Abstract In Visual question answering (VQA), a natural language answer is generated for a given image and a question related to that image. There is a significant growth in the VQA task by applying an efficient attention mechanism. However, current VQA models use region features or object features that are not adequate to improve the accuracy of generated answers. To deal with this issue, we have used a Two‐way Co‐Attention Mechanism (TCAM), which is capable enough to fuse different visual features (region, object, and concept) from diverse perspectives. These diverse features lead to different sets of answers, and also, there is an inherent relationship between these visual features. We have developed a powerful attention mechanism that uses these two critical aspects by using both bottom‐up and top‐down TCAM to extract discriminative feature information. We have proposed a Collective Feature Integration Module (CFIM) to combine multimodal attention features and thus capture the valuable information from these visual features by employing a TCAM. Further, we have formulated a Vertical CFIM for fusing the features belonging to the same class and a Horizontal CFIM for combining the features belonging to different types, thus balancing the influence of top‐down and bottom‐up co‐attention. The experiments are conducted on two significant datasets, VQA 1.0 and VQA 2.0. On VQA 1.0, the overall accuracy of our proposed method is 71.23 on the test‐dev set and 71.94 on the test‐std set. On VQA 2.0, the overall accuracy of our proposed method is 75.89 on the test‐dev set and 76.32 on the test‐std set. The above overall accuracy clearly reflecting the superiority of our proposed TCAM based approach over the existing methods.

Abstract Visual question answering (VQA) is a challenging task in computer vision. Recently, there has been a growing interest in text‐based VQA tasks, emphasizing the important role of textual information for better understanding of images. Effectively utilizing text information within the image is crucial for achieving success in this task. However, existing approaches often overlook the contextual information and neglect to utilize the relationships between scene‐text tokens and image objects. They simply incorporate the scene‐text tokens mined from the image into the VQA model without considering these important factors. In this paper, the proposed model initially analyzes the image to extract text and identify scene objects. It then comprehends the question and mines relationships among the question, OCRed text, and scene objects, ultimately generating an answer through relational reasoning by conducting semantic and positional attention. Our decoder with attention map loss enables prediction of complex answers and handles dynamic vocabularies, reducing decoding space. It outperforms softmax‐based cross entropy loss in accuracy and efficiency by accommodating varying vocabulary sizes. We evaluated our model's performance on the TextVQA dataset and achieved an accuracy of 53.91% on the validation set and 53.98% on the test set. Moreover, on the ST‐VQA dataset, our model obtained ANLS scores of 0.699 on the validation set and 0.692 on the test set.

Recently, all have witnessed a rapid growth of COVID-19 coronavirus worldwide. The calculation of COVID-19 time-series prediction is done using many techniques like compartment models, machine learning models (ML), and deep learning models. Therefore, in this paper, the authors have proposed an ensemble-based neural network model. Neural networks (NN), along with non-linear autoregressive (NAR) functions, fitting neural networks (FITNET), or fuzzy Systems, are widely used in time-series forecasting. The responses of NAR, FITNET predictor modules are aggregated using fuzzy logic, which improves the final prediction by intelligently integrating outputs of different modules. The whole model was put to the test in terms of forecasting the coronavirus time series in India, at 13 States. In the validation data set, results of ensemble NN models with fuzzy response integration demonstrate extremely better-predicted values. Overall, the results reveal that a modular neural network with fuzzy (MNNF) beats all other approaches in performance metrics, like Root Mean Squared Error (RMSE). Prediction errors of ensemble NN i.e., MNNF are much smaller than those of classic monolithic neural networks, showing advantages of the method proposed. The model provides the prediction for the upcoming 8 days.

Images captured in hazy or foggy weather conditions, suffer from various problems, such as limited visibility, low contrast, color distortions. These images are used in many computer vision applications, such as video surveillance, transportation, remote sensing. The elimination of the haze effect from these images is essential to ensure the perfect working of these applications. The degradation of a captured image is expressed by the physical model of hazy image formation. The physical model requires the estimation of transmission to restore a haze-free image, which is one of the most important parameters of single image dehazing (SID). Due to the ill-posed nature of SID, lots of priors/assumptions have been used. However, traditional methods fail when these priors do not hold, especially for varying haze concentrations, which lead to many issues such as incomplete haze removal or over enhancement in long-range regions. In this paper, a single image dehazing method based on a superpixel and nonlinear transformation is proposed. The proposed method transforms the minimum filtering on superpixels of a hazy image into the minimum filtering on superpixels of a haze-free image using nonlinear transformation. The nonlinear transformation prevents over enhancement in the long-range regions, while the superpixels reduce the halo artifacts in the dehazed image. The experimental results on challenging real hazy images, dense-hazy images, and synthetic images have proved that a combination of nonlinear transformation and superpixels provide the strength to the proposed method. The obtained dehazed results are evaluated qualitatively and quantitatively and it is found that the proposed method has tremendous performance as compared to state-of-the-art dehazing approaches.

All of us rely on the images for the memories of our life and loved ones. The images are useful in proving an evidence of the event. Image forgery has become much prominent nowadays and is being done either for fun or intentionally. In this paper, we detect copy move forgery by combining the two features namely, Zernike moments and auto colour correlogram. The first checks the shape of the objects in the block, the latter for distance of each colour pixel taking into account the 64 colours. Both combine together to identify the regions for which copy-move forgery exists. The first completes the number of comparisons in the order of n2, where n is the number of blocks. The ACC verifies the colours used in the block. If both matches are confirmed, the suspicious blocks are returned. The method out-performs the existing methods based on the probability approach.