3 accepted papers
Most existing GUI agents typically depend on non-vision inputs like HTML source code or accessibility trees, limiting flexibility across diverse software environments and platforms. Current multimodal large language models (MLLMs), though excel at using vision to ground real-world objects, often str…
Video saliency should be taken into consideration to facilitate optimization of the end-to-end video production, delivery and consumption ecosystem to improve user experience at lowered cost. Although recent studies have significantly increased the accuracy of saliency prediction, the approaches are…
In convolutional neural networks (CNNs), we propose to estimate the importance of a feature vector at a spatial location in the feature maps by the network's uncertainty on its class prediction, which can be quantified using the information entropy. Based on this idea, we propose the entropy-based f…