Enhancing person re-identification with distance fusion: A comparative study on multiple datasets

Person re-identification remains a critical conundrum of intelligent video surveillance system, which intends to query pedestrians with the same identity. It is of great significance to extract features with sharp discrimination and robustness, especially for images captured in complex scenes, such as illumination variance, different pose and viewpoints. In this paper, we propose a normalized distance aggregation strategy, which integrates three discriminative pedestrian feature extraction models, i.e., low-level local maximal occurrence (LOMO), mid-level salient color names based color descriptor (SCNCD), and high-level feature fusion net (FFN). We utilize each feature descriptor to train two distance metric learning models, including large-scale similarity learning (LSSL) and cross-view quadratic discriminant analysis (XQDA), respectively. Accordingly, the ultimate distance is calculated as the sum of six optimized distance metrics by the min-max normalization with respective weights. In experiments, comprehensive evaluation results indicate that our framework gains superior performance with robustness to illumination, viewpoint as well as pose changes, and exceeds the existing methods on the public dataset VIPeR.

Person re-identification is one of the hot topics in computer vision. How to design a robust feature representation to identify pedestrians is a key problem for person re-identification. In this paper, a feature representation based on Multi-Statistics Cascade on Pyramid (MSCP) is proposed for person re-identification. The MSCP feature is composed of deep PCA network feature and hand-crafted features of Local Maximal Occurrence (LOMO) feature and color correlogram. MSCP can characterize the pedestrian images precisely from both global and local views. The Cross-view Quadratic Discriminant Analysis (XQDA) is employed to learn the distance metric of MSCP features. And then a novel re-identification method based on MSCP and XQDA is achieved. Experimental results on VIPeR Dataset demonstrate that our proposed method can achieve superior identification performance compared with six state-of-art methods.

Person re-identification is an important task of matching pedestrians across non-overlapping camera views. In this paper, we exploit a weighted feature descriptor for person re-identification. We firstly compute the weights on the superpixel level via graph-based manifold ranking algorithm, then integrate the computed weights into a patch-based feature descriptor, named local maximal occurrence. Finally, the weighted descriptors are fed into a top-push distance learning to mitigate the cross-view gaps. We evaluate the proposed method on three benchmark datasets iLIDS-VID, PRID 450S and VIPeR. The promising experimental results demonstrate the effectiveness of the proposed method comparing with the state-of-the-arts.

Person re-identification (re-id) is an important task in video surveillance. It is challenging due to the appearance of the person varying a wide range across non-overlapping camera views. In recent years, attention-based models are introduced to learn discriminative representation. In this paper, we consider the attention selection in a natural way as like human moving attention on different parts of the visual field for person re-id. In concrete, we propose a Recurrent Deep Attention Network (RDAN) with an attention selection mechanism based on reinforcement learning. The proposed RDAN aims to progressively observe the identity-sensitive regions to build up the representation of individuals. Extensive experiments on three person reid benchmarks Market-1501, DukeMTMC-reID, and CUHK03- NP demonstrate the proposed method can achieve competitive performance.

The pervasive issue of online sexism continues to pose significant challenges, fostering environments characterized by toxicity and perpetuating harmful societal norms. In response, this paper presents an approach for the discovery of sexist statements employing convolutional neural networks (CNNs), Word Embeddings, and data augmentation techniques. Through the fusion of CNNs’ capacity for hierarchical feature extraction with the semantic representations afforded by Word Embeddings, our method achieves exemplary discrimination performance. Additionally, the incorporation of data augmentation enriches the training dataset, thereby augmenting model generalization and resilience. Empirical evaluation on a larger dataset of statements demonstrates the efficacy of our approach, surpassing many baseline approaches in terms of discovery accuracy, precision, recall and F1-score.

Many features have been proposed to improve the accuracy of person re-identification. Due to the illumination and viewpoint changes between different cameras, individual feature is less discriminative to separate different persons. In this paper, we propose a saliency-weighted feature descriptor and global-local fusion optimization for person re-identification. Firstly, the weights on pixels are calculated via saliency detection method, then the computed weights are integrated into local maximal occurrence (LOMO) feature descriptor. Secondly, the saliency weights are used to update the metric learning distance in training so that we can learn a new metric matrix for testing. And then, the whole person image is divided into upper and lower halves. A novel global-local fusion method is proposed to combine local and global regions together in the most appropriate way. After that an optimization algorithm is proposed to learn the weights among upper half, lower half and the whole image. According to those weights, a final fused distance is obtained. Experimental results show that the proposed method outperforms many state-of-the-art person re-identification methods.

Deep and low-level feature based attribute learning for person re-identification

Person re-identification is a challenging retrieval task that requires matching a person's acquired image across non-overlapping camera views. In this paper we propose an effective approach that incorporates both the fine and coarse pose information of the person to learn a discriminative embedding. In contrast to the recent direction of explicitly modeling body parts or correcting for misalignment based on these, we show that a rather straightforward inclusion of acquired camera view and/or the detected joint locations into a convolutional neural network helps to learn a very effective representation. To increase retrieval performance, re-ranking techniques based on computed distances have recently gained much attention. We propose a new unsupervised and automatic re-ranking framework that achieves state-of-the-art re-ranking performance. We show that in contrast to the current state-of-the-art re-ranking methods our approach does not require to compute new rank lists for each image pair (e.g., based on reciprocal neighbors) and performs well by using simple direct rank list based comparison or even by just using the already computed euclidean distances between the images. We show that both our learned representation and our re-ranking method achieve state-of-the-art performance on a number of challenging surveillance image and video datasets. Code is available at https://github.com/pse-ecn.

In recent years, convolutional neural network (CNN) has been increasingly considered as a promising technology for military and homeland security applications. The fusion of CNN and Support vector machine (SVM), a popular traditional machine learning approach, has received intensive attention in the field of synthetic aperture radar (SAR) automatic target recognition (ATR). This paper, firstly, discusses the effects of some preprocessing and image enhancement methods on the performance of SAR ATR, starting with the pre-trained AlexNet in a transfer-learning based approach. Secondly, the architecture of AlexNet is modified to form a new model suitable for SAR ATR. Finally, we propose a hybrid model associated with the success of the learning feature of our CNN model and the ability of SVM to process high-dimensional dataset effectively. To evaluate the proposed method, experiments are performed on the Moving and Stationary Target Acquisition and Recognition (MSTAR) public database. The comparative results demonstrate that these preprocessing and enhancement methods prior to the deep-learning process are not necessary since the feature representation ability of AlexNet is already powerful. Furthermore, experimental results on the benchmark MSTAR dataset illustrate the effectiveness of the proposed new model. On classification of ten-class targets, the commonly used translation augmentation for training data has been performed. By combining the CNN and SVM, the classification accuracy percentages can be slightly improved for our proposed new model.

To overcome the shortcomings of traditional manual counting methods, which are labor-intensive, resource-consuming, and inefficient, this study introduces a computer-based counting model. This model integrates convolutional neural networks (CNNs) with Transformer networks to efficiently recognize and count specific target objects in large-scale data scenarios. This approach leverages CNNs for local feature extraction and incorporates Transformer networks to capture long-range global information, achieving a synergistic effect. The methodology includes key steps such as “CNN for feature extraction and Transformer for global attention.” The experiment outcomes show that the model has an average absolute error of 10.13, a root mean square error of 12.08, an average counting accuracy of 98.6%, a peak signal-to-noise ratio of 23.75, a structural similarity of 0.933, a coefficient of determination of 0.901, an average counting time of about 6.58ms per image, and a parameter count of 3.21 in target counting. It can also recognize and respond well to high complexity scenes while maintaining high accuracy. Compared to the CNN model, the research model reduces the error rate by 13.4%, indicating that the fusion of CNN and Transformer networks is effective in object counting for computer vision tasks. This result indicates that the model integrating convolutional neural networks and fully self attention networks can be well applied to computer recognition and object counting.

Person re-identification is an important task in video surveillance systems. It can be formally defined as establishing the correspondence between images of a person taken from different cameras at different times. In this paper, we present a two stream convolutional neural network where each stream is a Siamese network. This architecture can learn spatial and temporal information separately. We also propose a weighted two stream training objective function which combines the Siamese cost of the spatial and temporal streams with the objective of predicting a person's identity. We evaluate our proposed method on the publicly available PRID2011 and iLIDS-VID datasets and demonstrate the efficacy of our proposed method. On average, the top rank matching accuracy is 4% higher than the accuracy achieved by the cross-view quadratic discriminant analysis used in combination with the hierarchical Gaussian descriptor (GOG+XQDA), and 5% higher than the recurrent neural network method.

This paper proposes a combined framework of CNN+RFC to brain tumor categorization/classification using MRI (Magnetic-Resonance Imaging) images, which combines both CNN (Convolution Neural Networks) and RFC (Random Forest Classification). Preprocessing, Feature bring-out, and Categorization are the three phases of the proposed framework. In the first step, we use the Gaussian Filter Method on the data set then we combine the original data set with processed data in parallel. The feature extraction of magnetic resonance imaging was performed automatically by CNN in the second step. We also called such a type of process in this paper as non-hand-crafted feature extraction. Several classification algorithms, including RFC (Random Forest Classifier), KNN (K-Nearest Neighbor Classifier), DT (Decision Tree Classifier), SVM (Support Vector Machine Classifier), and NB (Naïve Bayes Classifier), are used in the final step. The extracted features from the CNN model are then given to the classifier algorithms, which predict Glioma tumor, Pituitary tumor, Meningioma tumor, and no tumor as a result of the testing data set. Experiments are carried out on an open data set of images selected for classification from the Kaggle databases. This data set is very complex since it contains images of brain tumor with different angles and different depths. We don't alter this data set at all. We make a separate CSV file that contains testing images' name and their specification. Using this proposed approach, we were able to achieve 99.61% accuracy on the training data set, 92.16% on the validation data, and 71.2% on the CSV/testing data.

The fusion of convolutional neural networks (CNNs) and vision transformers (ViTs) is a powerful strategy for remote sensing scene classification (RSSC), leveraging their complementary strengths in local texture and global context modeling. To fully exploit these complementary strengths for addressing the inter-class similarity and high intra-class variability caused by the complex spatial arrangements of RS scenes, this work introduces the hierarchically aligned bidirectional CNN-Transformer network (HAB-Net), which fosters deeper, two-way integration through two novel components. First, Hierarchical Attention Gating (HAG) distills multi-level attention from the ViT into spatial gates, compelling the CNN to focus on semantically critical regions. In turn, CNN-driven Feedback Attention (CFA) completes the loop by feeding these enhanced, detail-rich CNN features back into the ViT, refining its tokens via cross-attention. Ultimately, a dual-stream head merges these mutually reinforced features for scene classification. Extensive experiments on the UCM, AID, and NWPU-RESISC45 benchmarks demonstrate that HAB-Net achieves state-of-the-art performance. Ablation studies confirm the indispensable contributions of both HAG and CFA, validating the effectiveness of the proposed deep bidirectional integration strategy.

In an era where COVID-19's varied radiological presentations challenge diagnostic precision, this paper introduces a novel fusion of Convolutional Neural Networks (CNN) and Long Short-Term Memory (LSTM) models to refine detection capabilities. The paper capitalizes on an expansive radiography database, utilizing lung segmentation and data augmentation to bolster the training set. Advanced CNN models extract salient features, which are then classified through meticulously optimized machine learning algorithms. The synergy between diverse CNN architectures and Bayesian Optimization markedly enhances hyperparameter tuning, culminating in a significant uplift in diagnostic accuracy. The integration of LSTM models further allows for nuanced severity assessments, paving the way for more personalized and effective pandemic management. This research heralds a new frontier in medical diagnostics, promising a leap in the accuracy of pandemic detection.

Fusion of multivariate EEG signals for schizophrenia detection using CNN and machine learning techniques