Open-set face identification with index-of-max hashing by learning

Motion trajectory recognition is important for characterizing the moving property of an object. The speed and accuracy of trajectory recognition rely on a compact and discriminative feature representation, and the situations of varying rotation, scaling and translation has to be specially considered. In this paper we propose a novel feature extraction method for trajectories. Firstly a trajectory is represented by a proposed point context, which is a rotation-scale-translation (RST) invariant shape descriptor with a flexible tradeoff between computational complexity and discrimination, yet we prove that it is a complete shape descriptor. Secondly, the shape context is nonlinearly mapped to a subspace by kernel nonparametric discriminant analysis (KNDA) to get a compact feature representation, and thus a trajectory is projected to a single point in a low-dimensional feature space. Experimental results show that, the proposed trajectory feature shows encouraging improvement than state-of-art methods.

Dimensionality reduction is of great importance which aims at reducing the spectral dimensionality while keeping the desirable intrinsic structure information of hyperspectral images. Tensor analysis which can retain both spatial and spectral information of hyperspectral images has caused more and more concern in the field of hyperspectral images processing. In general, a desirable low dimensionality feature representation should be discriminative and compact. To achieve this, a tensor discriminant analysis model via compact feature representation (TDA-CFR) was proposed in this paper. In TDA-CFR, the traditional linear discriminant analysis was extended to tensor space to make the resulting feature representation more informative and discriminative. Furthermore, TDA-CFR redefines the feature representation of each spectral band by employing the tensor low rank decomposition framework which leads to a more compact representation.

Compact feature representation of person image is important for person re-identification (Re-ID) task. Recently, part-based representation models have been widely studied for extracting the more compact and robust feature representation for person image to improve person Re-ID results. However, existing part-based representation models mostly extract the features of different parts independently which ignore the spatial relationship information among different parts. To address this issue, in this paper we propose a novel deep learning framework, named Part-based Hierarchical Graph Convolutional Network (PH-GCN) for person Re-ID problem. Given a person image, PH-GCN first constructs a hierarchical graph to represent the spatial relationships among different parts. Then, both local and global feature learning is achieved by the feature information passing in PH-GCN, which takes the information of other parts into account for part feature representation. Finally, a perceptron layer is adopted for the final person part label prediction and re-identification. The proposed framework provides a general solution that integrates <i>local</i>, <i>global</i> and <i>structural</i> feature learning simultaneously in a unified end-to-end network representation and learning. Extensive experiments on several widely used benchmark datasets demonstrate the effectiveness and benefits of the proposed PH-GCN approach for person Re-ID task.

Modern face recognition systems leverage datasets containing images of hundreds of thousands of specific individuals' faces to train deep convolutional neural networks to learn an embedding space that maps an arbitrary individual's face to a vector representation of their identity. The performance of a face recognition system in face verification (1:1) and face identification (1:N) tasks is directly related to the ability of an embedding space to discriminate between identities. Recently, there has been significant public scrutiny into the source and privacy implications of large-scale face recognition training datasets such as MS-Celeb-1M and MegaFace, as many people are uncomfortable with their face being used to train dual-use technologies that can enable mass surveillance. However, the impact of an individual's inclusion in training data on a derived system's ability to recognize them has not previously been studied. In this work, we audit ArcFace, a state-of-the-art, open source face recognition system, in a large-scale face identification experiment with more than one million distractor images. We find a Rank-1 face identification accuracy of 79.71% for individuals present in the model's training data and an accuracy of 75.73% for those not present. This modest difference in accuracy demonstrates that face recognition systems using deep learning work better for individuals they are trained on, which has serious privacy implications when one considers all major open source face recognition training datasets do not obtain informed consent from individuals during their collection.

Recently, unsupervised Hashing has attracted much attention in the machine learning and information retrieval communities, due to its low storage and high search efficiency. Most of existing unsupervised Hashing methods rely on the local semantic structure of the data as the guiding information, requiring to preserve such semantic structure in the Hamming space. Thus, how to precisely represent the local structure of the data and Hashing code s becomes the key point to success. This study proposes a novel Hashing method based on self-supervised learning. Specifically, it is proposed to utilize the contrast learning to acquire a compact and accurate feature representation for each sample, and then a semantic structure matrix can be constructed for representing the similarity between samples. Meanwhile, a new loss function is proposed to preserve the semantic information and improve the discriminative ability in the Hamming space, by the spirit of the instance discrimination method proposed recently. The proposed framework is end-to-end trainable. Extensive experiments on two large-scale image retrieval data sets show that the proposed method can significantly outperform current state-of-the-art methods.

Bilateral symmetry is a facial feature that plays an important role in the aesthetic judgments of faces. The extent to which symmetry contributes to the identification of faces is less clear. We investigated the relationship between facial asymmetry and identity using synthetic face stimuli where the geometric identity of the face can be precisely controlled. Thresholds for all observers were 2 times lower for discriminating facial asymmetry than they were for discriminating facial identity. The advantage for discriminating asymmetrical forms was not observed using nonface shape stimuli, suggesting this advantage is face-specific. Moreover, asymmetry thresholds were not affected when faces were either inverted or constructed about a nonmean face. These results, taken together, suggest that facial asymmetry is a characteristic that we are exquisitely sensitive to, and that may not contribute to face identification. This conclusion is consistent with neuroimaging evidence that suggests that face symmetry and face identity are processed by different neural mechanisms.

Person knowledge shapes face identity perception

&lt;p class="Abstract"&gt;Face identification is amongst the most efficacious and extensive applications in biometrics involving extraction and locating facial features. With identification being monotonous task attributable to reliance on parameters like varied cameras, fluctuating backgrounds, and exposure to the environment in which an individual is present. Thermal imaging is endeavoring to resolve the accuracy issue of apparent imaging, such as lighting and brightness intensity, among all biometric variables. This paper presents a study of thermal imaging and effective methods involved in the feature extraction process for facial features with thermal imaging under the influence of varied noise. A novel face dataset is created TID comprising 27 thermal images and its corresponding visual band image using Fluke 480 Ti Pro camera. The study analyses detection efficiency of six feature extraction techniques in visible and thermal bands in facial features identification. Also, the influence of noise in the thermal band within the region of interest using feature points FIN, FOUT has been estimated. Throughout TID dataset, ORB extraction technique has been able to identify strongest inlier features FIN to a maximum extent with detection around the nose, eyes, and mouth. Further, results indicate feature detection in thermal images being invariant to effect of noise for detecting facial features.&lt;/p&gt;

People prioritize diagnostic features in classification tasks. However, it is not clear whether this priority is fixed or is flexibly applied depending on the specific classification decision, or how feature use behavior contributes to individual differences in performance. Here we examined whether flexibility in features used in a face identification task supports face recognition ability. In Experiment 1, we show that the facial features most useful for identification vary-to a surprising degree-depending on the specific face identity comparison at hand. While the ears and eyes were the most diagnostic for face identification in general, they were the most diagnostic feature for just 22% and 14% of identity decisions, respectively. In three subsequent experiments, we find that flexibility in feature use contributes to an individual's face identity matching ability. Higher face identification accuracy was associated with being aware of (Experiments 2 and 4) and attending to (Experiments 3 and 4) the most diagnostic features for a specific facial comparison. This conferred an enhanced benefit relative to focusing on features that were diagnostic of face identity decisions in general (Experiment 4). We conclude that adaptability in information sampling supports face recognition ability and discuss theoretical and applied implications. (PsycInfo Database Record (c) 2024 APA, all rights reserved).

Due to the high dimensionality and high data redundancy of hyperspectral remote sensing images, it is difficult to maintain the nonlinear structural relationship in the dimensionality reduction representation of hyperspectral data. In this paper, a feature representation method based on high order contractive auto-encoder with nuclear norm constraint (CAE-HNC) is proposed. By introducing Jacobian matrix in the CAE of the nuclear norm constraint, the nuclear norm has better sparsity than the Frobenius norm and can better describe the local low dimension of the data manifold. At the same time, a second-order penalty term is added, which is the Frobenius norm of the Hessian matrix expressed in the hidden layer of the input, encouraging a smoother low-dimensional manifold geometry of the data. The experiment of hyperspectral remote sensing image shows that CAE-HNC proposed in this paper is a compact and robust feature representation method, which provides effective help for the ground object classification and target recognition of hyperspectral remote sensing image.

The number of protein families has been estimated to be as small as 1000. Recent study shows that the growth in discovery of novel structures that are deposited into PDB and the related rate of increase of SCOP categories are slowing down. This indicates that the protein structure space will be soon covered and thus we may be able to derive most of remaining structures by using the known folding patterns. Present tertiary structure prediction methods behave well when a homologous structure is predicted, but give poorer results when no homologous templates are available. At the same time, some proteins that share twilight-zone sequence identity can form similar folds. Therefore, determination of structural similarity without sequence similarity would be beneficial for prediction of tertiary structures. The proposed PFRES method for automated protein fold classification from low identity (<35%) sequences obtains 66.4% and 68.4% accuracy for two test sets, respectively. PFRES obtains 6.3-12.4% higher accuracy than the existing methods. The prediction accuracy of PFRES is shown to be statistically significantly better than the accuracy of competing methods. Our method adopts a carefully designed, ensemble-based classifier, and a novel, compact and custom-designed feature representation that includes nearly 90% less features than the representation of the most accurate competing method (36 versus 283). The proposed representation combines evolutionary information by using the PSI-BLAST profile-based composition vector and information extracted from the secondary structure predicted with PSI-PRED. The method is freely available from the authors upon request.

Motion trajectory recognition is one of the most important means to determine the identity of a moving object. A compact and discriminative feature representation method can improve the trajectory recognition accuracy. This paper presents an efficient framework for action recognition using a three-dimensional skeleton kinematic joint model. First, we put forward a rotation-scale-translation-invariant shape descriptor based on point context (PC) and the normal vector of hypersurface to jointly characterize local motion and shape information. Meanwhile, an algorithm for extracting the key trajectory based on the confidence coefficient is proposed to reduce the randomness and computational complexity. Second, to decrease the eigenvalue decomposition time complexity, a tensor shape descriptor (TSD) based on PC that can globally capture the spatial layout and temporal order to preserve the spatial information of each frame is proposed. Then, a multilinear projection process is achieved by tensor dynamic time warping to map the TSD to a low-dimensional tensor subspace of the same size. Experimental results show that the proposed shape descriptor is effective and feasible, and the proposed approach obtains considerable performance improvement over the state-of-the-art approaches with respect to accuracy on a public action dataset.

Using unlabeled data in a sparse-coding framework for human activity recognition

Semi-supervised learning (SSL), as one of the dominant methods, aims at leveraging the unlabeled data to deal with the annotation dilemma of supervised learning, which has attracted much attentions in the medical image segmentation. Most of the existing approaches leverage a unitary network by convolutional neural networks (CNNs) with compulsory consistency of the predictions through small perturbations applied to inputs or models. The penalties of such a learning paradigm are that (1) CNN-based models place severe limitations on global learning; (2) rich and diverse class-level distributions are inhibited. In this paper, we present a novel CNN-Transformer learning framework in the manifold space for semi-supervised medical image segmentation. First, at intra-student level, we propose a novel class-wise consistency loss to facilitate the learning of both discriminative and compact target feature representations. Then, at inter-student level, we align the CNN and Transformer features using a prototype-based optimal transport method. Extensive experiments show that our method outperforms previous state-of-the-art methods on three public medical image segmentation benchmarks.

The runtime and accuracy of interconnect parasitic extraction are becoming increasingly crucial for integrated circuit design in advanced manufacturing processes. In this study, we propose a novel method of capacitance matching that maps low-level features to high-level spaces, which reduces feature dimensions without losing essential information and provides a compact form for the geometric features of 2-D patterns in full-chip capacitance extraction. Furthermore, we are introducing a creative labeling strategy that eliminates the requirement for separate task-specific heads or different input representations. This innovative approach enables simultaneous data processing for both total and coupling capacitance tasks, leading to a significant reduction of complexities. Our experiments demonstrate that our entire feature representation and pattern-matching algorithm delivers exceptional accuracy, improved runtime, providing an efficient solution for large-scale capacitance extraction.