Diffusion models have achieved remarkable success in image generation, with applications broadening across various domains. Inpainting is one such application that can benefit significantly from diffusion models. Existing methods either hijack the reverse process of a pretrained diffusion model or cast the problem into a larger framework, i.e., conditioned generation. However, these approaches often require nested loops in the generation process or additional components for conditioning. In this paper, we present region-aware diffusion models (RAD) for inpainting with a simple yet effective reformulation of the vanilla diffusion models. RAD utilizes a different noise schedule for each pixel, which allows local regions to be generated asynchronously while considering the global image context. A plain reverse process requires no additional components, enabling RAD to achieve inference time up to 100 times faster than the state-of-the-art approaches. Moreover, we employ low-rank adaptation (LoRA) to fine-tune RAD based on other pretrained diffusion models, reducing computational burdens in training as well. Experiments demonstrated that RAD provides state-of-the-art results both qualitatively and quantitatively, on the FFHQ, LSUN Bedroom, and ImageNet datasets.

Understanding human-to-human interactions, especially in contexts like public security surveillance, is critical for monitoring and maintaining safety. Traditional activity recognition systems are limited by fixed vocabularies, predefined labels, and rigid interaction categories that often rely on choreographed videos and overlook concurrent interactive groups. These limitations make such systems less adaptable to real-world scenarios, where interactions are diverse and unpredictable. In this paper, we propose an open vocabulary human-to-human interaction recognition (OV-HHIR) framework that leverages large language models to generate open-ended textual descriptions of both seen and unseen human interactions in open-world settings without being confined to a fixed vocabulary. Additionally, we create a comprehensive, large-scale human-to-human interaction dataset by standardizing and combining existing public human interaction datasets into a unified benchmark. Extensive experiments demonstrate that our method outperforms traditional fixed-vocabulary classification systems and existing cross-modal language models for video understanding, setting the stage for more intelligent and adaptable visual understanding systems in surveillance and beyond.

Disordered Quantum many-body Systems (DQS) and Quantum Neural Networks (QNN) have many structural features in common. However, a DQS is essentially an initialized QNN with random weights, often leading to non-random outcomes. In this work, we emphasize the possibilities of random processes being a deceptive quantum-generating model effectively hidden in a QNN. When we choose weights in a QNN randomly the unitarity property of quantum gates is unchanged. As we show, this can lead to memory effects with multiple consequences on the learnability and trainability of QNN one would not expect from a classical neural network with random weights. This phenomenon may lead to a fundamental misunderstanding of the capabilities of common quantum generative models, where the generation of new samples is essentially averaging over random outputs. While we suggest that DQS can be effectively used for tasks like image augmentation, we draw the attention that overly simple datasets are often used to show the generative capabilities of quantum models, potentially leading to overestimation of their effectiveness.

In this paper, we propose SPACE, a novel anomaly detection methodology that integrates a Feature Encoder (FE) into the structure of the Student-Teacher method. The proposed method has two key elements: Spatial Consistency regularization Loss (SCL) and Feature converter Module (FM). SCL prevents overfitting in student models by avoiding excessive imitation of the teacher model. Simultaneously, it facilitates the expansion of normal data features by steering clear of abnormal areas generated through data augmentation. This dual functionality ensures a robust boundary between normal and abnormal data. The FM prevents the learning of ambiguous information from the FE. This protects the learned features and enables more effective detection of structural and logical anomalies. Through these elements, SPACE is available to minimize the influence of the FE while integrating various data augmentations. In this study, we evaluated the proposed method on the MVTec LOCO, MVTec AD, and VisA datasets. Experimental results, through qualitative evaluation, demonstrate the superiority of detection and efficiency of each module compared to state-of-the-art methods.

We present a novel local-global feature fusion framework for body-weight exercise recognition with floor-based dynamic pressure maps. One step further from the existing studies using deep neural networks mainly focusing on global feature extraction, the proposed framework aims to combine local and global features using image processing techniques and the YOLO object detection to localize pressure profiles from different body parts and consider physical constraints. The proposed local feature extraction method generates two sets of high-level local features consisting of cropped pressure mapping and numerical features such as angular orientation, location on the mat, and pressure area. In addition, we adopt a knowledge distillation for regularization to preserve the knowledge of the global feature extraction and improve the performance of the exercise recognition. Our experimental results demonstrate a notable 11 percent improvement in F1 score compared to the baseline 3DCNN for exercise recognition while preserving label-specific features.

Manufacturing industries strive to improve production efficiency and product quality by deploying advanced sensing and control systems. Wearable sensors are emerging as a promising solution for achieving this goal, as they can provide continuous and unobtrusive monitoring of workers’ activities in the manufacturing line. This article presents a novel wearable sensing prototype that combines IMU and body capacitance sensing modules to recognize worker activities in the manufacturing line. To handle these multimodal sensor data, we propose and compare early, and late sensor data fusion approaches for multichannel time-series convolutional neural networks and deep convolutional LSTM. We evaluate the proposed hardware and neural network model by collecting and annotating sensor data using the proposed sensing prototype and Apple Watches in the testbed of the manufacturing line. Experimental results demonstrate that our proposed methods achieve superior performance compared to the baseline methods, indicating the potential of the proposed approach for real-world applications in manufacturing industries. Furthermore, the proposed sensing prototype with a body capacitive sensor (BCS) and feature fusion method improves by 6.35%, yielding a 9.38% higher macro F1 score than the proposed sensing prototype without a BCS and Apple Watch data, respectively.

In this work, we propose an open-source scalable end-to-end RTL framework FieldHAR, for complex human activ-ity recognition (HAR) from heterogeneous sensors using artificial neural networks (ANN) optimized for FPGA or ASIC integration. FieldHAR aims to address the lack of apparatus to transform complex HAR methodologies often limited to offline evaluation to efficient runtime edge applications. The framework uses parallel sensor interfaces and integer-based multi-branch convolutional neural networks (CNNs) to support flexible modality extensions with synchronous sampling at the maximum rate of each sensor. To validate the framework, we used a sensor-rich kitchen scenario HAR application which was demonstrated in a previous offline study. Through resource-aware optimizations, with FieldHAR the entire RTL solution was created from data acquisition to ANN inference taking as low as 25% logic elements and 2% memory bits of a low-end Cyclone IV FPGA and less than 1% accuracy loss from the original FP32 precision offline study. The RTL implementation also shows advantages over MCU-based solutions, including superior data acquisition performance and virtually eliminating ANN inference bottleneck.

Recent advances in deep learning have significantly improved the performance of various computer vision applications. However, discovering novel categories in an incremental learning scenario remains a challenging problem due to the lack of prior knowledge about the number and nature of new categories. Existing methods for novel category discovery are limited by their reliance on labeled datasets and prior knowledge about the number of novel categories and the proportion of novel samples in the batch. To address the limitations and more accurately reflect real-world scenarios, in this paper, we propose a novel unsupervised class incremental learning approach for discovering novel categories on unlabeled sets without prior knowledge. The proposed method fine-tunes the feature extractor and proxy anchors on labeled sets, then splits samples into old and novel categories and clusters on the unlabeled dataset. Furthermore, the proxy anchors-based exemplar generates representative category vectors to mitigate catastrophic forgetting. Experimental results demonstrate that our proposed approach outperforms the state-of-the-art methods on fine-grained datasets under real-world scenarios.

Online clothing shopping has become increasingly popular, but the high rate of returns due to size and fit issues has remained a major challenge. To address this problem, virtual try-on systems have been developed to provide customers with a more realistic and personalized way to try on clothing. In this paper, we propose a novel virtual try-on method called ClothFit, which can predict the draping shape of a garment on a target body based on the actual size of the garment and human attributes. Unlike existing try-on models, ClothFit considers the actual body proportions of the person and available cloth sizes for clothing virtualization, making it more appropriate for current online apparel outlets. The proposed method utilizes a U-Net-based network architecture that incorporates cloth and human attributes to guide the realistic virtual try-on synthesis. Specifically, we extract features from a cloth image using an auto-encoder and combine them with features from the user’s height, weight, and cloth size. The features are concatenated with the features from the U-Net encoder, and the U-Net decoder synthesizes the final virtual try-on image. Our experimental results demonstrate that ClothFit can significantly improve the existing state-of-the-art methods in terms of photo-realistic virtual try-on results.

Early prediction of remaining useful life (RUL) is crucial for effective battery management across various industries, ranging from household appliances to large-scale applications. Accurate RUL prediction improves the reliability and maintainability of battery technology. However, existing methods have limitations, including assumptions of data from the same sensors or distribution, foreknowledge of the end of life (EOL), and neglect to determine the first prediction cycle (FPC) to identify the start of the unhealthy stage. This paper proposes a novel method for RUL prediction of Lithium-ion batteries. The proposed framework comprises two stages: determining the FPC using a neural network-based model to divide the degradation data into distinct health states and predicting the degradation pattern after the FPC to estimate the remaining useful life as a percentage. Experimental results demonstrate that the proposed method outperforms conventional approaches in terms of RUL prediction. Furthermore, the proposed method shows promise for real-world scenarios, providing improved accuracy and applicability for battery management.

The naphtha cracking process heavily relies on the composition of naphtha, which is a complex blend of different hydrocarbons. Predicting the naphtha composition accurately is crucial for efficiently controlling the cracking process and achieving maximum performance. Traditional methods, such as gas chromatography and true boiling curve, are not feasible due to the need for pilot-plant-scale experiments or cost constraints. In this paper, we propose a neural network framework that utilizes chemical property information to improve the performance of naphtha composition prediction. Our proposed framework comprises two parts: a Watson K factor estimation network and a naphtha composition prediction network. Both networks share a feature extraction network based on Convolutional Neural Network (CNN) architecture, while the output layers use Multi-Layer Perceptron (MLP) based networks to generate two different outputs - Watson K factor and naphtha composition. The naphtha composition is expressed in percentages, and its sum should be 100%. To enhance the naphtha composition prediction, we utilize a distillation simulator to obtain the distillation curve from the naphtha composition, which is dependent on its chemical properties. By designing a loss function between the estimated and simulated Watson K factors, we improve the performance of both Watson K estimation and naphtha composition prediction. The experimental results show that our proposed framework can predict the naphtha composition accurately while reflecting real naphtha chemical properties.

The estimation of 3D human body shape and clothing measurements is crucial for virtual try-on and size recommendation problems in the fashion industry but has always been a challenging problem due to several conditions, such as lack of publicly available realistic datasets, ambiguity in multiple camera resolutions, and the undefinable human shape space. Existing works proposed various solutions to these problems but could not succeed in the industry adaptation because of complexity and restrictions. To solve the complexity and challenges, in this paper, we propose a simple yet effective architecture to estimate both shape and measures from frontal- and side-view images. We utilize silhouette segmentation from the two multi-view images and implement an auto-encoder network to learn low-dimensional features from segmented silhouettes. Then, we adopt a kernel-based regularized regression module to estimate the body shape and measurements. The experimental results show that the proposed method provides competitive results on the synthetic dataset, NOMO-3d-400-scans Dataset, and RGB Images of humans captured in different cameras.

User dependence remains one of the most difficult general problems in Human Activity Recognition (HAR), in particular when using wearable sensors. This is due to the huge variability of the way different people execute even the simplest actions. In addition, detailed sensor fixtures and placement will be different for different people or even at different times for the same users. In theory, the problem can be solved by a large enough data set. However, recording data sets that capture the entire diversity of complex activity sets is seldom practicable. Instead, models are needed that focus on features that are invariant across users. To this end, we present an adversarial subject-independent feature extraction method with the maximum mean discrepancy (MMD) regularization for human activity recognition. The proposed model is capable of learning a subject-independent embedding feature representation from multiple subjects datasets and generalizing it to unseen target subjects. The proposed network is based on the adversarial encoder-decoder structure with the MMD to realign the data distribution over multiple subjects. Experimental results show that the proposed method not only outperforms state-of-the-art methods over the four real-world datasets but also improves the subject generalization effectively. We evaluate the method on well-known public data sets showing that it significantly improves user-independent performance and reduces variance in results.

The demands of automated shipping address recognition and verification have increased to handle a large number of packages and to save costs associated with misdelivery. A previous study proposed a deep learning system where the shipping address is recognized and verified based on a camera image capturing the shipping address and barcode area. Because the system performance depends on the input image quality, inspection of input image quality is necessary for image preprocessing. In this paper, we propose an input image quality verification method combining global and local features. Object detection and scale-invariant feature transform in different feature spaces are developed to extract global and local features from several independent convolutional neural networks. The conditions of shipping label images are classified by fully connected fusion layers with concatenated global and local features. The experimental results regarding real captured and generated images show that the proposed method achieves better performance than other methods. These results are expected to improve the shipping address recognition and verification system by applying different image preprocessing steps based on the classified conditions.

Shipping labels are widely used in logistics. It is important to ensure the quality of printing label and to verify contents of the shipping label on the package. We developed a verification and recognition method for various types of shipping labels by using deep neural networks. The experimental results showed 96% recognition accuracy in rotation-invariant conditions. Also, we introduce Google Maps API for validating the address which can reduce the cost of returning packages due to the invalid address. To train and evaluate the method, we have generated and collected 25 different types of shipping label dataset. We plan to release the dataset on our website1.

3D point cloud data is used for 3D model acquisition, geometry processing and 3D inspection. Registration of 3D point cloud data is crucial for each field. The difference between 2D image registration and 3D point cloud registration is that the latter requires several things to be considered: translation on each plane, rotation, tilt and etc. This paper describes a method of registering 3D point cloud data with noise. The relationship between the two sets of 3D point cloud data can be obtained by Affine transformation. In order to calculate 3D Affine transformation matrix, corresponding points are required. To find the corresponding points, we use the height map which is projected from 3D point cloud data onto XY plane. We formulate the height map matching as a cost function and estimate the corresponding points. To find the proper 3D Affine transformation matrix, we formulate a cost function which uses the relationship of the corresponding points. Also the proper 3D Affine transformation matrix can be calculated by minimizing the cost function. The experimental results show that the proposed method can be applied to various objects and gives better performance than the previous work.

Albedo estimation from a facial image is crucial for various computer vision tasks, such as 3-D morphable-model fitting, shape recovery, and illumination-invariant face recognition, but the currently available methods do not give good estimation results. Most methods ignore the influence of cast shadows and require a statistical model to obtain facial albedo. This paper describes a method for albedo estimation that makes combined use of image intensity and facial depth information for an image with cast shadows and general unknown light. In order to estimate the albedo map of a face, we formulate the albedo estimation problem as a linear programming problem that minimizes intensity error under the assumption that the surface of the face has constant albedo. Since the solution thus obtained has significant errors in certain parts of the facial image, the albedo estimate needs to be compensated. We minimize the mean square error of albedo under the assumption that the surface normals, which are calculated from the facial depth information, are corrupted with noise. The proposed method is simple and the experimental results show that this method gives better estimates than other methods.

Albedo estimation from a facial image is crucial for various computer vision tasks such as 3D morphable model fitting, shape recovery and illumination-invariant face recognition, but it has not been addressed well. This paper describes how albedo can be estimated from the combined use of image in tensity and facial depth information even if the image is under general,unknown light with cast shadow. In order to estimate the albedo map, we formulate the albedo estimation problem as a linear programming using 1-norm under the assumption that the surface of a face has a constant albedo. The proposed method is simple and the experiment results show that the proposed approach gives better albedo estimation than other methods.