5 accepted papers
Precise and real-time visual localization is critical for applications like AR/VR and robotics, especially on resource-constrained edge devices such as smart glasses, where battery life and heat dissipation can be primary concerns. While many efficient models exist, further reducing compute without
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…
"Self-supervised learning methods have demonstrated impressive performance across visual understanding tasks, including human behavior understanding. However, there has been limited work for self-supervised learning for egocentric social videos. Visual processing in such contexts faces several chall…
To capture variation in categorical emotion recognition by human perceivers, we propose a multi-label learning and evaluation method that can employ the distribution of emotion labels generated by every human annotator. In contrast to the traditional accuracy-based performance measure for categorica…