MC-Net: Integrating Multi-Level Geometric Context for Two-View Correspondence Learning

Content-based web image retrieval based on the query-by-example (QBE) principle remains a challenging problem due to the semantic gap as well as the gap between a user's intent and the representativeness of a typical image query. In this article, we propose to address this problem by integrating query-related contextual information into an advanced query model to improve the performance of QBE-based web image retrieval. We consider both the local and global context of the query image. The local context can be inferred from the web pages and the click-through log associated with the query image, while the global context is derived from the entire corpus comprising all web images and the associated web pages. To effectively incorporate the local query context we propose a language modeling based approach to deal with the combined structured query representation from the contextual and visual information. The global query context is integrated by the multi-modal relevance model to “reconstruct” the query from the document models indexed in the corpus. In this way, the global query context is employed to address the noise or missing information in the query and its local context, so that a comprehensive and robust query model can be obtained. We evaluated the proposed approach on a representative product image dataset collected from the web and demonstrated that the inclusion of the local and global query contexts significantly improves the performance of QBE-based web image retrieval.

Context-based attention models achieve state-of-the-art results on constructing document representations. Current methods build document representations based on a trainable global context vector for all documents, while local contexts capturing document-specific information are ignored. Representing document context as a vector also restricts the model's capacity to capture complete semantic components of documents. In this work, we address these limitations by proposing novel attention-based approaches. We first propose a local and global context attention (LGCA) model, which constructs the context representations of a document as a combination of global and local contexts. The local context is used to capture local document-specific information. Furthermore, a multi-context attention (MCA) model is proposed to capture multiple local contexts within a document, thereby fusing the overall semantic information of documents. We conduct experiments on document-level sentiment classification tasks where extra user and product information is shown to be important. Experimental results indicate that our methods significantly outperform previous models with and without user and product information. It is also demonstrated that our model has great potential of handling extra information to improve document classification performance.

A text corpus typically contains two types of context information -- global context and local context. Global context carries topical information which can be utilized by topic models to discover topic structures from the text corpus, while local context can train word embeddings to capture semantic regularities reflected in the text corpus. This encourages us to exploit the useful information in both the global and the local context information. In this paper, we propose a unified language model based on matrix factorization techniques which 1) takes the complementary global and local context information into consideration simultaneously, and 2) models topics and learns word embeddings collaboratively. We empirically show that by incorporating both global and local context, this collaborative model can not only significantly improve the performance of topic discovery over the baseline topic models, but also learn better word embeddings than the baseline word embedding models. We also provide qualitative analysis that explains how the cooperation of global and local context information can result in better topic structures and word embeddings.

In contextual cueing tasks, participants can use a repeating local context to learn to detect the target, yet most contextual cueing studies have relied on repeating global context properties. We examined whether observers can use local context repetitions in a similar manner as they use global context repetitions. In addition, we examined how reward-predicting context features modulate the use of local and global contexts. Participants searched through contexts in which either the entire context configuration or only a local context around the target repeated, intermixed with novel contexts. Half of the context items appeared in a color signaling either low or high reward. We found that local context repetitions led to comparable benefits in response times and fixation count as global context repetitions did. Surprisingly, reward magnitude did not affect performance in local nor in global contexts. The results suggest that a local chunk of distractors can be used for context learning and attention guidance in a similar manner as the global context configuration. We suggest that the proportion of repeated and novel context trials is crucial for context learning and that our combination of locally and globally repeating contexts provided an environment that facilitated learning in both context types because it allowed predicting the target location from the context in most of the trials.

This article seeks to employ bibliometric analysis to offer a thorough picture of the research environment concerning local, global, and glocal contexts. Amidst the increasing globalization, it is imperative to deeply understand the interplay between local and global contexts and the "glocal" concept. This study investigates the current body of literature on these three areas by assessing patterns of publishing, trends in research, and collaborations among scientists. Using data from famous academic databases, we have found noteworthy keywords, notable authors, and esteemed publications pertaining to this topic. The research indicates a significant rise in the quantity of publications regarding local, global, and global contexts during the previous two decades. This research also illustrates a shift in focus from localized contextual examinations to a more inclusive approach that combines global and local perspectives. These findings are anticipated to offer scholars and practitioners a novel understanding of the dynamics of interaction between local, global, and glocal contexts. Moreover, these discoveries will be a significant reference for forthcoming investigations in this field.

Numerical phantoms are a common tool for the evaluation of registration and reconstruction algorithms. For applications concerning motion, dense deformation fields are of particular interest. Phantoms, however, are often described as surfaces and thus motion vectors can only be generated at these surfaces. In order to create dense motion fields, interpolation is required. A frequently used method for this purpose is the Parzen interpolator. However, with a high number of surface motion vectors and a high voxel count, its run time increases dramatically. In this paper, we investigate different methods to accelerate the creation of these motion fields using hierarchical sampling and the random ball cover. In the results, we show that a 64 3 volume can be sampled in less than one second with an error below 0.1 mm. Furthermore, we accelerate the interpolation of a 256 3 dense deformation field to only ˜. 5m inutes using the proposed methods from days with previous methods.

In this chapter, the authors report themes that emerged when a cross-cultural team of researchers involved in a virtual international community of practice (Global Social Justice in Education-GSJE) investigated reflections on activities focused on social justice in local and global contexts. The findings suggested that the activities elicited GSJE community members' understandings of the complexities of social justice associated with naming practices, privilege, and the arts within their own and across contexts. The authors discuss implications of the activities to advance diverse educators' understanding of social justice in global and local contexts. They also unpack the opportunities and challenges that resulted from the collaborative research process and the writing of this chapter completed by the international author team comprised of 11 education scholars from seven countries.

Enhancing context knowledge repositories with justifiable exceptions

Identification of transcription factor binding sites (TFBSs) is essential for revealing the rules of protein-DNA binding. Although some computational methods have been presented to predict TFBSs using epigenomic and sequence features, most of them ignore the common features among cross-cell types. It is still unclear to what extent the common features could help for this task. To this end, we proposed a new method (named Attention-augmented Convolutional Neural Network, or ACNN) to predict TFBSs. ACNN uses attention-augmented convolutional layers to capture global and local contexts in DNA sequences and employs the convolutional layers to capture features of histone modification markers. In addition, ACNN adopts the private and shared convolutional neural network (CNN) modules to learn specific and common features, respectively. To encourage the shared CNN module to learn the common features, adversarial training is applied in ACNN. The results on 253 ChIP-seq datasets show that ACNN outperforms other existing methods. The attention-augmented convolutional layers and adversarial training mechanism in ACNN can effectively improve the prediction performance. Moreover, in the case of limited labeled data, ACNN also performs better than a baseline method. We further visualize the convolution kernels as motifs to explain the interpretability of ACNN.

Twitter has attracted millions of users to share and disseminate most up-to-date information, resulting in large volumes of data produced everyday. However, many applications in Information Retrieval (IR) and Natural Language Processing (NLP) suffer severely from the noisy and short nature of tweets. In this paper, we propose a novel framework for tweet segmentation in a batch mode, called HybridSeg. By splitting tweets into meaningful segments, the semantic or context information is well preserved and easily extracted by the downstream applications. HybridSeg finds the optimal segmentation of a tweet by maximizing the sum of the stickiness scores of its candidate segments. The stickiness score considers the probability of a segment being a phrase in English (i.e., global context) and the probability of a segment being a phrase within the batch of tweets (i.e., local context). For the latter, we propose and evaluate two models to derive local context by considering the linguistic features and term-dependency in a batch of tweets, respectively. HybridSeg is also designed to iteratively learn from confident segments as pseudo feedback. Experiments on two tweet data sets show that tweet segmentation quality is significantly improved by learning both global and local contexts compared with using global context alone. Through analysis and comparison, we show that local linguistic features are more reliable for learning local context compared with term-dependency. As an application, we show that high accuracy is achieved in named entity recognition by applying segment-based part-of-speech (POS) tagging.

Emotion recognition plays a pivotal role in advancing Human-Computer Interaction (HCI) by enabling systems to understand and respond to human emotional states. Among various modalities, Speech Emotion Recognition (SER) stands out as a non-invasive, cost-effective, and temporally efficient approach for detecting emotions. This study leverages the RAVDESS dataset, which provides high-quality audio recordings for emotion classification. The proposed methodology involves preprocessing audio signals to remove noise, extracting temporal and spectral features in both time and frequency domains, and implementing machine learning models for multi-class emotion classification. The study evaluates and compares the performance of several classification models, including Random Forest (RF), Multilayer Perceptron (MLP), Support Vector Machine (SVM), Convolutional Neural Networks (CNN), and Decision Trees (DT). Experimental results demonstrate promising accuracy levels, highlighting the potential of these machine learning techniques in SER. This research contributes to the integration of SER within Brain-Computer Interfaces (BCI) and other emotion-aware applications, paving the way for enhanced interactive systems. Keywords – Speech Emotion Recognition -Machine Learning - Random Forest -Multilayer Perceptron - Support Vector Machine - Convolutional Neural Networks - Decision Tree - RAVDESS Dataset

Graph convolutional network – Long short term memory neural network- multi layer perceptron- Gaussian progress regression model: A new deep learning model for predicting ozone concertation

Irrespective of the success of the deep learning-based mixed-domain transfer learning approach for solving various Natural Language Processing tasks, it does not lend a generalizable solution for detecting misinformation from COVID-19 social media data. Due to the inherent complexity of this type of data, caused by its dynamic (context evolves rapidly), nuanced (misinformation types are often ambiguous), and diverse (skewed, fine-grained, and overlapping categories) nature, it is imperative for an effective model to capture both the local and global context of the target domain. By conducting a systematic investigation, we show that: (i) the deep Transformer-based pre-trained models, utilized via the mixed-domain transfer learning, are only good at capturing the local context, thus exhibits poor generalization, and (ii) a combination of shallow network-based domain-specific models and convolutional neural networks can efficiently extract local as well as global context directly from the target data in a hierarchical fashion, enabling it to offer a more generalizable solution.

This paper describes a hybrid object-based video coding scheme that achieves efficient compression by separating moving objects from stationary background and transmitting the shape, motion and residuals for each segmented object. In this scheme, a new content-based object segmentation algorithm is proposed, which does not assume any prior modeling of the objects being segmented. The binarization process, which finds large object regions, is based on a threshold function that calculates block histograms and takes image noise into account. The resultant binary mask is further processed using morphological operations. The motion vectors are estimated inside the change detection mask using block-matching method between two successive frames, and then the dense motion field is estimated using the motion vectors and the Horn-Schunck algorithm.

HLSK-CASMamba: hybrid large selective kernel and convolutional additive self-attention mamba for hyperspectral image classification