Search

Due to the rich spatio-temporal visual content and complex multimodal relations, Video Question Answering (VideoQA) has become a challenging task and attracted increasing attention. Current methods usually leverage visual attention, linguistic attention, or self-attention to uncover latent correlations between video content and question semantics. Although these methods exploit interactive information between different modalities to improve comprehension ability, inter- and intra-modality correlations cannot be effectively integrated in a uniform model. To address this problem, we propose a novel VideoQA model called Cross-Attentional Spatio-Temporal Semantic Graph Networks (CASSG). Specifically, a multi-head multi-hop attention module with diversity and progressivity is first proposed to explore fine-grained interactions between different modalities in a crossing manner. Then, heterogeneous graphs are constructed from the cross-attended video frames, clips, and question words, in which the multi-stream spatio-temporal semantic graphs are designed to synchronously reasoning inter- and intra-modality correlations. Last, the global and local information fusion method is proposed to coalesce the local reasoning vector learned from multi-stream spatio-temporal semantic graphs and the global vector learned from another branch to infer the answer. Experimental results on three public VideoQA datasets confirm the effectiveness and superiority of our model compared with state-of-the-art methods. [ABSTRACT FROM AUTHOR]

Visual question answering (VQA) has gained increasing attention in both natural language processing and computer vision. The attention mechanism plays a crucial role in relating the question to meaningful image regions for answer inference. However, most existing VQA methods: 1) learn the attention distribution either from free-form regions or detection boxes in the image, which is intractable in answering questions about the foreground object and background form, respectively and 2) neglect the prior knowledge of human attention and learn the attention distribution with an unguided strategy. To fully exploit the advantages of attention, the learned attention distribution should focus more on the question-related image regions, such as human attention for both the questions, about the foreground object and background form. To achieve this, this article proposes a novel VQA model, called adversarial learning of supervised attentions (ALSAs). Specifically, two supervised attention modules: 1) free form-based and 2) detection-based, are designed to exploit the prior knowledge for attention distribution learning. To effectively learn the correlations between the question and image from different views, that is, free-form regions and detection boxes, an adversarial learning mechanism is implemented as an interplay between two supervised attention modules. The adversarial learning reinforces the two attention modules mutually to make the learned multiview features more effective for answer inference. The experiments performed on three commonly used VQA datasets confirm the favorable performance of ALSA. [ABSTRACT FROM AUTHOR]

These days, social media users tend to express their feelings through sharing images online. Capturing the emotions embedded in these social images involves great research challenges and practical values. Most existing works concentrate on extracting the visual feature from a global view, while ignoring the fact that visual objects are also rich in emotion. How to leverage the multilevel visual features to improve the sentiment analysis performance is important yet challenging. Besides, existing works view each social image as an independent sample while ignoring the rich correlations among social images, which may be helpful in detecting visual emotion. In this article, we propose a novel model called social relations-guided multiattention networks (SRGMANs) to incorporate both the multilevel (region-level and object-level) visual features of a single image and the correlations among multiple social images to conduct visual sentiment analysis. Specifically, we first construct a heterogeneous network consisting of various types of social relations and introduce a heterogeneous network embedding method to learn the network representation for each image. Then, two visual attention branches (region attention network and object attention network) are devised to extract emotional and discriminative visual features. For each branch, we design a self-attention module to capture the emotional dependencies among visual parts. Besides, a network-guided attention module is also designed in each branch to focus on more network-related emotional visual parts with the guidance of the topology information. Finally, the attended visual features from the two attention models, together with network representation features, are combined within a holistic framework to predict the sentiment of social images. Extensive experiments demonstrate the superiority of our model on three benchmark datasets. [ABSTRACT FROM AUTHOR]

In the circumstance of social big data, sentiment analysis is attracting increasing attention for its capacity in understanding individuals’ attitudes and feelings. Traditional sentiment analysis methods focus on single modality and become ineffective as enormous data are emerging on the social websites with multiple manifestations. In this article, multimodal learning approaches are proposed to capture the relations between image and text, which only stay at the region level and ignore the fact that the channels are also closely correlated with the semantic information. In addition, social images in the social platforms are closely connected by various types of relations, which are also conducice to sentiment classification but neglected by most existing works. In this article, we propose an attention-based heterogeneous relational model to improve the multimodal sentiment analysis performance by incorporating rich social information. Specifically, we propose a progressive dual attention module to capture the correlations between image and text, and then learn the joint image-text representation from the perspective of content information. A channel attention schema is proposed here to highlight semantically rich image channels and a region attention schema is further designed to highlight the emotional regions based on the attended channels. After that, we construct a heterogeneous relation network and extend graph convolutional network to aggregate the content information from social contexts as complements to learn high-quality representations of social images. Our proposal is thoroughly evaluated on two benchmark datasets, and experimental results demonstrate the superiority of the proposed model. [ABSTRACT FROM AUTHOR]

Learning the representation for social images has recently made remarkable achievements for many tasks, such as cross-modal retrieval and multilabel classification. However, since social images contain both multimodal contents (e.g., visual images and textual descriptions) and social relations among images, simply modeling the content information may lead to suboptimal embedding. In this paper, we propose a novel multimodal representation learning model for social images, that is, correlational multimodal variational autoencoder (CMVAE) via triplet network. Specifically, in order to mine the highly nonlinear correlation between the visual content and the textual content, a CMVAE is proposed to learn a unified representation for the multiple modalities of social images. Both common information in all modalities and private information in each modality are encoded for the representation learning. To incorporate the social relations among images, we employ the triplet network to embed multiple types of social links in the representation learning. Then, a joint embedding model is proposed to combine the social relations for representation learning of the multimodal contents. Comprehensive experiment results on four datasets confirm the effectiveness of our method in two tasks, namely, multilabel classification and cross-modal retrieval. Our method outperforms the state-of-the-art multimodal representation learning methods with significant improvement of performance. [ABSTRACT FROM AUTHOR]

Landmark retrieval is to return a set of images with their landmarks similar to those of the query images. Existing studies on landmark retrieval focus on exploiting the geometries of landmarks for visual similarity matches. However, the visual content of social images is of large diversity in many landmarks, and also some images share common patterns over different landmarks. On the other side, it has been observed that social images usually contain multimodal contents, i.e., visual content and text tags, and each landmark has the unique characteristic of both visual content and text content. Therefore, the approaches based on similarity matching may not be effective in this environment. In this paper, we investigate whether the geographical correlation among the visual content and the text content could be exploited for landmark retrieval. In particular, we propose an effective multimodal landmark classification paradigm to leverage the multimodal contents of social image for landmark retrieval, which integrates feature refinement and landmark classifier with multimodal contents by a joint model. The geo-tagged images are automatically labeled for classifier learning. Visual features are refined based on low rank matrix recovery, and multimodal classification combined with group sparse is learned from the automatically labeled images. Finally, candidate images are ranked by combining classification result and semantic consistence measuring between the visual content and text content. Experiments on real-world datasets demonstrate the superiority of the proposed approach as compared to existing methods. [ABSTRACT FROM PUBLISHER]

Image location prediction is used to estimate the geolocation where an image is taken, which is important for many image applications, such as image retrieval, image browsing, and organization. Since a social image contains heterogeneous contents, such as visual content and textual content, effectively incorporating these contents to predict location is nontrivial. Moreover, it is observed that image content patterns and the locations where they may appear correlate hierarchically. Traditional image location prediction methods mainly adopt a single-level architecture and assume images are independently distributed in geographical space, which is not directly adaptable to the hierarchical correlation. In this paper, we propose a geographically hierarchical bi-modal deep belief network (GH-BDBN) model, which is a compositional learning architecture that integrates multi-modal deep learning model with a non-parametric hierarchical prior model. GH-BDBN learns a joint representation capturing the correlations among different types of image content using a bi-modal DBN, with a geographically hierarchical prior over the joint representation to model the hierarchical correlation between image content and location. Then, an efficient inference algorithm is proposed to learn the parameters and the geographical hierarchical structure of geographical locations. Experimental results demonstrate the superiority of our model for image location prediction. [ABSTRACT FROM PUBLISHER]

With the availability of cheap location sensors, geotagging of images in online social media is very popular. With a large amount of geo-tagged social images, it is interesting to study how these images are shared across geographical regions and how the geographical language characteristics and vision patterns are distributed across different regions. Unlike textual document, geo-tagged social image contains multiple types of content, i.e., textual description, visual content, and geographical information. Existing approaches usually mine geographical characteristics using a subset of multiple types of image contents or combining those contents linearly, which ignore correlations between different types of contents, and their geographical distributions. Therefore, in this paper, we propose a novel method to discover geographical characteristics of geo-tagged social images using a geographical topic model called geographical topic model of social images (GTMSIs). GTMSI integrates multiple types of social image contents as well as the geographical distributions, in which image topics are modeled based on both vocabulary and visual features. In GTMSI, each region of the image would have its own topic distribution, and hence have its own language model and vision pattern. Experimental results show that our GTMSI could identify interesting topics and vision patterns, as well as provide location prediction and image tagging. [ABSTRACT FROM PUBLISHER]