Determining Attention Mechanism for Visual Sentiment Analysis of an Image using SVM Classifier in Deep learning based Architecture

Das, Priyanka; Ghosh, Anupam; Majumdar, Rana

doi:10.1109/icrito48877.2020.9197899

Cited by 12 publications

(6 citation statements)

References 9 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In the future, we plan to use the state-of-the-art attention mechanism [16] or object detection systems [50][51][52] to retrieve the corresponding affective regions. en, we will combine the whole image and the affective regions to obtain better performance and more powerful interpretability.…”

Section: Discussionmentioning

confidence: 99%

“…Some state-of-the-art methods employed CNN to complete image sentiment analysis. Das et al [16] proposed a deep learning model including an attention mechanism for focusing local regions and determining the required sentiment. She et al [17] proposed a model called weakly supervised coupled network (WSCNet) that aims to automatically select relevant regions to reduce the burden of sentiment annotation and improve performance.…”

Section: Related Workmentioning

confidence: 99%

“…To align image regions for gaining spatial invariance and learning strongly localized features, Durand et al [19] designed a new method called weakly supervised learning of deep ConvNets for image classification, pointwise localization, and segmentation (WILDCAT). Evidently, these weakly supervised methods [16][17][18][19] are dedicated to easing the annotation burden. Similarly, Sun et al [20] discovered the affective regions via a deep network.…”

Section: Related Workmentioning

confidence: 99%

“…Summarily, the above methods have achieved evident progress in the field of image sentiment analysis. Early works [16][17][18][19][20][21][22][23] focused on the analysis of local regions in images rather than the whole image. Most of them require massive high-quality data to train a robust model.…”

Section: Related Workmentioning

confidence: 99%

See 3 more Smart Citations

Image Sentiment Analysis via Active Sample Refinement and Cluster Correlation Mining

Zhang

Shi

Hou

et al. 2022

Computational Intelligence and Neuroscience

View full text Add to dashboard Cite

Training an effective image sentiment analysis model using high-quality samples and the implicit cross-modal semantics among heterogeneous features is still challenging. To address this problem, we propose an active sample refinement (ASR) strategy to obtain sufficient high-quality images with definite sentiment semantics. We mine the cluster correlation among the heterogeneous SENet features. Discriminative cross-modal semantics is generated to train an effective but robust image classifier. Ensemble learning is employed to further boost performance. Our method outperforms other competitive baselines, demonstrating its effectiveness and robustness. Meanwhile, the ASR strategy is a useful supplement to the current data augmentation method.

show abstract

Section: Discussionmentioning

confidence: 99%

Section: Related Workmentioning

confidence: 99%

Section: Related Workmentioning

confidence: 99%

Section: Related Workmentioning

confidence: 99%

See 2 more Smart Citations

Image Sentiment Analysis via Active Sample Refinement and Cluster Correlation Mining

Zhang

Shi

Hou

et al. 2022

Computational Intelligence and Neuroscience

View full text Add to dashboard Cite

show abstract

“…6 Papiya Das et al [49] SVM classification layer was used on deep CNN architecture. On various visual datasets, the accuracies were 65.89% and 68.67%.…”

Section: By Incorporating Label Informationmentioning

confidence: 99%

Visual Sentiment Analysis Using Deep Learning Models with Social Media Data

et al. 2022

View full text Add to dashboard Cite

Analyzing the sentiments of people from social media content through text, speech, and images is becoming vital in a variety of applications. Many existing research studies on sentiment analysis rely on textual data, and similar to the sharing of text, users of social media share more photographs and videos. Compared to text, images are said to exhibit the sentiments in a much better way. So, there is an urge to build a sentiment analysis model based on images from social media. In our work, we employed different transfer learning models, including the VGG-19, ResNet50V2, and DenseNet-121 models, to perform sentiment analysis based on images. They were fine-tuned by freezing and unfreezing some of the layers, and their performance was boosted by applying regularization techniques. We used the Twitter-based images available in the Crowdflower dataset, which contains URLs of images with their sentiment polarities. Our work also presents a comparative analysis of these pre-trained models in the prediction of image sentiments on our dataset. The accuracies of our fine-tuned transfer learning models involving VGG-19, ResNet50V2, and DenseNet-121 are 0.73, 0.75, and 0.89, respectively. When compared to previous attempts at visual sentiment analysis, which used a variety of machine and deep learning techniques, our model had an improved accuracy by about 5% to 10%. According to the findings, the fine-tuned DenseNet-121 model outperformed the VGG-19 and ResNet50V2 models in image sentiment prediction.

show abstract