Sentiment Analysis of Images with Tensor Factorization

The rapid growth of edge data generated by mobile devices and applications deployed at the edge of the network has exacerbated the problem of information overload. As an effective way to alleviate information overload, recommender system can improve the quality of various services by adding application data generated by users on edge devices, such as visual and textual information, on the basis of sparse rating data. The visual information in the movie trailer is a significant part of the movie recommender system. However, due to the complexity of visual information extraction, data sparsity cannot be remarkably alleviated by merely using the rough visual features to improve the rating prediction accuracy. Fortunately, the convolutional neural network can be used to extract the visual features precisely. Therefore, the end-to-end neural image caption (NIC) model can be utilized to obtain the textual information describing the visual features of movie trailers. This paper proposes a trailer inception probabilistic matrix factorization model called Ti-PMF, which combines NIC, recurrent convolutional neural network, and probabilistic matrix factorization models as the rating prediction model. We implement the proposed Ti-PMF model with extensive experiments on three real-world datasets to validate its effectiveness. The experimental results illustrate that the proposed Ti-PMF outperforms the existing ones.

With the development of social platforms, people are more likely to use pictures to share their sentiments and opinions. With the development of deep learning, the current mainstream image sentiment analysis research mainly focuses on the use of high-level semantic sentiment features of images, and less on the use of low-level sentiment features such as colors, lines and so on. Aiming at the above problems, this paper proposes an image sentiment analysis model based on multi-level feature fusion (MLFF). Firstly, the convolution neural network is used to learn different levels of image features; Then the multi-level features are input into the bidirectional sequential neural network, and attention is introduced to fuse to generate multi-level fusion features; Finally, the multi-level fusion features are input to the full connection layer for classification. The experimental results show that the fusion model proposed in this paper can make effective use of multi-level image features and effectively improve the performance of image sentiment analysis.

An image is worth a thousand words, conveying information that goes beyond the mere visual content therein. In this paper, we study the intent behind social media images with an aim to analyze how visual information can facilitate recognition of human intent. Towards this goal, we introduce an intent dataset, Intentonomy, comprising 14K images covering a wide range of everyday scenes. These images are manually annotated with 28 intent categories derived from a social psychology taxonomy. We then systematically study whether, and to what extent, commonly used visual information, i.e., object and context, contribute to human motive understanding. Based on our findings, we conduct further study to quantify the effect of attending to object and context classes as well as textual information in the form of hashtags when training an intent classifier. Our results quantitatively and qualitatively shed light on how visual and textual information can produce observable effects when predicting intent. <sup xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">1</sup>

Recent years have seen a rapid growth in the number of fake news that are posted online. Fake news detection is very challenging since they are usually created to contain a mixture of false and real information and images that have been manipulated that confuses the readers. In this paper, we propose a multimodal system with the aim to differentiate between fake and real posts. Our system is based on a neural network and combines textual, visual and semantic information. The textual information is extracted from the content of the post, the visual one from the image that is associated with the post and the semantic refers to the similarity between the image and the text of the post. We conduct our experiments on three standard real world collections and we show the importance of those features on detecting fake news.

As mobile and chatbot-based shopping platforms continue to reshape online retail experiences, consumers are increasingly exposed to product information in sequential rather than simultaneous formats. Drawing on information foraging theory, we examine the marginal value consumers derive when textual and visual product information are presented sequentially. We conducted an online experiment (n = 86) with student sample to test whether different information presentation sequence (text first vs. image first) would lead to different perceived diagnosticity, product attitude, and purchase intention. We also examined whether this sequence effect differed between search (notebook and hanger) and experience (sofa and portable closet) products. Findings from mixed-effects regressions show that presenting textual information before visual information results in greater marginal gains in all three outcomes, particularly for experience products. These findings offer new insights into the cognitive dynamics of sequential information processing and practical implications for optimizing product presentation in online retail design.

We present an iterative and unsupervised learning approach for the speaker verification task. In conventional speaker verification, Probabilistic Linear Discriminant Analysis (PLDA) has been widely used as a supervised backend. However, PLDA requires fully labeled training data, which is often difficult to obtain in reality. To automatically retrieve the speaker labels of unlabeled training data, we propose to use the Affinity Propagation (AP) - a clustering method that takes pairwise data similarity as input - to generate the labels for the PLDA modeling. We further propose an iterative refinement strategy that incrementally updates the similarity input of the AP clustering with the previous iteration's PLDA scoring outputs. Moreover, we evaluate the performance of different PLDA scoring methods for the multiple enrollment task and show that the generalized hypothesis testing achieves the best results. Experiments were conducted on the NIST SRE 2010 and the 2014 i-vector challenge database. The results show that our proposed iterative and unsupervised PLDA model learning approach outperformed the cosine similarity baseline by 35% relatively.

As one of the most popular social media platforms, microblogs are ideal places for news propagation. In microblogs, tweets with both text and images are more likely to attract attention than text-only tweets. This advantage is exploited by fake news producers to publish fake news, which has a devasting impact on individuals and society. Thus, multimodal fake news detection has attracted the attention of many researchers. For news with text and image, multimodal fake news detection utilizes both text and image information to determine the authenticity of news. Most of the existing methods for multimodal fake news detection obtain a joint representation by simply concatenating a vector representation of the text and a visual representation of the image, which ignores the dependencies between them. Although there are a small number of approaches that use the attention mechanism to fuse them, they are not fine-grained enough in feature fusion. The reason is that, for a given image, there are multiple visual features and certain correlations between these features. They do not use multiple feature vectors representing different visual features to fuse with textual features, and ignore the correlations, resulting in inadequate fusion of textual features and visual features. In this paper, we propose a novel fine-grained multimodal fusion network (FMFN) to fully fuse textual features and visual features for fake news detection. Scaled dot-product attention is utilized to fuse word embeddings of words in the text and multiple feature vectors representing different features of the image, which not only considers the correlations between different visual features but also better captures the dependencies between textual features and visual features. We conduct extensive experiments on a public Weibo dataset. Our approach achieves competitive results compared with other methods for fusing visual representation and text representation, which demonstrates that the joint representation learned by the FMFN (which fuses multiple visual features and multiple textual features) is better than the joint representation obtained by fusing a visual representation and a text representation in determining fake news.

The identification and classification of lithofacies is key to understanding the heterogeneity of the reservoir. Traditional manual facies prediction using well log data are characterized by uncertainties and are often time consuming especially when working with large datasets. Machine learning provides a more efficient way of predicting facies when applied to large data. In this study we consider unsupervised learning approach: clustering and supervised learning approach: support vector machine for facies classification. Unsupervised learning was done using only raw and processed well logs parameters and the responses were grouped into various clusters based on similarities. Optimal number of clusters were selected from the elbow plot and dendogram. The supervised learning is done using well logs-raw and processed parameters. The targeted output was depofacies defined using core facies derived from core data. Both approaches showed good results with less uncertainty and bias when compared to already established facies defined from core data. The result from this process provides a more realistic input for generating facies models.

Recently, user generated multimedia contents (e.g. text, image, speech and video) on social media are increasingly used to share their experiences and emotions, for example, a tweet usually contains both texts and images. Compared to sentiment analysis of texts and images separately, the combination of text and image may reveal tweet sentiment more adequately. Motivated by this rationale, we propose a method based on convolutional neural networks (CNN) for multimedia (tweets consist of text and image) sentiment analysis. Two individual CNN architectures are used for learning textual features and visual features, which can be combined as input of another CNN architecture for exploiting the internal relation between text and image. Experimental results on two real-world datasets demonstrate that the proposed method achieves effective performance on multimedia sentiment analysis by capturing the combined information of texts and images.

Purpose:Automatic surgical instruction generation is a crucial part for intra-operative surgical assistance. However, understanding and translating surgical activities into human-like sentences are particularly challenging due to the complexity of surgical environment and the modal gap between images and natural languages. To this end, we introduce SIG-Former, a transformer-backboned generation network to predict surgical instructions from monocular RGB images.Methods:Taking a surgical image as input, we first extract its visual attentive feature map with a fine-tuned ResNet-101 model, followed by transformer attention blocks to correspondingly model its visual representation, text embedding and visual–textual relational feature. To tackle the loss-metric inconsistency between training and inference in sequence generation, we additionally apply a self-critical reinforcement learning approach to directly optimize the CIDEr score after regular training.Results:We validate our proposed method on DAISI dataset, which contains 290 clinical procedures from diverse medical subjects. Extensive experiments demonstrate that our method outperforms the baselines and achieves promising performance on both quantitative and qualitative evaluations.Conclusion:Our experiments demonstrate that SIG-Former is capable of mapping dependencies between visual feature and textual information. Besides, surgical instruction generation is still at its preliminary stage. Future works include collecting large clinical dataset, annotating more reference instructions and preparing pre-trained models on medical images.

Learning feature embedding directly from images without any human supervision is a very challenging and essential task in the field of computer vision and machine learning. Following the paradigm in supervised manner, most existing unsupervised metric learning approaches mainly focus on binary similarity in Euclidean space. However, these methods cannot achieve promising performance in many practical applications, where the manual information is lacking and data exhibits non-Euclidean latent anatomy. To address this limitation, we propose an Unsupervised Hyperbolic Metric Learning method with Hierarchical Similarity. It considers the natural hierarchies of data by taking advantage of Hyperbolic metric learning and hierarchical clustering, which can effectively excavate richer similarity information beyond binary in modeling. More importantly, we design a new loss function to capture the hierarchical similarity among samples to enhance the stability of the proposed method. Extensive experimental results on benchmark datasets demonstrate that our method achieves state-of-the-art performance compared with current unsupervised deep metric learning approaches.

Intelligent medicine is eager to automatically generate radiology reports to ease the tedious work of radiologists. Previous researches mainly focused on the text generation with encoder-decoder structure, while CNN networks for visual features ignored the long-range dependencies correlated with textual information. Besides, few studies exploit cross-modal mappings to promote radiology report generation. To alleviate the above problems, we propose a novel end-to-end radiology report generation model dubbed Self-Supervised dual-Stream Network (S3-Net). Specifically, a Dual-Stream Visual Feature Extractor (DSVFE) composed of ResNet and SwinTransformer is proposed to capture more abundant and effective visual features, where the former focuses on local response and the latter explores long-range dependencies. Then, we introduced the Fusion Alignment Module (FAM) to fuse the dual-stream visual features and facilitate alignment between visual features and text features. Furthermore, the Self-Supervised Learning with Mask(SSLM) is introduced to further enhance the visual feature representation ability. Experimental results on two mainstream radiology reporting datasets (IU X-ray and MIMIC-CXR) show that our proposed approach outperforms previous models in terms of language generation metrics.

Recent years have witnessed a great success of social media websites. Tag-based image search is an important approach to access the image content of interest on these websites. However, the existing ranking methods for tag-based image search frequently return results that are irrelevant or lacking in diversity. Most of the existing methods estimate the relevance of images by using tags and visual characteristics either separately or sequentially. The proposed system uses an approach that utilize simultaneously both visual information and textual information in real time to estimate the relevance of user tagged image. The method used to determine the relevance estimation is the hypergraph learning approach. The hypergraph is a generalization of a graph in which an edge in the hypergraph can be connected to any number of vertices. In the proposed method each social image can be represented by the bag-of-visual words and bag-of-textual words, which can be obtained from the textual content and visual content of the particular image. A hypergraph can be constructed in which the vertices represent the social images for ranking and the each hyperedge represents the visual words or tags that are obtained from the image. In the hypergraph learning scheme, both the visual content and tag information are taken into consideration at same time. Different from the method used by the traditional hypergraph, in the proposed system a social image hypergraph is constructed where vertices represent the images and hyperedges represent the visual or textual terms. The set of pseudo-positive images are used to achieve the learning, where the weight of hyperedges are updated throughout the learning process. Thus only the most relevant images are given to the user.

CE-DCVSI: Multimodal relational extraction based on collaborative enhancement of dual-channel visual semantic information

Flame spray pyrolysis (FSP) is a process used to synthesize nanoparticles through the combustion of an atomized precursor solution; this process has applications in catalysts, battery materials, and pigments. Current limitations revolve around understanding how to consistently achieve a stable flame and the reliable production of nanoparticles. Machine learning and artificial intelligence algorithms that detect unstable flame conditions in real time may be a means of streamlining the synthesis process and improving FSP efficiency. In this study, the FSP flame stability is first quantified by analyzing the brightness of the flame’s anchor point. This analysis is then used to label data for both unsupervised and supervised machine learning approaches. The unsupervised learning approach allows for autonomous labeling and classification of new data by representing data in a reduced dimensional space and identifying combinations of features that most effectively cluster it. The supervised learning approach, on the other hand, requires human labeling of training and test data but is able to classify multiple objects of interest (such as the burner and pilot flames) within the video feed. The accuracy of each of these techniques is compared against the evaluations of human experts. Both the unsupervised and supervised approaches can track and classify FSP flame conditions in real time to alert users of unstable flame conditions. This research has the potential to autonomously track and manage flame spray pyrolysis as well as other flame technologies by monitoring and classifying the flame stability.