Search Results

We introduce DiffH₂O, a new diffusion-based framework for synthesizing realistic, dexterous hand-object interactions from natural language. Our model employs a temporal two-stage diffusion process, dividing hand-object motion generation into grasping and ...

Existing datasets for 3D hand-object interaction are limited either in the data cardinality, data variations in interaction scenarios, or the quality of annotations. In this work, we present a comprehensive new training dataset for hand-object ...

We introduce Lumos, the first end-to-end multimodal question-answering system with text understanding capabilities. At the core of Lumos is a Scene Text Recognition (STR) component that extracts text from first person point-of-view images, the output of ...

We propose a dataset to study the influence of object-specific characteristics on human pick-and-place movements and compare the quality of the motion kinematics extracted by various sensors. This dataset is also suitable for promoting a broader ...

Item-finding tasks due to memory lapse are costly activities commonly experienced by many people. However, conventional systems are not suitable for use in a collaborative environment. Therefore, we propose a multi-functional, pre-registration-free, ...

Single view-based reconstruction of hand-object interaction is challenging due to the severe observation missing caused by occlusions. This paper proposes a physics-based method to better solve the ambiguities in the reconstruction. It first proposes a ...

People spend an enormous amount of time and effort looking for lost objects. To help remind people of the location of lost objects, various computational systems that provide information on their locations have been developed. However, prior systems for ...

Reconstructing hand-object interactions is a challenging task due to strong occlusions and complex motions. This article proposes a real-time system that uses a single depth stream to simultaneously reconstruct hand poses, object shape, and rigid/non-...

People spend an enormous amount of time and effort looking for lost objects. To help remind people of the location of lost objects, various computational systems that provide information on their locations have been developed. However, prior systems for ...

Hand-object interaction is challenging to reconstruct but important for many applications like HCI, robotics and so on. Previous works focus on either the hand or the object while we jointly track the hand poses, fuse the 3D object model and reconstruct ...

The objective of this set of experiments was to evaluate thermal pattern recognition on the hand and arm and to determine which features of thermal stimuli are encoded by cutaneous thermoreceptors and perceived by the user of a thermal display. Thermal ...

A thermal model is proposed that predicts the temperature responses of the skin and material surface during hand-object interactions as well as the heat flux exchanged when the fingerpad makes contact with an object. The surface features of the ...