Search

Capturing long-range dependencies during feature extraction is crucial for video-based person re-identification (re-id) since it would help to tackle many challenging problems such as occlusion and dramatic pose variation. Moreover, capturing subtle differences, such as bags and glasses, is indispensable to distinguish similar pedestrians. In this paper, we propose a novel and efficacious Statistic Attention (SA) block which can capture both the long-range dependencies and subtle differences. SA block leverages high-order statistics of feature maps, which contain both long-range and high-order information. By modeling relations with these statistics, SA block can explicitly capture long-range dependencies with less time complexity. In addition, high-order statistics usually concentrate on details of feature maps and can perceive the subtle differences between pedestrians. In this way, SA block is capable of discriminating pedestrians with subtle differences. Furthermore, this lightweight block can be conveniently inserted into existing deep neural networks at any depth to form Statistic Attention Network (SANet). To evaluate its performance, we conduct extensive experiments on two challenging video re-id datasets, showing that our SANet outperforms the state-of-the-art methods. Furthermore, to show the generalizability of SANet, we evaluate it on three image re-id datasets and two more general image classification datasets, including ImageNet. The source code is available at http://vipl.ict.ac.cn/resources/codes/code/SANet code.zip.

In this paper, we address the semantic segmentation task with a new context aggregation scheme named object context, which focuses on enhancing the role of object information. Motivated by the fact that the category of each pixel is inherited from the object it belongs to, we define the object context for each pixel as the set of pixels that belong to the same category as the given pixel in the image. We use a binary relation matrix to represent the relationship between all pixels, where the value one indicates the two selected pixels belong to the same category and zero otherwise. We propose to use a dense relation matrix to serve as a surrogate for the binary relation matrix. The dense relation matrix is capable to emphasize the contribution of object information as the relation scores tend to be larger on the object pixels than the other pixels. Considering that the dense relation matrix estimation requires quadratic computation overhead and memory consumption w.r.t. the input size, we propose an efficient interlaced sparse self-attention scheme to model the dense relations between any two of all pixels via the combination of two sparse relation matrices. To capture richer context information, we further combine our interlaced sparse self-attention scheme with the conventional multi-scale context schemes including pyramid pooling (Zhao et al. 2017) and atrous spatial pyramid pooling (Chen et al. 2018). We empirically show the advantages of our approach with competitive performances on five challenging benchmarks including: Cityscapes, ADE20K, LIP, PASCAL-Context and COCO-Stuff.

Face presentation attack detection (PAD) is essential for securing the widely used face recognition systems. Most of the existing PAD methods do not generalize well to unseen scenarios because labeled training data of the new domain is usually not available. In light of this, we propose an unsupervised domain adaptation with disentangled representation (DR-UDA) approach to improve the generalization capability of PAD into new scenarios. DR-UDA consists of three modules, i.e., ML-Net, UDA-Net and DR-Net. ML-Net aims to learn a discriminative feature representation using the labeled source domain face images via metric learning. UDA-Net performs unsupervised adversarial domain adaptation in order to optimize the source domain and target domain encoders jointly, and obtain a common feature space shared by both domains. As a result, the source domain PAD model can be effectively transferred to the unlabeled target domain for PAD. DR-Net further disentangles the features irrelevant to specific domains by reconstructing the source and target domain face images from the common feature space. Therefore, DR-UDA can learn a disentangled representation space which is generative for face images in both domains and discriminative for live vs. spoof classification. The proposed approach shows promising generalization capability in several public-domain face PAD databases.

In this work, we study the problem of deep representation learning on a large face dataset with long-tail distribution. Training convolutional neural networks on such dataset with conventional strategy suffers from imbalance problem which results in biased classification boundary, and the few-shot classes lying in tail parts further make the model prone to overfitting. Aiming to learn more discriminative CNN model from long-tail data, we propose a novel aggregate-and-disperse training schema. Firstly, our proposed method aggregates similar classes in tail part to avoid imbalance problem. Based on the aggregated super classes and those original head classes, a model is pre-trained to capture accurate discrimination in head classes as well as coarse discrinimation in tail classes. Secondly, we selectively disperses those aggregated super classes to learn precise inter-class variations and refine the representation for better generalization. We perform extensive experiments on MS-Celeb-1M, BLUFR and MegaFace. Compared with baselines and existing methods, our method achieves better performance of face recognition, demonstrating its effectiveness of handling long-tail distribution.

Due to the highly complex semantic information of images, even with the same query image, the expected content-based image retrieval results could be very different and personalized in different scenarios. However, most existing hashing methods only preserve one single type of semantic similarity, making them incapable of addressing such realistic retrieval tasks. To deal with this problem, we propose a unified hashing framework to encode multiple types of information into the binary codes by exploiting convolutional networks (CNNs). Specifically, we assume that typical retrieval tasks are generally defined in two aspects, i.e. high-level semantics (e.g. object categories) and visual attributes (e.g. object shape and color). To this end, our Dual Purpose Hashing model is trained to jointly preserve two kinds of similarities characterizing the two aspects respectively. Moreover, since images with both category and attribute labels are scarce, our model is carefully designed to leverage the abundant partially labelled data as training inputs to alleviate the risk of overfitting. With such a framework, the binary codes of new-coming images can be readily obtained by quantizing the outputs of a specific CNN layer, and different retrieval tasks can be achieved by using the binary codes in different ways. Experiments on two large-scale datasets show that our method achieves comparable or even better performance than those state-of-the-art methods specifically designed for each individual retrieval task while being more compact than the compared methods.

Solving visual question answering (VQA) task requires recognizing many diverse visual concepts as the answer. These visual concepts contain rich structural semantic meanings, e.g., some concepts in VQA are highly related (e.g., red & blue), some of them are less relevant (e.g., red & standing). It is very natural for humans to efficiently learn concepts by utilizing their semantic meanings to concentrate on distinguishing relevant concepts and eliminate the disturbance of irrelevant concepts. However, previous works usually use a simple MLP to output visual concept as the answer in a flat label space that treats all labels equally, causing limitations in representing and using the semantic meanings of labels. To address this issue, we propose a novel visual recognition module named Dynamic Concept Recognizer (DCR), which is easy to be plugged in an attention-based VQA model, to utilize the semantics of the labels in answer prediction. Concretely, we introduce two key features in DCR: 1) a novel structural label space to depict the difference of semantics between concepts, where the labels in new label space are assigned to different groups according to their meanings. This type of semantic information helps decompose the visual recognizer in VQA into multiple specialized sub-recognizers to improve the capacity and efficiency of the recognizer. 2) A feature attention mechanism to capture the similarity between relevant groups of concepts, e.g., human-related group “chef, waiter” is more related to “swimming, running, etc.” than scene related group “sunny, rainy, etc.”. This type of semantic information helps sub-recognizers for relevant groups to adaptively share part of modules and to share the knowledge between relevant sub-recognizers to facilitate the learning procedure. Extensive experiments on several datasets have shown that the proposed structural label space and DCR module can efficiently learn the visual concept recognition and benefit the performance of the VQA model.

CaO-Al2O3-SiO2(CAS) glass ceramics were designed and prepared using a melt-quench approach. The coefficient of the thermal expansion (CTE) of the synthesized CAS (4.12 × 10−6 K−1) matched perfectly with that of the SiC ceramic (4.01 × 10−6 K−1). Thermal analysis of the CAS was conducted. Then the joining of the SiC ceramics by the CAS glass ceramics under various process parameters were conducted. The bonding temperature affects the fluidity of the CAS glass and the oxidation of the SiC substrate. The holding duration decides the infiltration of the CAS glass into the SiC substrate. The optimal bonding parameter is 1400 ℃/10 min and the corresponding highest shear strength of the SiC/CAS/SiC bonded joints in average was 56 MPa. Fracture observation was also conducted to help analyze the relationship between the interfacial microstructure and the joint strength. Finally, the formation mechanism of the SiC/CAS/SiC bonded joints was proposed.

Visual sign language recognition is an interesting and challenging problem. To create a discriminative representation, a hierarchical Grassmann covariance matrix (HGCM) model is proposed for sign description. Furthermore, a multi-temporal belief propagation (MTBP) based segmentation approach is presented for continuous sequence spotting. Concretely speaking, a sign is represented by multiple covariance matrices, followed by evaluating and selecting their most significant singular vectors. These covariance matrices are transformed into a more compact and discriminative HGCM, which is formulated on the Grassmann manifold. Continuous sign sequences can be recognized frame by frame using the HGCM model, before being optimized by MTBP, which is a carefully designed graphic model. The proposed method is thoroughly evaluated on isolated and synthetic and real continuous sign datasets as well as on HDM05. Extensive experimental results convincingly show the effectiveness of our proposed framework.

Monitoring of fuel element failure in a nuclear reactor is an important process to ensure safe operation of the nuclear reactor. It is feasible to detect fuel element rupture by analysing the radionuclides of fission products and activation products in the primary coolant. To identify the radionuclides in the primary coolant, the most convenient method to measure their activity concentrations is γ-ray spectrometry. A γ-ray spectral analysis method for real-time detection of fuel element failure is proposed in this paper. The method aims to implement a Gaussian smoothing processing for spectral data, extract peaks of spectral data through mathematical morphological transformation, determine left and right peak boundaries with a gradient descent algorithm and finally estimate net peak area with an image method. The method can rapidly recognize a designated key radionuclide from an obtained spectrum and extract peak information to meet the demands of real-time monitoring of fuel element failure in pressurized water reactors.

The explosive growth of digital images in video surveillance and social media has led to the significant need for efficient search of persons of interest in law enforcement and forensic applications. Despite tremendous progress in primary biometric traits (e.g., face and fingerprint) based person identification, a single biometric trait alone cannot meet the desired recognition accuracy in forensic scenarios. Tattoos, as one of the important soft biometric traits, have been found to be valuable for assisting in person identification. However, tattoo search in a large collection of unconstrained images remains a difficult problem, and existing tattoo search methods mainly focus on matching cropped tattoos, which is different from real application scenarios. To close the gap, we propose an efficient tattoo search approach that is able to learn tattoo detection and compact representation jointly in a single convolutional neural network (CNN) via multi-task learning. While the features in the backbone network are shared by both tattoo detection and compact representation learning, individual latent layers of each sub-network optimize the shared features toward the detection and feature learning tasks, respectively. We resolve the small batch size issue inside the joint tattoo detection and compact representation learning network via random image stitch and preceding feature buffering. We evaluate the proposed tattoo search system using multiple public-domain tattoo benchmarks, and a gallery set with about 300K distracter tattoo images compiled from these datasets and images from the Internet. In addition, we also introduce a tattoo sketch dataset containing 300 tattoos for sketch-based tattoo search. Experimental results show that the proposed approach has superior performance in tattoo detection and tattoo search at scale compared to several state-of-the-art tattoo retrieval algorithms., Comment: Technical Report (15 pages, 14 figures)

A calibration system was designed to meet the calibration requirement of the radioactive aerosal monitors. The system consists of a radioactive aerosol generation unit, a dilution and mixing unit, a sampling and measuring unit, a purification unit and an automatic control unit. The commonly-used α and β radioactive solutions Am(NO3)3 and CsCl were selected to prepared different concentrations of monodisperse radioactive aerosol. After testing the calibration system, it was determined that the measurement uncertainty of the α and β efficiency calibration factors taken by the system for the radioactive aerosol monitor was 2.8% and 2.6%, respectively.

Zero-shot learning (ZSL) has enjoyed great popularity in recent years due to its ability to recognize novel objects, where semantic information is exploited to build up relations among different categories. Traditional ZSL approaches usually focus on learning more robust visual-semantic embeddings among seen classes and directly apply them to the unseen classes without considering whether they are suitable. It is well known that domain gap exists between seen and unseen classes. In order to tackle such problem, we propose a novel adaptive metric learning approach to measure the compatibility between visual samples and class semantics, where class similarities are utilized to adapt the visual-semantic embedding to the unseen classes. Extensive experiments on four benchmark ZSL datasets show the effectiveness of the proposed approach.

Attributes are mid-level semantic properties of objects. Recent research has shown that visual attributes can benefit many typical learning problems in computer vision community. However, attribute learning is still a challenging problem as the attributes may not always be predictable directly from input images and the variation of visual attributes is sometimes large across categories. In this paper, we propose a unified multiplicative framework for attribute learning, which tackles the key problems. Specifically, images and category information are jointly projected into a shared feature space, where the latent factors are disentangled and multiplied to fulfil attribute prediction. The resulting attribute classifier is category-specific instead of being shared by all categories. Moreover, our model can leverage auxiliary data to enhance the predictive ability of attribute classifiers, which can reduce the effort of instance-level attribute annotation to some extent. By integrated into an existing deep learning framework, our model can both accurately predict attributes and learn efficient image representations. Experimental results show that our method achieves superior performance on both instance-level and category-level attribute prediction. For zero-shot learning based on visual attributes and human-object interaction recognition, our method can improve the state-of-the-art performance on several widely used datasets.

Although the conventional active appearance model (AAM) has achieved some success for face alignment, it still suffers from the generalization problem when be applied to unseen subjects and images. To deal with the generalization problem of AAM, we first reformulate the original AAM as sparsity-regularized AAM, which can achieve more compact/better shape and appearance priors by selecting nearest neighbors as the bases of the shape and appearance model. To speed up the fitting procedure, the sparsity in sparsity-regularized AAM is approximated by using the locality (i.e., K-nearest neighbor), and thus inducing the locality-constrained active appearance-model (LC-AAM). The LC-AAM solves a constrained AAM-like fitting problem with the K-nearest neighbors as the bases of shape and appearance model. To alleviate the adverse influence of inaccurate K-nearest neighbor results, the locality constraint is further embedded in the discriminative fitting method denoted as LC-DFM, which can find better K-nearest neighbor results by employing shape-indexed feature, and can also tolerate some inaccurate neighbors benefited from the regression model rather than the generative model in AAM. Extensive experiments on several datasets demonstrate that our methods outperform the state-of-the-arts in both detection accuracy and generalization ability.

In this paper, we present a new hashing method to learn compact binary codes for highly efficient image retrieval on large-scale datasets. While the complex image appearance variations still pose a great challenge to reliable retrieval, in light of the recent progress of Convolutional Neural Networks (CNNs) in learning robust image representation on various vision tasks, this paper proposes a novel Deep Supervised Hashing method to learn compact similarity-preserving binary code for the huge body of image data. Specifically, we devise a CNN architecture that takes pairs/triplets of images as training inputs and encourages the output of each image to approximate discrete values (e.g. $$+\,1$$/$$-\,1$$). To this end, the loss functions are elaborately designed to maximize the discriminability of the output space by encoding the supervised information from the input image pairs/triplets, and simultaneously imposing regularization on the real-valued outputs to approximate the desired discrete values. For image retrieval, new-coming query images can be easily encoded by forward propagating through the network and then quantizing the network outputs to binary codes representation. Extensive experiments on three large scale datasets CIFAR-10, NUS-WIDE, and SVHN show the promising performance of our method compared with the state-of-the-arts.

Expressive representations for characterizing face appearances are essential for accurate face detection. Due to different poses, scales, illumination, occlusion, etc, face appearances generally exhibit substantial variations, and the contents of each local region (facial part) vary from one face to another. Current detectors, however, particularly those based on convolutional neural networks, apply identical operations (e.g. convolution or pooling) to all local regions on each face for feature aggregation (in a generic sliding-window configuration), and take all local features as equally effective for the detection task. In such methods, not only is each local feature suboptimal due to ignoring region-wise distinctions, but also the overall face representations are semantically inconsistent. To address the issue, we design a hierarchical attention mechanism to allow adaptive exploration of local features. Given a face proposal, part-specific attention modeled as learnable Gaussian kernels is proposed to search for proper positions and scales of local regions to extract consistent and informative features of facial parts. Then face-specific attention predicted with LSTM is introduced to model relations between the local parts and adjust their contributions to the detection tasks. Such hierarchical attention leads to a part-aware face detector, which forms more expressive and semantically consistent face representations. Extensive experiments are performed on three challenging face detection datasets to demonstrate the effectiveness of our hierarchical attention and make comparisons with state-of-the-art methods.

Hereditary angioedema (HAE) is a rare and potentially life-threatening disease that affects an estimated 1 in 50,000 individuals worldwide. Berotralstat (BCX7353) is the only small molecule approved by the US Food and Drug Administration (FDA) for the prophylactic treatment of HAE attacks in patients 12 years and older. During the discovery of BCX7353, we also identified a novel series of small molecules containing a quaternary carbon as potent and orally bioavailable Plasma Kallikrein (PKal) inhibitors. Lead compound was identified as a potent inhibitor following a detailed lead optimization process that balanced the lipophilic efficiency (LipE) and pharmacokinetic (PK) profile.

Heavy metal contamination in agricultural soil and immobilization remediation have generated widespread concern in all areas of society. Sulfhydryl-functionalized materials as emerging amendments exhibit application potential, but the dose-effect relationship and immobilization mechanism are poorly understood. To understand the relationship between the immobilization effect and total sulfhydryl content, sulfhydryl-grafted palygorskite (SGP) with three sulfhydryl loading rates (0.88 mmol/g, 1.83 mmol/g, and 2.77 mmol/g) was prepared and characterized in the current study. The Cd immobilization efficiency and the dose-effect relationship were investigated via sorption in solutions, soil incubation, and field-scale wheat cultivation.

The Risk Analysis Index (RAI) for frailty is a rapid survey for comorbidities and performance status, which predicts mortality after general surgery. We aimed to validate the RAI in predicting outcomes after hepatopancreatobiliary surgery.Associations of RAI, determined in 162 patients prior to undergoing hepatopancreatobiliary surgery, with prospectively collected 30-day post-operative outcomes were analyzed with multivariate logistic and linear regression.Patients (age 62 ± 14, 51% female) had a median RAI of 7, range 0-25. With every unit increase in RAI, length of stay increased by 5% (95% CI: 2-7%), odds of ICU admission increased by 10% (0-20%), ICU length of stay increased by 21% (9-34%), and odds of discharge to a nursing facility increased by 8% (0-17%) (all P 0.05). Particularly in patients who suffered a first post-operative complication, RAI was associated with additional complications (1.6 unit increase in Comprehensive Complication Index per unit increase in RAI, P = 0.002). In a direct comparison in a subset of 74 patients, RAI and the ACS-NSQIP Risk Calculator performed comparably in predicting outcomes.While RAI and ACS-NSQIP Risk Calculator comparatively predicted short-term outcomes after HPB surgery, RAI has been specifically designed to identify frail patients who can potentially benefit from preoperative prehabilitation interventions.

Face attribute estimation has many potential applications in video surveillance, face retrieval, and social media. While a number of methods have been proposed for face attribute estimation, most of them did not explicitly consider the attribute correlation and heterogeneity (e.g., ordinal vs. nominal and holistic vs. local) during feature representation learning. In this paper, we present a Deep Multi-Task Learning (DMTL) approach to jointly estimate multiple heterogeneous attributes from a single face image. In DMTL, we tackle attribute correlation and heterogeneity with convolutional neural networks (CNNs) consisting of shared feature learning for all the attributes, and category-specific feature learning for heterogeneous attributes. We also introduce an unconstrained face database (LFW+), an extension of public-domain LFW, with heterogeneous demographic attributes (age, gender, and race) obtained via crowdsourcing. Experimental results on benchmarks with multiple face attributes (MORPH II, LFW+, CelebA, LFWA, and FotW) show that the proposed approach has superior performance compared to state of the art. Finally, evaluations on a public-domain face database (LAP) with a single attribute show that the proposed approach has excellent generalization ability., Comment: To appear in the IEEE Trans. Pattern Analysis and Machine Intelligence (final)

Attributes are widely used in different vision tasks. However, existing attribute resources are quite limited and most of them are not in large scale. Current attribute annotation process is generally done by human, which is expensive and time-consuming. In this paper, we propose a novel framework to perform effective attribute annotations. Based on the common knowledge that attributes can be shared among different classes, we leverage the benefits of transfer learning and active learning together to transfer knowledge from some existing small attribute databases to large-scale target databases. In order to learn more robust attribute models, attribute relationships are incorporated to assist the learning process. Using the proposed framework, we conduct extensive experiments on two large-scale image databases, i.e. ImageNet and SUN Attribute, where high quality automatic attribute annotations are obtained.

In indirectly driven inertial confinement fusion, a high-purity germanium detector is widely used in the calibration of various X-ray detectors as a quantitative spectrum detector for the irradiating X-ray. However, the intrinsic peak efficiency of the high-purity germanium detector, which is the foundation of its applications, has not been investigated in depth. In this work, an optimized data-processing method is developed to explore the intrinsic peak efficiency of the high-purity germanium detector, based on calibration experiments. The intrinsic peak efficiency of the detector is absolutely and accurately calibrated and simulated for X-ray energy in the range of 5.48–302.85 keV. The experimental and simulated results, which agree well, are analyzed and explained in detail. The efficiency curve obtained from the data reveals the rise, flat, and fall characters. In addition, the impact of the absorption edge, which is located at 11.10 keV, on the efficiency curve was found and explained in terms of the escape of the excited K α lines. This work will improve the calibration efficiency of various X-ray detectors based on the high-purity germanium detector, and help in advancing the quantitative understanding of the detection results in inertial confinement fusion.