Sorry, you need to enable JavaScript to visit this website.

Robust video scene classification models should capture the spatial (pixel-wise) and temporal (frame-wise) characteristics of a video effectively. Transformer models with self-attention which are designed to get contextualized representations for individual tokens given a sequence of tokens, are becoming increasingly popular in many computer vision tasks. However, the use of Transformer based models for video under-standing is still relatively unexplored.

When training an anchor-based object detector with a sparsely annotated dataset, the effort required to locate positive examples can cause performance degradation. Because anchor-based object detection models collect positive examples under IoU between anchors and ground-truth bounding boxes, in a sparsely annotated image, some objects that are not annotated can be assigned as negative examples, such as backgrounds.

The present Multi-view stereo (MVS) methods with supervised learning-based networks have an impressive performance comparing with traditional MVS methods. However, the ground-truth depth maps for training are hard to be obtained and are within limited kinds of scenarios. In this paper, we propose a novel unsupervised multi-metric MVS network, named M^3VSNet, for dense point cloud reconstruction without any supervision.

Automated unsupervised video summarization by key-frame extraction consists in identifying representative video frames, best abridging a complete input sequence, and temporally ordering them to form a video summary, without relying on manually constructed ground-truth key-frame sets. State-of-the-art unsupervised deep neural approaches consider the desired summary to be a subset of the original sequence, composed of video frames that are sufficient to visually reconstruct the entire input.

Visualizing the features captured by Convolutional Neural Networks (CNNs) is one of the conventional approaches to interpret the predictions made by these models in numerous image recognition applications. Grad-CAM is a popular solution that provides such a visualization by combining the activation maps obtained from the model.However, the average gradient-based terms deployed in this method under-estimates the contribution of the representations discovered by the model to its predictions.

Explainable AI (XAI) is an active research area to interpret a neural network’s decision by ensuring transparency and trust in the task-specified learned models.Recently,perturbation-based model analysis has shown better interpretation, but back-propagation techniques are still prevailing because of their computational efficiency. In this work, we combine both approaches as a hybrid visual explanation algorithm and propose an efficient interpretation method for convolutional neural networks.