Researchers are interested in Facial Emotion Recognition (FER) because it could be useful in many ways and has promising applications. The main task of FER is to identify and recognize the original facial expressions of users from digital inputs. Feature extraction and emotion recognition make up the majority of the traditional FER. Deep Neural Networks, specifically Convolutional Neural Network (CNN), are popular and highly used in FER due to their inherent image feature extraction process. This work presents a novel method dubbed as EfficientNet-XGBoost that is based on Transfer Learning (TL) technique. EfficientNet-XGBoost is basically a cascading of the EfficientNet and the XGBoost techniques along with certain enhancements by experimentation that reflects the novelty of the work. To ensure faster learning of the network and to overcome the vanishing gradient problem, our model incorporates fully connected layers of global average pooling, dropout and dense. EfficientNet is fine-tuned by replacing the upper dense layer(s) and cascading the XGBoost classifier making it suitable for FER. Feature map visualization is carried out that reveals the reduction in the size of feature vectors. The proposed method is well-validated on benchmark datasets such as CK+, KDEF, JAFFE, and FER2013. To overcome the issue of data imbalance, in some of the datasets namely CK+ and FER2013, we augmented data artificially through geometric transformation techniques. The proposed method is implemented individually on these datasets and corresponding results are recorded for performance analysis. The performance is computed with the help of several metrics like precision, recall and F1 measure. Comparative analysis with competent schemes are carried out on the same sample data sets separately. Irrespective of the nature of the datasets, the proposed scheme outperforms the rest with overall rates of accuracy being 100%, 98% and 98% for the first three datasets respectively. However, for the FER2013 datasets, efficiency is less promisingly observed in support of the proposed work.

The task of multi-view video summarization is to efficiently represent the most significant information from a set of videos captured for a certain period of time by multiple cameras. The problem is highly challenging because of the huge size of the data, presence of many unimportant frames with low activity, inter-view dependencies, and significant variations in illumination. In this paper, we propose a graph-theoretic solution to the above problems. Semantic feature in form of visual bag of words and visual features like color, texture, and shape are used to model shot representative frames after temporal segmentation . Gaussian entropy is then applied to filter out frames with low activity. Inter-view dependencies are captured via bipartite graph matching. Finally, the optimum-path forest algorithm is applied for the clustering purpose. Subjective as well as objective evaluations clearly indicate the effectiveness of the proposed approach.

To decipher human activities and facilitate organic computer-human interactions, facial expression recognition is crucial using four datasets JAFFE, CKPlus, KDEF and AffectNet, we achieve excellent accuracy in human face emotion classification with the VGG 16 pre-trained model with transfer learning. To obtain a comprehensive insight of the model’s decision-making process, we employ Layerwise Relevance Propagation (LRP), a method from explainable Artificial Intelligence (XAI). Only positive relevance scores are taken into account for successfully predicted test images from the datasets. Contributory pixels towards predicting the intensity of emotion are pixels with good relevance ratings. By combining emotion recognition with LRP, we can forecast emotion labels and ranks. Using a confusion matrix, we checked if our predictions were in line with reality. Our model achieved intensity prediction accuracy of 96.33% on JAFFE, 95.78% on CKPlus, 95.78% on KDEF, and 93.89% on AffectNet. A group of ten annotators work together to generate ground truth by assigning ratings of “MINIMAL, “AVERAGE, and “STRONG to each image. This study demonstrates how well our method predicts the ranks of emotion intensity and provides information on how trustworthy and interpretable the model is. Facial emotion recognition’s intensity ranking is made more robust with the addition of XAI techniques like LRP.

Movie scene detection has emerged as an important problem in present day multimedia applications. Since a movie typically consists of huge amount of video data with widespread content variations, detecting a movie scene has become extremely challenging. In this paper, we propose a fast yet accurate solution for movie scene detection using Nyström approximated multisimilarity spectral clustering with a temporal integrity constraint. We use multiple similarity matrices to model the wide content variations typically present in any movie dataset. Nyström approximation is employed to reduce the high computational cost of constructing multiple similarity measures. The temporal integrity constraint captures the inherent temporal cohesion of the movie shots. Experiments on five movie datasets from different genres clearly demonstrate the superiority of the proposed solution over the state-of-the-art methods.

Scalable video summarization has emerged as an important problem in present day multimedia applications. Effective summaries need to be provided to the users for videos of any duration at low computational cost. In this paper, we propose a framework which is scalable during both the analysis and the generation stages of video summarization. The problem of scalable video summarization is modeled as a problem of scalable graph clustering and is solved using skeleton graph and random walks in the analysis stage. A cluster significance factor-based ranking procedure is adopted in the generation stage. Experiments on videos of different genres and durations clearly indicate the supremacy of the proposed method over a recently published work.