This paper is on highly accurate and highly efficient human pose estimation. Recent works based on Fully Convolutional Networks (FCNs) have demonstrated excellent results for this difficult problem. While residual connections within FCNs have proved to be quintessential for achieving high accuracy, we re-analyze this design choice in the context of improving both the accuracy and the efficiency over the state-of-the-art. In particular, we make the following contributions: (a) We propose gated skip connections with per-channel learnable parameters to control the data flow for each channel within the module within the macro-module. (b) We introduce a hybrid network that combines the HourGlass and U-Net architectures which minimizes the number of identity connections within the network and increases the performance for the same parameter budget. Our model achieves state-of-the-art results on the MPII and LSP datasets. In addition, with a reduction of 3x in model size and complexity, we show no decrease in performance when compared to the original HourGlass network.
Hangzhou Dianzi University（杭州电子科技大学）；Zhejiang University-University of Illinois at Urbana-Champaign Institute（浙江大学伊利诺伊大学厄巴纳香槟校区联合学院）；University of Washington（华盛顿大学）
3D human pose estimation (HPE) is crucial in many fields, such as human behavior analysis, augmented reality/virtual reality (AR/VR) applications, and self-driving industry. Videos that contain multiple potentially occluded people captured from freely moving monocular cameras are very common in real-world scenarios, while 3D HPE for such scenarios is quite challenging, partially because there is a lack of such data with accurate 3D ground truth labels in existing datasets. In this paper, we propose a temporal regression network with a gated convolution module to transform 2D joints to 3D and r…
Uncertainty-Guided Adverse Weather Restoration via Gated Transformer Network
School of Automation, Southeast University（东南大学自动化学院）；Chair of Robotics, Artificial Intelligence and Real-time Systems, Technical University of Munich（慕尼黑工业大学机器人、人工智能与实时系统讲席教授组）
Leibniz University Hannover（汉诺威莱布尼茨大学）；UBC Vancouver（不列颠哥伦比亚大学温哥华校区）
Human pose estimation from single images is a challenging problem in computer vision that requires large amounts of labeled training data to be solved accurately. Unfortunately, for many human activities (\eg outdoor sports) such training data does not exist and is hard or even impossible to acquire with traditional motion capture systems. We propose a self-supervised approach that learns a single image 3D pose estimator from unlabeled multi-view data. To this end, we exploit multi-view consistency constraints to disentangle the observed 2D pose into the underlying 3D pose and camera rotation.…
Existing CNN-based methods for pixel labeling heavily depend on multi-scale features to meet the requirements of both semantic comprehension and detail preservation. State-of-the-art pixel labeling neural networks widely exploit conventional scale-transfer operations, i.e., up-sampling and down-sampling to learn multi-scale features. In this work, we find that these operations lead to scale-confused features and suboptimal performance because they are spatial-invariant and directly transit all feature information cross scales without spatial selection. To address this issue, we propose the Gat…
Although the performance of 3D human pose and shape estimation methods has improved significantly in recent years, existing approaches typically generate 3D poses defined in camera or human-centered coordinate system. This makes it difficult to estimate a person's pure pose and motion in world coordinate system for a video captured using a moving camera. To address this issue, this paper presents a camera motion agnostic approach for predicting 3D human pose and mesh defined in the world coordinate system. The core idea of the proposed approach is to estimate the difference between two adjacen…
University of Cambridge（剑桥大学）；Cancer Research UK Cambridge Centre（英国癌症研究中心剑桥中心）
Background: Colonoscopy remains the gold-standard screening for colorectal cancer. However, significant miss rates for polyps have been reported, particularly when there are multiple small adenomas. This presents an opportunity to leverage computer-aided systems to support clinicians and reduce the number of polyps missed. Method: In this work we introduce the Focus U-Net, a novel dual attention-gated deep neural network, which combines efficient spatial and channel-based attention into a single Focus Gate module to encourage selective learning of polyp features. The Focus U-Net further incorp…
University of Rochester（罗切斯特大学）；Bytedance AI Lab（字节跳动人工智能实验室）
In this work, we propose a new solution to 3D human pose estimation in videos. Instead of directly regressing the 3D joint locations, we draw inspiration from the human skeleton anatomy and decompose the task into bone direction prediction and bone length prediction, from which the 3D joint locations can be completely derived. Our motivation is the fact that the bone lengths of a human skeleton remain consistent across time. This promotes us to develop effective techniques to utilize global information across all the frames in a video for high-accuracy bone length prediction. Moreover, for the…
CIIRC - Czech Institute of Informatics, Robotics and Cybernetics（捷克信息学、机器人学与控制论研究所（CIIRC））；Czech Technical University in Prague（捷克布拉格技术大学）；Faculty of Electrical Engineering, Czech Technical University in Prague（捷克布拉格技术大学电气工程学院）
Most state-of-the-art localization algorithms rely on robust relative pose estimation and geometry verification to obtain moving object agnostic camera poses in complex indoor environments. However, this approach is prone to mistakes if a scene contains repetitive structures, e.g., desks, tables, boxes, or moving people. We show that the movable objects incorporate non-negligible localization error and present a new straightforward method to predict the six-degree-of-freedom (6DoF) pose more robustly. We equipped the localization pipeline InLoc with real-time instance segmentation network YOLA…
Sun Yat-sen University（中山大学）；South China Normal University（华南师范大学）
Despite remarkable advances in image synthesis research, existing works often fail in manipulating images under the context of large geometric transformations. Synthesizing person images conditioned on arbitrary poses is one of the most representative examples where the generation quality largely relies on the capability of identifying and modeling arbitrary transformations on different body parts. Current generative models are often built on local convolutions and overlook the key challenges (e.g. heavy occlusions, different views or dramatic appearance changes) when distinct geometric change…
GTR: Gated Token Recurrence for Efficient Dense Prediction
Didi International Business Group（滴滴国际业务集团）；Intellindust AI Lab（Intellindust AI实验室）；Institute of Automation, Chinese Academy of Sciences（中国科学院自动化研究所）；Didi Research（滴滴研究院）；The Hong Kong University of Science and Technology (Guangzhou)（香港科技大学（广州））
Hunan University（湖南大学）；State University of New York at Buffalo（纽约州立大学布法罗分校）
Semantic segmentation for lightweight object parsing is a very challenging task, because both accuracy and efficiency (e.g., execution speed, memory footprint or computational complexity) should all be taken into account. However, most previous works pay too much attention to one-sided perspective, either accuracy or speed, and ignore others, which poses a great limitation to actual demands of intelligent devices. To tackle this dilemma, we propose a novel lightweight architecture named Context-Integrated and Feature-Refined Network (CIFReNet). The core components of CIFReNet are the Long-skip…
Face alignment consists of aligning a shape model on a face image. It is an active domain in computer vision as it is a preprocessing for a number of face analysis and synthesis applications. Current state-of-the-art methods already perform well on "easy" datasets, with moderate head pose variations, but may not be robust for "in-the-wild" data with poses up to 90°. In order to increase robustness to an ensemble of factors of variations (e.g. head pose or occlusions), a given layer (e.g. a regressor or an upstream CNN layer) can be replaced by a Mixture of Experts (MoE) layer that uses an ense…
Salient Object Detection is the task of predicting the human attended region in a given scene. Fusing depth information has been proven effective in this task. The main challenge of this problem is how to aggregate the complementary information from RGB modality and depth modality. However, conventional deep models heavily rely on CNN feature extractors, and the long-range contextual dependencies are usually ignored. In this work, we propose Dual Swin-Transformer based Mutual Interactive Network. We adopt Swin-Transformer as the feature extractor for both RGB and depth modality to model the lo…
SAGE: Shape-Adapting Gated Experts for Adaptive Histopathology Image Segmentation
University of Science, VNU-HCM（越南国家大学科学学院）；Trivita AI；University of Technology, VNU-HCM（越南国家大学技术学院）；Michigan State University, USA（美国密歇根州立大学）；The University of Texas at Austin（德克萨斯大学奥斯汀分校）
Human pose estimation (HPE) is one of the most challenging tasks in computer vision as humans are deformable by nature and thus their pose has so much variance. HPE aims to correctly identify the main joint locations of a single person or multiple people in a given image or video. Locating joints of a person in images or videos is an important task that can be applied in action recognition and object tracking. As have many computer vision tasks, HPE has advanced massively with the introduction of deep learning to the field. In this paper, we focus on one of the deep learning-based approaches o…
University of Trento（特伦托大学）；Inria Grenoble Rhone-Alpes（法国国家信息与自动化研究所格勒诺布尔罗纳-阿尔卑斯分部）
In this paper we address the problem of generating person images conditioned on a given pose. Specifically, given an image of a person and a target pose, we synthesize a new image of that person in the novel pose. In order to deal with pixel-to-pixel misalignments caused by the pose differences, we introduce deformable skip connections in the generator of our Generative Adversarial Network. Moreover, a nearest-neighbour loss is proposed instead of the common L1 and L2 losses in order to match the details of the generated image with the target image. We test our approach using photos of persons…
Universidad Politécnica de Madrid（马德里理工大学）；ETSII, Universidad Rey Juan Carlos（胡安·卡洛斯国王大学工程学院）
We present a deep learning-based multi-task approach for head pose estimation in images. We contribute with a network architecture and training strategy that harness the strong dependencies among face pose, alignment and visibility, to produce a top performing model for all three tasks. Our architecture is an encoder-decoder CNN with residual blocks and lateral skip connections. We show that the combination of head pose estimation and landmark-based face alignment significantly improve the performance of the former task. Further, the location of the pose task at the bottleneck layer, at the en…
GDKVM: Echocardiography Video Segmentation via Spatiotemporal Key-Value Memory with Gated Delta Rule
College of Computer Science and Software Engineering, Shenzhen University（深圳大学计算机科学与软件工程学院）；Centre for Smart Health, School of Nursing, The Hong Kong Polytechnic University（香港理工大学智能健康中心）
Why DiT Models Underperform as Representation Learners without Long Skip Connections
Institute of Information Engineering, CAS（中国科学院信息工程研究所）；School of Cyber Security, University of Chinese Academy of Sciences（中国科学院大学网络空间安全学院）；Alibaba Group（阿里巴巴集团）；Institute of Computing Technology, CAS（中国科学院计算技术研究所）；Beijing Academy of Artificial Intelligence（北京人工智能研究院）；School of Computer Science and Tech., University of Chinese Academy of Sciences（中国科学院大学计算机科学与技术学院）；Key Laboratory of Big Data Mining and Knowledge Management, CAS（中国科学院大数据挖掘与知识管理重点实验室）
Human pose transfer, as a misaligned image generation task, is very challenging. Existing methods cannot effectively utilize the input information, which often fail to preserve the style and shape of hair and clothes. In this paper, we propose an adaptive human pose transfer network with two hierarchical deformation levels. The first level generates human semantic parsing aligned with the target pose, and the second level generates the final textured person image in the target pose with the semantic guidance. To avoid the drawback of vanilla convolution that treats all the pixels as valid info…
University of Trento（特伦托大学）；Télécom Paris（巴黎高等电信学院）；Institut polytechnique de Paris（巴黎理工学院）
In this paper, we address the problem of generating person images conditioned on both pose and appearance information. Specifically, given an image xa of a person and a target pose P(xb), extracted from a different image xb, we synthesize a new image of that person in pose P(xb), while preserving the visual details in xa. In order to deal with pixel-to-pixel misalignments caused by the pose differences between P(xa) and P(xb), we introduce deformable skip connections in the generator of our Generative Adversarial Network. Moreover, a nearest-neighbour loss is proposed instead of the common L1 …
Text-guided 3D Human Motion Generation with Keyframe-based Parallel Skip Transformer
School of Electrical, Electronic and Computer Engineering, University of Western Australia（西澳大学电气、电子与计算机工程学院）；University of Melbourne（墨尔本大学）；Commonwealth Scientific and Industrial Research Organisation (CSIRO)（联邦科学与工业研究组织）；Hunan University（湖南大学）；University of Central Florida（中佛罗里达大学）
Ferdowsi University of Mashhad（马什哈德菲尔多西大学）；Stanford University（斯坦福大学）；University of Adelaide（阿德莱德大学）
Smooth and seamless robot navigation while interacting with humans depends on predicting human movements. Forecasting such human dynamics often involves modeling human trajectories (global motion) or detailed body joint movements (local motion). Prior work typically tackled local and global human movements separately. In this paper, we propose a novel framework to tackle both tasks of human motion (or trajectory) and body skeleton pose forecasting in a unified end-to-end pipeline. To deal with this real-world problem, we consider incorporating both scene and social contexts, as critical clues …
Purdue University（普渡大学）；IBM T.J Watson Research Center（IBM托马斯·J·沃森研究中心）
Deep Neural Networks (DNNs) have emerged as the method of choice for solving a wide range of machine learning tasks. The enormous computational demands posed by DNNs have most commonly been addressed through the design of custom accelerators. However, these accelerators are prohibitive in many design scenarios (e.g., wearable devices and IoT sensors), due to stringent area/cost constraints. Accelerating DNNs on these low-power systems, comprising of mainly the general-purpose processor (GPP) cores, requires new approaches. We improve the performance of DNNs on GPPs by exploiting a key attribut…
University of California, Merced（加州大学默塞德分校）；Shenzhen Institutes of Advanced Technology, Chinese Academy of Sciences（中国科学院深圳先进技术研究院）；The Chinese University of Hong Kong（香港中文大学）
We present a novel framework for hallucinating faces of unconstrained poses and with very low resolution (face size as small as 5pxIOD). In contrast to existing studies that mostly ignore or assume pre-aligned face spatial configuration (e.g. facial landmarks localization or dense correspondence field), we alternatingly optimize two complementary tasks, namely face hallucination and dense correspondence field estimation, in a unified framework. In addition, we propose a new gated deep bi-network that contains two functionality-specialized branches to recover different levels of texture details…
Traffic violation and the flexible and changeable nature of pedestrians make it more difficult to predict pedestrian behavior or intention, which might be a potential safety hazard on the road. Pedestrian motion state (such as walking and standing) directly affects or reflects its intention. In combination with pedestrian motion state and other influencing factors, pedestrian intention can be predicted to avoid unnecessary accidents. In this paper, pedestrian is treated as non-rigid object, which can be represented by a set of two-dimensional key points, and the movement of key point relative …
Max Planck Institute for Informatics（马克斯·普朗克信息学研究所）；Saarland Informatics Campus（萨尔兰信息学园区）；EPFL（洛桑联邦理工学院）；University of British Columbia（不列颠哥伦比亚大学）
We present a real-time approach for multi-person 3D motion capture at over 30 fps using a single RGB camera. It operates successfully in generic scenes which may contain occlusions by objects and by other people. Our method operates in subsequent stages. The first stage is a convolutional neural network (CNN) that estimates 2D and 3D pose features along with identity assignments for all visible joints of all individuals.We contribute a new architecture for this CNN, called SelecSLS Net, that uses novel selective long and short range skip connections to improve the information flow allowing for…
Align Your Rhythm: Generating Highly Aligned Dance Poses with Gating-Enhanced Rhythm-Aware Feature Representation
College of Computer Science and Technology, Harbin Engineering University（哈尔滨工程大学计算机科学与技术学院）；Shanghai Academy of Artificial Intelligence for Science（上海人工智能科学研究院）；School of Intelligence Science and Technology, Nanjing University（南京大学智能科学与技术学院）；State Key Laboratory of Space-Ground Integrated Information Technology（空间地面一体化信息技术创新实验室）
