The first two authors (G. Alinezhad Noghre and A. Danesh Pazho) have equal contribution. Conference: International Conference on Pattern Recognition and Artificial Intelligence
发表信息：
In International Conference on Pattern Recognition and Artificial Intelligence (pp. 258-270). Springer, Cham (2022)
Recent advancements in computer vision have seen a rise in the prominence of applications using neural networks to understand human poses. However, while accuracy has been steadily increasing on State-of-the-Art datasets, these datasets often do not address the challenges seen in real-world applications. These challenges are dealing with people distant from the camera, people in crowds, and heavily occluded people. As a result, many real-world applications have trained on data that does not reflect the data present in deployment, leading to significant underperformance. This article presents ADG-Pose, a method for automatically generating datasets for real-world human pose estimation. These datasets can be customized to determine person distances, crowdedness, and occlusion distributions. Models trained with our method are able to perform in the presence of these challenges where those trained on other datasets fail. Using ADG-Pose, end-to-end accuracy for real-world skeleton-based action recognition sees a 20% increase on scenes with moderate distance and occlusion levels, and a 4X increase on distant scenes where other models failed to perform better than random.
Vision-based Perception System for Automated Delivery Robot-Pedestrians Interactions
Laboratory of Innovations in Transportation (LiTrans)（创新交通实验室）；Data Science Program Toronto Metropolitan University, Canada, Toronto（数据科学项目多伦多 Metropolitan 大学）
University of Illinois at Urbana-Champaign（伊利诺伊大学厄巴纳-香槟分校）
We propose a flexible person generation framework called Dressing in Order (DiOr), which supports 2D pose transfer, virtual try-on, and several fashion editing tasks. The key to DiOr is a novel recurrent generation pipeline to sequentially put garments on a person, so that trying on the same garments in different orders will result in different looks. Our system can produce dressing effects not achievable by existing work, including different interactions of garments (e.g., wearing a top tucked into the bottom or over it), as well as layering of multiple garments of the same type (e.g., jacket…
University of Freiburg（弗莱堡大学）；Adobe Research（Adobe研究院）
Estimating 3D hand pose from single RGB images is a highly ambiguous problem that relies on an unbiased training dataset. In this paper, we analyze cross-dataset generalization when training on existing datasets. We find that approaches perform well on the datasets they are trained on, but do not generalize to other datasets or in-the-wild scenarios. As a consequence, we introduce the first large-scale, multi-view hand dataset that is accompanied by both 3D hand pose and shape annotations. For annotating this real-world dataset, we propose an iterative, semi-automated `human-in-the-loop' appro…
Surround-view fisheye cameras are commonly used for near-field sensing in automated driving. Four fisheye cameras on four sides of the vehicle are sufficient to cover 360° around the vehicle capturing the entire near-field region. Some primary use cases are automated parking, traffic jam assist, and urban driving. There are limited datasets and very little work on near-field perception tasks as the focus in automotive perception is on far-field perception. In contrast to far-field, surround-view perception poses additional challenges due to high precision object detection requirements of 10cm …
University of Bergen（卑尔根大学）；Utrecht University（乌得勒支大学）
Cookie banners, the pop ups that appear to collect your consent for data collection, are a tempting ground for dark patterns. Dark patterns are design elements that are used to influence the user's choice towards an option that is not in their interest. The use of dark patterns renders consent elicitation meaningless and voids the attempts to improve a fair collection and use of data. Can machine learning be used to automatically detect the presence of dark patterns in cookie banners? In this work, a dataset of cookie banners of 300 news websites was used to train a prediction model that does …
Automated Metaheuristic Algorithm Design with Autoregressive Learning
Southern University of Science and Technology（南方科技大学）；Research Institute of Trustworthy Autonomous Systems, Southern University of Science and Technology（南方科技大学可信自主系统研究院）；Harbin Institute of Technology, Shenzhen（哈尔滨工业大学（深圳））
A novel method to identify trampoline skills using a single video camera is proposed herein. Conventional computer vision techniques are used for identification, estimation, and tracking of the gymnast's body in a video recording of the routine. For each frame, an open source convolutional neural network is used to estimate the pose of the athlete's body. Body orientation and joint angle estimates are extracted from these pose estimates. The trajectories of these angle estimates over time are compared with those of labelled reference skills. A nearest neighbour classifier utilising a mean squa…
Department of Radiology, Massachusetts General Hospital（麻省总医院放射科）；Radiology, Perelman School of Medicine, University of Pennsylvania（宾夕法尼亚大学佩雷尔曼医学院放射科）
In fetal-brain MRI, head-pose changes between prescription and acquisition present a challenge to obtaining the standard sagittal, coronal and axial views essential to clinical assessment. As motion limits acquisitions to thick slices that preclude retrospective resampling, technologists repeat ~55-second stack-of-slices scans (HASTE) with incrementally reoriented field of view numerous times, deducing the head pose from previous stacks. To address this inefficient workflow, we propose a robust head-pose detection algorithm using full-uterus scout scans (EPI) which take ~5 seconds to acquire. …
Johns Hopkins University（约翰斯·霍普金斯大学）；Max Planck Institute for Informatics（马克斯·普朗克信息学研究所）；University of Freiburg（弗赖堡大学）
Human pose and shape (HPS) estimation methods achieve remarkable results. However, current HPS benchmarks are mostly designed to test models in scenarios that are similar to the training data. This can lead to critical situations in real-world applications when the observed data differs significantly from the training data and hence is out-of-distribution (OOD). It is therefore important to test and improve the OOD robustness of HPS methods. To address this fundamental problem, we develop a simulator that can be controlled in a fine-grained manner using interpretable parameters to explore the …
Univ. of California Santa Barbara（加州大学圣巴巴拉分校）；West Virginia University（西弗吉尼亚大学）；Santa Barbara Cottage Hospital（圣巴巴拉 Cottage 医院）
Manual analysis of body poses of bed-ridden patients requires staff to continuously track and record patient poses. Two limitations in the dissemination of pose-related therapies are scarce human resources and unreliable automated systems. This work addresses these issues by introducing a new method and a new system for robust automated classification of sleep poses in an Intensive Care Unit (ICU) environment. The new method, coupled-constrained Least-Squares (cc-LS), uses multimodal and multiview (MM) data and finds the set of modality trust values that minimizes the difference between expect…
Northeastern University（东北大学）；Pfizer（辉瑞公司）；Tufts University School of Medicine（塔夫茨大学医学院）；Boston University School of Medicine（波士顿大学医学院）
Objective monitoring and assessment of human motor behavior can improve the diagnosis and management of several medical conditions. Over the past decade, significant advances have been made in the use of wearable technology for continuously monitoring human motor behavior in free-living conditions. However, wearable technology remains ill-suited for applications which require monitoring and interpretation of complex motor behaviors (e.g. involving interactions with the environment). Recent advances in computer vision and deep learning have opened up new possibilities for extracting information…
University of Konstanz（康斯坦茨大学）；Max Planck Institute of Animal Behavior（马克斯·普朗克动物行为研究所）；Technische Universität München（慕尼黑工业大学）；Eötvös Loránd University（厄特沃什·罗兰大学）；Hungarian Academy of Sciences（匈牙利科学院）
Recent advances in machine learning and computer vision are revolutionizing the field of animal behavior by enabling researchers to track the poses and locations of freely moving animals without any marker attachment. However, large datasets of annotated images of animals for markerless pose tracking, especially high-resolution images taken from multiple angles with accurate 3D annotations, are still scant. Here, we propose a method that uses a motion capture (mo-cap) system to obtain a large amount of annotated data on animal movement and posture (2D and 3D) in a semi-automatic manner. Our me…
We address the discovery of composition transfer in artworks based on their visual content. Automated analysis of large art collections, which are growing as a result of art digitization among museums and galleries, is an important tool for art history and assists cultural heritage preservation. Modern image retrieval systems offer good performance on visually similar artworks, but fail in the cases of more abstract composition transfer. The proposed approach links artworks through a pose similarity of human figures depicted in images. Human figures are the subject of a large fraction of visua…
Current 6D object pose methods consist of deep CNN models fully optimized for a single object but with its architecture standardized among objects with different shapes. In contrast to previous works, we explicitly exploit each object's distinct topological information i.e. 3D dense meshes in the pose estimation model, with an automated process and prior to any post-processing refinement stage. In order to achieve this, we propose a learning framework in which a Graph Convolutional Neural Network reconstructs a pose conditioned 3D mesh of the object. A robust estimation of the allocentric orie…
Scholars have recently drawn attention to a range of controversial issues posed by the use of computer vision for automatically generating descriptions of people in images. Despite these concerns, automated image description has become an important tool to ensure equitable access to information for blind and low vision people. In this paper, we investigate the ethical dilemmas faced by companies that have adopted the use of computer vision for producing alt text: textual descriptions of images for blind and low vision people, We use Facebook's automatic alt text tool as our primary case study.…
Norwegian University of Science and Technology（挪威科技大学）；St. Olavs Hospital, Trondheim University Hospital（圣奥拉夫医院，特隆赫姆大学医院）
Assessment of spontaneous movements can predict the long-term developmental disorders in high-risk infants. In order to develop algorithms for automated prediction of later disorders, highly precise localization of segments and joints by infant pose estimation is required. Four types of convolutional neural networks were trained and evaluated on a novel infant pose dataset, covering the large variation in 1 424 videos from a clinical international community. The localization performance of the networks was evaluated as the deviation between the estimated keypoint positions and human expert ann…
We propose a fully automated system that simultaneously estimates the camera intrinsics, the ground plane, and physical distances between people from a single RGB image or video captured by a camera viewing a 3-D scene from a fixed vantage point. To automate camera calibration and distance estimation, we leverage priors about human pose and develop a novel direct formulation for pose-based auto-calibration and distance estimation, which shows state-of-the-art performance on publicly available datasets. The proposed approach enables existing camera systems to measure physical distances without …
Comparison of marker-less 2D image-based methods for infant pose estimation
University Medical Center Göttingen（戈滕堡大学医学中心）；German Center for Child and Adolescent Health (DZKJ)（德国儿童与青少年健康研究中心）；Leibniz ScienceCampus Göttingen（戈滕堡莱比锡科学校园）；University of Göttingen（戈滕堡大学）；III Institute of Physics - Biophysics（物理-生物物理第三研究所）；University Hospital Heidelberg（海德堡大学医院）；Ruprecht-Karls University of Heidelberg（海德堡鲁珀特-卡尔大学）；Department of Child and Adolescent Psychiatry（儿童与青少年精神病科部门）；Medical University of Graz（格拉茨医学院）；Curtin Autism Research Group（库林自闭症研究组）；Curtin School of Allied Health（库林健康联盟学校）；Curtin University（库林大学）；Center of Neurodevelopmental Disorders (KIND)（神经发育障碍中心（KIND））；Department of Women’s and Children’s Health（妇女与儿童健康部门）；Center for Psychiatry Research（精神医学研究中心）；Karolinska Institutet（卡罗林斯卡研究所）；Region Stockholm（斯德哥尔摩地区）；Child and Adolescent Psychiatry, Stockholm Health Care Services, Region Stockholm（斯德哥尔摩健康服务儿童与青少年精神病科，斯德哥尔摩地区）；Stockholm Health Care Services, Region Stockholm（斯德哥尔摩健康服务，斯德哥尔摩地区）
University of Zurich（苏黎世大学）；Czech Technical University in Prague（捷克布拉格技术大学）
Visual Localization is one of the key enabling technologies for autonomous driving and augmented reality. High quality datasets with accurate 6 Degree-of-Freedom (DoF) reference poses are the foundation for benchmarking and improving existing methods. Traditionally, reference poses have been obtained via Structure-from-Motion (SfM). However, SfM itself relies on local features which are prone to fail when images were taken under different conditions, e.g., day/ night changes. At the same time, manually annotating feature correspondences is not scalable and potentially inaccurate. In this work,…
Ulm University（乌尔姆大学）；Otto von Guericke University Magdeburg（马格德堡奥托·冯·格里克大学）
We present a joint camera and radar approach to enable autonomous vehicles to understand and react to human gestures in everyday traffic. Initially, we process the radar data with a PointNet followed by a spatio-temporal multilayer perceptron (stMLP). Independently, the human body pose is extracted from the camera frame and processed with a separate stMLP network. We propose a fusion neural network for both modalities, including an auxiliary loss for each modality. In our experiments with a collected dataset, we show the advantages of gesture recognition with two modalities. Motivated by adver…
New York University, Tandon School of Engineering（纽约大学坦登工程学院）
Estimating the 6D pose of objects is beneficial for robotics tasks such as transportation, autonomous navigation, manipulation as well as in scenarios beyond robotics like virtual and augmented reality. With respect to single image pose estimation, pose tracking takes into account the temporal information across multiple frames to overcome possible detection inconsistencies and to improve the pose estimation efficiency. In this work, we introduce a novel Deep Neural Network (DNN) called VIPose, that combines inertial and camera data to address the object pose tracking problem in real-time. The…
University of Washington（华盛顿大学）；Electronics and Telecommunications Research Institute（电子与电信研究所）
The Alberta Infant Motor Scale (AIMS) is a well-known assessment scheme that evaluates the gross motor development of infants by recording the number of specific poses achieved. With the aid of the image-based pose recognition model, the AIMS evaluation procedure can be shortened and automated, providing early diagnosis or indicator of potential developmental disorder. Due to limited public infant-related datasets, many works use the SMIL-based method to generate synthetic infant images for training. However, this domain mismatch between real and synthetic training samples often leads to perfo…
We present a new dataset for 6-DoF pose estimation of known objects, with a focus on robotic manipulation research. We propose a set of toy grocery objects, whose physical instantiations are readily available for purchase and are appropriately sized for robotic grasping and manipulation. We provide 3D scanned textured models of these objects, suitable for generating synthetic training data, as well as RGBD images of the objects in challenging, cluttered scenes exhibiting partial occlusion, extreme lighting variations, multiple instances per image, and a large variety of poses. Using semi-autom…
While many recent hand pose estimation methods critically rely on a training set of labelled frames, the creation of such a dataset is a challenging task that has been overlooked so far. As a result, existing datasets are limited to a few sequences and individuals, with limited accuracy, and this prevents these methods from delivering their full potential. We propose a semi-automated method for efficiently and accurately labeling each frame of a hand depth video with the corresponding 3D locations of the joints: The user is asked to provide only an estimate of the 2D reprojections of the visib…
Simon Fraser University（西蒙弗雷泽大学）；Alibaba XR Lab（阿里巴巴XR实验室）；Shanghai Jiao Tong University（上海交通大学）
We present a dataset of 998 3D models of everyday tabletop objects along with their 847,000 real world RGB and depth images. Accurate annotations of camera poses and object poses for each image are performed in a semi-automated fashion to facilitate the use of the dataset for myriad 3D applications like shape reconstruction, object pose estimation, shape retrieval etc. We primarily focus on learned multi-view 3D reconstruction due to the lack of appropriate real world benchmark for the task and demonstrate that our dataset can fill that gap. The entire annotated dataset along with the source c…
University of Michigan（密歇根大学）；Ford Center for Autonomous Vehicles Laboratory（福特自动驾驶汽车实验室）
This paper presents a novel dataset titled PedX, a large-scale multimodal collection of pedestrians at complex urban intersections. PedX consists of more than 5,000 pairs of high-resolution (12MP) stereo images and LiDAR data along with providing 2D and 3D labels of pedestrians. We also present a novel 3D model fitting algorithm for automatic 3D labeling harnessing constraints across different modalities and novel shape and temporal priors. All annotated 3D pedestrians are localized into the real-world metric space, and the generated 3D models are validated using a mocap system configured in a…
