5 accepted papers
Foreground segmentation is a fundamental task in computer vision, encompassing various subdivision tasks. Previous research has typically designed task-specific architectures for each task, leading to a lack of unification. Moreover, they primarily focus on recognizing foreground objects without eff…
Ground terrain perception has become the primary visual task for the robust navigation of intelligent systems in unstructured outdoor environments. However, complex ter-rain poses a significant challenge to vision-based perception. This work introduces a novel estimation task using RGB images to fac
"Humans can foresee the future based on present observations, a skill we term as foresight minds. However, this capability remains under-explored within existing MLLMs, hindering their capacity to understand intentions behind subjects. To address this, we integrate the future modeling into MLLMs. By…
"Most Large Vision-Language Models (LVLMs) enjoy the same vision vocabulary, i.e., CLIP, for common vision tasks. However, for some special task that needs dense and fine-grained perception, the CLIP-style vocabulary may encounter low efficiency in tokenizing corresponding vision knowledge and even…
Pneumatic actuators have been widely used in robotics due to their inherent compliance and relatively high strength. In this letter, the authors report on the design, analysis and experimental validation of a novel pneumatic/cable-driven hybrid linear actuator whose structure is a combination of ori