile devices to achieve low latency and real-time processing and to preserve user privacy. However, most video analytic systems are heavyweight and are trained offline with some pre-defined latency or accuracy requirements. This makes them unable to adapt at runtime in the…
William & Mary（威廉与玛丽学院）；The University of Texas at Dallas（德克萨斯大学达拉斯分校）
Screen recordings of mobile applications are easy to obtain and capture a wealth of information pertinent to software developers (e.g., bugs or feature requests), making them a popular mechanism for crowdsourced app feedback. Thus, these videos are becoming a common artifact that developers must manage. In light of unique mobile development constraints, including swift release cycles and rapidly evolving platforms, automated techniques for analyzing all types of rich software artifacts provide benefit to mobile developers. Unfortunately, automatically analyzing screen recordings presents serio…
University of Wisconsin-Madison（威斯康星大学麦迪逊分校）；Google（谷歌）
Inverted bottleneck layers, which are built upon depthwise convolutions, have been the predominant building blocks in state-of-the-art object detection models on mobile devices. In this work, we investigate the optimality of this design pattern over a broad range of mobile accelerators by revisiting the usefulness of regular convolutions. We discover that regular convolutions are a potent component to boost the latency-accuracy trade-off for object detection on accelerators, provided that they are placed strategically in the network via neural architecture search. By incorporating regular conv…
Video Object Recognition in Mobile Edge Networks: Local Tracking or Edge Detection?
School of Communications and Electronics Engineering, East China Normal University（电子信息工程学院，华东师范大学）；School of Electronics and Information Technology, Sun Yat-sen University（电子信息技术学院，中山大学）；School of Computer Science, Fudan University（计算机科学学院，复旦大学）；Information Systems Technology and Design Pillar, Singapore University of Technology and Design（信息系统技术与设计学院，新加坡科技设计大学）
Penn State University（宾夕法尼亚州立大学）；International Institute of Tropical Agriculture（国际热带农业研究所）
Convolutional neural network models (CNNs) have made major advances in computer vision tasks in the last five years. Given the challenge in collecting real world datasets, most studies report performance metrics based on available research datasets. In scenarios where CNNs are to be deployed on images or videos from mobile devices, models are presented with new challenges due to lighting, angle, and camera specifications, which are not accounted for in research datasets. It is essential for assessment to also be conducted on real world datasets if such models are to be reliably integrated with…
HSE University（高等经济大学）；St. Petersburg Department of Steklov Institute of Mathematics（斯捷克洛夫数学研究所圣彼得堡分所）；Samsung-PDMI Joint AI Center（三星-PDMI联合人工智能中心）
In this paper user modeling task is examined by processing a gallery of photos and videos on a mobile device. We propose novel engine for user preference prediction based on scene recognition, object detection and facial analysis. At first, all faces in a gallery are clustered and all private photos and videos with faces from large clusters are processed on the embedded system in offline mode. Other photos may be sent to the remote server to be analyzed by very deep models. The visual features of each photo are obtained from scene recognition and object detection models. These features are agg…
Video action recognition, which is topical in computer vision and video analysis, aims to allocate a short video clip to a pre-defined category such as brushing hair or climbing stairs. Recent works focus on action recognition with deep neural networks that achieve state-of-the-art results in need of high-performance platforms. Despite the fast development of mobile computing, video action recognition on mobile devices has not been fully discussed. In this paper, we focus on the novel mobile video action recognition task, where only the computational capabilities of mobile devices are accessib…
Transformer-based models have achieved top performance on major video recognition benchmarks. Benefiting from the self-attention mechanism, these models show stronger ability of modeling long-range dependencies compared to CNN-based models. However, significant computation overheads, resulted from the quadratic complexity of self-attention on top of a tremendous number of tokens, limit the use of existing video transformers in applications with limited resources like mobile devices. In this paper, we extend Mobile-Former to Video Mobile-Former, which decouples the video architecture into a lig…
MobileVidFactory: Automatic Diffusion-Based Social Media Video Generation for Mobile Devices from Text
University of Electronic Science and Technology of China（电子科技大学）；Microsoft Research（微软研究院）；University of Rochester（罗切斯特大学）；National Taiwan University（国立台湾大学）
Northwestern Polytechnical University（西北工业大学）；City University of Hong Kong（香港城市大学）
The ubiquity of camera-embedded devices and the advances in deep learning have stimulated various intelligent mobile video applications. These applications often demand on-device processing of video streams to deliver real-time, high-quality services for privacy and robustness concerns. However, the performance of these applications is constrained by the raw video streams, which tend to be taken with small-aperture cameras of ubiquitous mobile platforms in dim light. Despite extensive low-light video enhancement solutions, they are unfit for deployment to mobile devices due to their complex mo…
We present DeepCache, a principled cache design for deep learning inference in continuous mobile vision. DeepCache benefits model execution efficiency by exploiting temporal locality in input video streams. It addresses a key challenge raised by mobile vision: the cache must operate under video scene variation, while trading off among cacheability, overhead, and loss in model accuracy. At the input of a model, DeepCache discovers video temporal locality by exploiting the video's internal structure, for which it borrows proven heuristics from video compression; into the model, DeepCache propaga…
We present an end-to-end neural network-based model for inferring an approximate 3D mesh representation of a human face from single camera input for AR applications. The relatively dense mesh model of 468 vertices is well-suited for face-based AR effects. The proposed model demonstrates super-realtime inference speed on mobile GPUs (100-1000+ FPS, depending on the device and model variant) and a high prediction quality that is comparable to the variance in manual annotations of the same image.
National Taiwan University（台湾大学）；Intel Labs, Intel Technologies India Pvt. Ltd.（英特尔印度技术私人有限公司英特尔研究院）；Seoul National University（首尔大学）
We develop a system which generates summaries from seniors' indoor-activity videos captured by a social robot to help remote family members know their seniors' daily activities at home. Unlike the traditional video summarization datasets, indoor videos captured from a moving robot poses additional challenges, namely, (i) the video sequences are very long (ii) a significant number of video-frames contain no-subject or with subjects at ill-posed locations and scales (iii) most of the well-posed frames contain highly redundant information. To address this problem, we propose to \hl{exploit} pose …
This paper tackles the problem of semi-supervised video object segmentation on resource-constrained devices, such as mobile phones. We formulate this problem as a distillation task, whereby we demonstrate that small space-time-memory networks with finite memory can achieve competitive results with state of the art, but at a fraction of the computational cost (32 milliseconds per frame on a Samsung Galaxy S22). Specifically, we provide a theoretically grounded framework that unifies knowledge distillation with supervised contrastive representation learning. These models are able to jointly bene…
Realizing the potential of neural video codecs on mobile devices is a big technological challenge due to the computational complexity of deep networks and the power-constrained mobile hardware. We demonstrate practical feasibility by leveraging Qualcomm's technology and innovation, bridging the gap from neural network-based codec simulations running on wall-powered workstations, to real-time operation on a mobile device powered by Snapdragon technology. We show the first-ever inter-frame neural video decoder running on a commercial mobile phone, decoding high-definition videos in real-time whi…
University of Cambridge（剑桥大学）；University of St Andrews（圣安德鲁斯大学）
Visual recognition and vision based retrieval of objects from large databases are tasks with a wide spectrum of potential applications. In this paper we propose a novel recognition method from video sequences suitable for retrieval from databases acquired in highly unconstrained conditions e.g. using a mobile consumer-level device such as a phone. On the lowest level, we represent each sequence as a 3D mesh of densely packed local appearance descriptors. While image plane geometry is captured implicitly by a large overlap of neighbouring regions from which the descriptors are extracted, 3D inf…
Istanbul Technical University（伊斯坦布尔理工大学）；University of Central Florida（中佛罗里达大学）
In recent years, we have seen the performance of video-based person Re-Identification (ReID) methods have improved considerably. However, most of the work in this area has dealt with videos acquired by fixed cameras with wider field of view. Recently, widespread use of wearable cameras and recording devices such as cellphones have opened the door to interesting research in first-person Point-of-view (POV) videos (egocentric videos). Nonetheless, analysis of such videos is challenging due to factors such as poor video quality due to ego-motion, blurriness, severe changes in lighting conditions …
Alpen-Adria-Universität Klagenfurt（克拉根福大学）；Christian Doppler Laboratory ATHENA（克里斯蒂安·多普勒ATHENA实验室）；Institute of Information Technology（信息技术研究所）
Deep neural network (DNN) based approaches have been intensively studied to improve video quality thanks to their fast advancement in recent years. These approaches are designed mainly for desktop devices due to their high computational cost. However, with the increasing performance of mobile devices in recent years, it became possible to execute DNN based approaches in mobile devices. Despite having the required computational power, utilizing DNNs to improve the video quality for mobile devices is still an active research area. In this paper, we propose an open-source mobile platform, namely …
Video super-resolution is one of the most popular tasks on mobile devices, being widely used for an automatic improvement of low-bitrate and low-resolution video streams. While numerous solutions have been proposed for this problem, they are usually quite computationally demanding, demonstrating low FPS rates and power efficiency on mobile devices. In this Mobile AI challenge, we address this problem and propose the participants to design an end-to-end real-time video super-resolution solution for mobile NPUs optimized for low energy consumption. The participants were provided with the REDS tr…
INRIA（法国国家信息与自动化研究所）；Phu Xuan Private University（富春私立大学）
Mobile object tracking has an important role in the computer vision applications. In this paper, we use a tracked target-based taxonomy to present the object tracking algorithms. The tracked targets are divided into three categories: points of interest, appearance and silhouette of mobile objects. Advantages and limitations of the tracking approaches are also analyzed to find the future directions in the object tracking domain.
Face tracking serves as the crucial initial step in mobile applications trying to analyse target faces over time in mobile settings. However, this problem has received little attention, mainly due to the scarcity of dedicated face tracking benchmarks. In this work, we introduce MobiFace, the first dataset for single face tracking in mobile situations. It consists of 80 unedited live-streaming mobile videos captured by 70 different smartphone users in fully unconstrained environments. Over $95K$ bounding boxes are manually labelled. The videos are carefully selected to cover typical smartphone …
A new video coding method based on compressive sampling is proposed. In this method, a video is coded using compressive measurements on video cubes. Video reconstruction is performed by minimization of total variation (TV) of the pixelwise DCT coefficients along the temporal direction. A new reconstruction algorithm is developed from TVAL3, an efficient TV minimization algorithm based on the alternating minimization and augmented Lagrangian methods. Video coding with this method is inherently scalable, and has applications in mobile broadcast.
We present Steadiface, a new real-time face-centric video stabilization method that simultaneously removes hand shake and keeps subject's head stable. We use a CNN to estimate the face landmarks and use them to optimize a stabilized head center. We then formulate an optimization problem to find a virtual camera pose that locates the face to the stabilized head center while retains smooth rotation and translation transitions across frames. We test the proposed method on fieldtest videos and show it stabilizes both the head motion and background. It is robust to large head pose, occlusion, facia…
Recent research has made great progress in realizing neural style transfer of images, which denotes transforming an image to a desired style. Many users start to use their mobile phones to record their daily life, and then edit and share the captured images and videos with other users. However, directly applying existing style transfer approaches on videos, i.e., transferring the style of a video frame by frame, requires an extremely large amount of computation resources. It is still technically unaffordable to perform style transfer of videos on mobile phones. To address this challenge, we pr…
We present Mobile Video Networks (MoViNets), a family of computation and memory efficient video networks that can operate on streaming video for online inference. 3D convolutional neural networks (CNNs) are accurate at video recognition but require large computation and memory budgets and do not support online inference, making them difficult to work on mobile devices. We propose a three-step approach to improve computational efficiency while substantially reducing the peak memory usage of 3D CNNs. First, we design a video network search space and employ neural architecture search to generate …
MobileWAM: Bridging World Action Models to Mobile Manipulation with Chain-of-Foresight
Institute for AI Industry Research (AIR), Tsinghua University（清华大学人工智能产业研究院（AIR））；Shanghai Jiao Tong University（上海交通大学）；The Hong Kong University of Science and Technology (Guangzhou)（香港科技大学（广州））；AIR Wuxi Innovation Center, Tsinghua University（清华大学AIR无锡创新中心）；The University of Adelaide（阿德莱德大学）；Wuhan University（武汉大学）；Southeast University（东南大学）；Beijing Jiaotong University（北京交通大学）；Fudan University（复旦大学）；Li Auto（理想汽车）；School of Information, Renmin University of China（中国人民大学信息学院）
Nowadays, with the vigorous expansion and development of gaming video streaming techniques and services, the expectation of users, especially the mobile phone users, for higher quality of experience is also growing swiftly. As most of the existing research focuses on traditional video streaming, there is a clear lack of both subjective study and objective quality models that are tailored for quality assessment of mobile gaming content. To this end, in this study, we first present a brand new Tencent Gaming Video dataset containing 1293 mobile gaming sequences encoded with three different codec…
Federal Research Center “Computer Science and Control” of Russian Academy of Sciences（俄罗斯科学院计算机科学与控制联邦研究中心）；Smart Engines Service LLC；Moscow Institute of Physics and Technology “MIPT”（莫斯科物理技术学院（MIPT））
Due to a noticeable expansion of document recognition applicability, there is a high demand for recognition on mobile devices. A mobile camera, unlike a scanner, cannot always ensure the absence of various image distortions, therefore the task of improving the recognition precision is relevant. The advantage of mobile devices over scanners is the ability to use video stream input, which allows to get multiple images of a recognized document. Despite this, not enough attention is currently paid to the issue of combining recognition results obtained from different frames when using video stream …
Neural style transfer is a well-known branch of deep learning research, with many interesting works and two major drawbacks. Most of the works in the field are hard to use by non-expert users and substantial hardware resources are required. In this work, we present a solution to both of these problems. We have applied neural style transfer to real-time video (over 25 frames per second), which is capable of running on mobile devices. We also investigate the works on achieving temporal coherence and present the idea of fine-tuning, already trained models, to achieve stable video. What is more, w…
We explore object discovery and detector adaptation based on unlabeled video sequences captured from a mobile platform. We propose a fully automatic approach for object mining from video which builds upon a generic object tracking approach. By applying this method to three large video datasets from autonomous driving and mobile robotics scenarios, we demonstrate its robustness and generality. Based on the object mining results, we propose a novel approach for unsupervised object discovery by appearance-based clustering. We show that this approach successfully discovers interesting objects rele…
Budapest University of Technology and Economics（布达佩斯技术与经济大学）
Articulatory-to-acoustic (forward) mapping is a technique to predict speech using various articulatory acquisition techniques as input (e.g. ultrasound tongue imaging, MRI, lip video). The advantage of lip video is that it is easily available and affordable: most modern smartphones have a front camera. There are already a few solutions for lip-to-speech synthesis, but they mostly concentrate on offline training and inference. In this paper, we propose a system built from a backend for deep neural network training and inference and a fronted as a form of a mobile application. Our initial evalua…
