Ultrasound (US) imaging is a popular tool in clinical diagnosis, offering safety, repeatability, and real-time capabilities. Freehand 3D US is a technique that provides a deeper understanding of scanned regions without increasing complexity. However, estimating elevation displacement and accumulation error remains challenging, making it difficult to infer the relative position using images alone. The addition of external lightweight sensors has been proposed to enhance reconstruction performance without adding complexity, which has been shown to be beneficial. We propose a novel online self-consistency network (OSCNet) using multiple inertial measurement units (IMUs) to improve reconstruction performance. OSCNet utilizes a modal-level self-supervised strategy to fuse multiple IMU information and reduce differences between reconstruction results obtained from each IMU data. Additionally, a sequence-level self-consistency strategy is proposed to improve the hierarchical consistency of prediction results among the scanning sequence and its sub-sequences. Experiments on large-scale arm and carotid datasets with multiple scanning tactics demonstrate that our OSCNet outperforms previous methods, achieving state-of-the-art reconstruction performance.
Existing methods for 3D human mesh recovery always directly estimate SMPL parameters, which involve both joint rotations and shape parameters. However, these methods present rotation semantic ambiguity, rotation error accumulation, and shape estimation overfitting, which also leads to errors in the estimated pose. Additionally, these methods have not efficiently leveraged the advancements in another hot topic, human pose estimation. To address these issues, we propose a novel approach, Decomposition of 3D Rotation and Lift from 2D Joint to 3D mesh (D3L). We disentangle 3D joint rotation into bone direction and bone twist direction so that the human mesh recovery task is broken down into estimation of pose, twist, and shape, which can be handled independently. Then we design a 2D-to-3D lifting network for estimating twist direction and 3D joint position from 2D joint position sequences and introduce a nonlinear optimization method for fitting shape parameters and bone directions. Our approach can leverage human pose estimation methods, and avoid pose errors introduced by shape estimation overfitting. We conduct experiments on the Human3.6M dataset and demonstrate improved performance compared to existing methods by a large margin.
Massive human-related data is collected to train neural networks for computer vision tasks. A major conflict is exposed relating to software engineers between better developing AI systems and distancing from the sensitive training data. To reconcile this conflict, this paper proposes an efficient privacy-preserving learning paradigm, where images are first encrypted to become ``human-imperceptible, machine-recognizable'' via one of the two encryption strategies: (1) random shuffling to a set of equally-sized patches and (2) mixing-up sub-patches of the images. Then, minimal adaptations are made to vision transformer to enable it to learn on the encrypted images for vision tasks, including image classification and object detection. Extensive experiments on ImageNet and COCO show that the proposed paradigm achieves comparable accuracy with the competitive methods. Decrypting the encrypted images requires solving an NP-hard jigsaw puzzle or an ill-posed inverse problem, which is empirically shown intractable to be recovered by various attackers, including the powerful vision transformer-based attacker. We thus show that the proposed paradigm can ensure the encrypted images have become human-imperceptible while preserving machine-recognizable information. The code is available at \url{https://github.com/FushengHao/PrivacyPreservingML.}
Decoders play significant roles in recovering scene depths. However, the decoders used in previous works ignore the propagation of multilevel lossless fine-grained information, cannot adaptively capture local and global information in parallel, and cannot perform sufficient global statistical analyses on the final output disparities. In addition, the process of mapping from a low-resolution feature space to a high-resolution feature space is a one-to-many problem that may have multiple solutions. Therefore, the quality of the recovered depth map is low. To this end, we propose a high-quality decoder (HQDec), with which multilevel near-lossless fine-grained information, obtained by the proposed adaptive axial-normalized position-embedded channel attention sampling module (AdaAxialNPCAS), can be adaptively incorporated into a low-resolution feature map with high-level semantics utilizing the proposed adaptive information exchange scheme. In the HQDec, we leverage the proposed adaptive refinement module (AdaRM) to model the local and global dependencies between pixels in parallel and utilize the proposed disparity attention module to model the distribution characteristics of disparity values from a global perspective. To recover fine-grained high-resolution features with maximal accuracy, we adaptively fuse the high-frequency information obtained by constraining the upsampled solution space utilizing the local and global dependencies between pixels into the high-resolution feature map generated from the nonlearning method. Extensive experiments demonstrate that each proposed component improves the quality of the depth estimation results over the baseline results, and the developed approach achieves state-of-the-art results on the KITTI and DDAD datasets. The code and models will be publicly available at \href{https://github.com/fwucas/HQDec}{HQDec}.
With the rapid development of 3D vision applications based on point clouds, point cloud quality assessment(PCQA) is becoming an important research topic. However, the prior PCQA methods ignore the effect of local quality variance across different areas of the point cloud. To take an advantage of the quality distribution imbalance, we propose a no-reference point cloud quality assessment (NR-PCQA) method with local area correlation analysis capability, denoted as COPP-Net. More specifically, we split a point cloud into patches, generate texture and structure features for each patch, and fuse them into patch features to predict patch quality. Then, we gather the features of all the patches of a point cloud for correlation analysis, to obtain the correlation weights. Finally, the predicted qualities and correlation weights for all the patches are used to derive the final quality score. Experimental results show that our method outperforms the state-of-the-art benchmark NR-PCQA methods. The source code for the proposed COPP-Net can be found at https://github.com/philox12358/COPP-Net.
Current methods for few-shot segmentation (FSSeg) have mainly focused on improving the performance of novel classes while neglecting the performance of base classes. To overcome this limitation, the task of generalized few-shot semantic segmentation (GFSSeg) has been introduced, aiming to predict segmentation masks for both base and novel classes. However, the current prototype-based methods do not explicitly consider the relationship between base and novel classes when updating prototypes, leading to a limited performance in identifying true categories. To address this challenge, we propose a class contrastive loss and a class relationship loss to regulate prototype updates and encourage a large distance between prototypes from different classes, thus distinguishing the classes from each other while maintaining the performance of the base classes. Our proposed approach achieves new state-of-the-art performance for the generalized few-shot segmentation task on PASCAL VOC and MS COCO datasets.
Photometric differences are widely used as supervision signals to train neural networks for estimating depth and camera pose from unlabeled monocular videos. However, this approach is detrimental for model optimization because occlusions and moving objects in a scene violate the underlying static scenario assumption. In addition, pixels in textureless regions or less discriminative pixels hinder model training. To solve these problems, in this paper, we deal with moving objects and occlusions utilizing the difference of the flow fields and depth structure generated by affine transformation and view synthesis, respectively. Secondly, we mitigate the effect of textureless regions on model optimization by measuring differences between features with more semantic and contextual information without adding networks. In addition, although the bidirectionality component is used in each sub-objective function, a pair of images are reasoned about only once, which helps reduce overhead. Extensive experiments and visual analysis demonstrate the effectiveness of the proposed method, which outperform existing state-of-the-art self-supervised methods under the same conditions and without introducing additional auxiliary information.
While deep learning has been widely used for video analytics, such as video classification and action detection, dense action detection with fast-moving subjects from sports videos is still challenging. In this work, we release yet another sports video dataset $\textbf{P$^2$A}$ for $\underline{P}$ing $\underline{P}$ong-$\underline{A}$ction detection, which consists of 2,721 video clips collected from the broadcasting videos of professional table tennis matches in World Table Tennis Championships and Olympiads. We work with a crew of table tennis professionals and referees to obtain fine-grained action labels (in 14 classes) for every ping-pong action that appeared in the dataset and formulate two sets of action detection problems - action localization and action recognition. We evaluate a number of commonly-seen action recognition (e.g., TSM, TSN, Video SwinTransformer, and Slowfast) and action localization models (e.g., BSN, BSN++, BMN, TCANet), using $\textbf{P$^2$A}$ for both problems, under various settings. These models can only achieve 48% area under the AR-AN curve for localization and 82% top-one accuracy for recognition since the ping-pong actions are dense with fast-moving subjects but broadcasting videos are with only 25 FPS. The results confirm that $\textbf{P$^2$A}$ is still a challenging task and can be used as a benchmark for action detection from videos.
Over the past decades, the incidence of thyroid cancer has been increasing globally. Accurate and early diagnosis allows timely treatment and helps to avoid over-diagnosis. Clinically, a nodule is commonly evaluated from both transverse and longitudinal views using thyroid ultrasound. However, the appearance of the thyroid gland and lesions can vary dramatically across individuals. Identifying key diagnostic information from both views requires specialized expertise. Furthermore, finding an optimal way to integrate multi-view information also relies on the experience of clinicians and adds further difficulty to accurate diagnosis. To address these, we propose a personalized diagnostic tool that can customize its decision-making process for different patients. It consists of a multi-view classification module for feature extraction and a personalized weighting allocation network that generates optimal weighting for different views. It is also equipped with a self-supervised view-aware contrastive loss to further improve the model robustness towards different patient groups. Experimental results show that the proposed framework can better utilize multi-view information and outperform the competing methods.
To understand human behaviors, action recognition based on videos is a common approach. Compared with image-based action recognition, videos provide much more information. Reducing the ambiguity of actions and in the last decade, many works focused on datasets, novel models and learning approaches have improved video action recognition to a higher level. However, there are challenges and unsolved problems, in particular in sports analytics where data collection and labeling are more sophisticated, requiring sport professionals to annotate data. In addition, the actions could be extremely fast and it becomes difficult to recognize them. Moreover, in team sports like football and basketball, one action could involve multiple players, and to correctly recognize them, we need to analyse all players, which is relatively complicated. In this paper, we present a survey on video action recognition for sports analytics. We introduce more than ten types of sports, including team sports, such as football, basketball, volleyball, hockey and individual sports, such as figure skating, gymnastics, table tennis, tennis, diving and badminton. Then we compare numerous existing frameworks for sports analysis to present status quo of video action recognition in both team sports and individual sports. Finally, we discuss the challenges and unsolved problems in this area and to facilitate sports analytics, we develop a toolbox using PaddlePaddle, which supports football, basketball, table tennis and figure skating action recognition.