4 papers
Test-Time Adaptation for Tactile-Vision-Language Models
Chuyang Ye, Haoxian Jing, Qinting Jiang +4
Tactile-vision-language (TVL) models are increasingly deployed in real-world robotic and multimodal perception tasks, where test-time distribution shifts are unavoidable. Existing…
Seeing through Unclear Glass: Occlusion Removal with One Shot
Qiang Li, Yuanming Cao
Images taken through window glass are often degraded by contaminants adhered to the glass surfaces. Such contaminants cause occlusions that attenuate the incoming light and scatter…
A Turing Test for Artificial Nets devoted to model Human Vision
Jorge Vila-Tomás, Pablo Hernández-Cámara, Qiang Li +2
In our invited talk at the AI Evaluation Workshop of the University of Bristol back in June 2022 we argued that, despite claims about successful modeling of the visual brain using…
Robotic Perception with a Large Tactile-Vision-Language Model for Physical Property Inference
Zexiang Guo, Hengxiang Chen, Xinheng Mai +5
Inferring physical properties can significantly enhance robotic manipulation by enabling robots to handle objects safely and efficiently through adaptive grasping strategies. Previ…