3 accepted papers
Visual place recognition is crucial for autonomous navigation and robotic mapping. Current methods struggle with perceptual aliasing and computational inefficiency. We present SemVPR, a novel approach integrating multimodal semantic knowledge into VPR. By leveraging a pre-trained vision-language mod…
Generating body pose from head-mounted, egocentric inputs is essential for immersive VR/AR and assistive technologies, as it supports more natural interactions. However, the task is challenging due to limited visibility of body parts in first-person views and the sparseness of sensory data, with onl…
Modern video coding standards use hybrid coding techniques to remove spatial and temporal redundancy. However, efficient exploitation of statistical dependencies measured by a mean squared error (MSE) does not always produce the best psychovisual result. In this paper, we propose a pixel-level textu…