相关论文: Binding Touch to Everything: Learning Unified Mult…

Hand motion plays a central role in human interaction, yet modeling realistic 4D hand motion (i.e., 3D hand pose sequences over time) remains challenging. Research in this area is typically divided into two tasks: (1) Estimation approaches…

Tactile perception is essential for embodied agents to understand physical attributes of objects that cannot be determined through visual inspection alone. While existing approaches have made progress in visual and language modalities for…

Face recognition is a crucial task in various multimedia applications such as security check, credential access and motion sensing games. However, the task is challenging when an input face is noisy (e.g. poor-condition RGB image) or lacks…

For successful deployment of robots in multifaceted situations, an understanding of the robot for its environment is indispensable. With advancing performance of state-of-the-art object detectors, the capability of robots to detect objects…

Can a robot grasp an unknown object without seeing it? In this paper, we present a tactile-sensing based approach to this challenging problem of grasping novel objects without prior knowledge of their location or physical properties. Our…

Robotic insertion tasks remain challenging due to uncertainties in perception and the need for precise control, particularly in unstructured environments. While humans seamlessly combine vision and touch for such tasks, effectively…

Research on multi-modal learning dominantly aligns the modalities in a unified space at training, and only a single one is taken for prediction at inference. However, for a real machine, e.g., a robot, sensors could be added or removed at…

We introduce Unimotion, the first unified multi-task human motion model capable of both flexible motion control and frame-level motion understanding. While existing works control avatar motion with global text conditioning, or with…

Materials science datasets are inherently heterogeneous and are available in different modalities such as characterization spectra, atomic structures, microscopic images, and text-based synthesis conditions. The advancements in multi-modal…

In many applications involving multi-media data, the definition of similarity between items is integral to several key tasks, e.g., nearest-neighbor retrieval, classification, and recommendation. Data in such regimes typically exhibits…

Today's touch sensors come in many shapes and sizes. This has made it challenging to develop general-purpose touch processing methods since models are generally tied to one specific sensor design. We address this problem by performing…

Joint image-text embedding is the bedrock for most Vision-and-Language (V+L) tasks, where multimodality inputs are simultaneously processed for joint visual and textual understanding. In this paper, we introduce UNITER, a UNiversal…

Three-dimensional (3D) applications have come to every corner of life. We present 3DTouch, a novel 3D wearable input device worn on the fingertip for interacting with 3D applications. 3DTouch is self-contained, and designed to universally…

We abstract the features (i.e. learned representations) of multi-modal data into 1) uni-modal features, which can be learned from uni-modal training, and 2) paired features, which can only be learned from cross-modal interactions.…

Visual-language models have advanced the development of universal models, yet their application in medical imaging remains constrained by specific functional requirements and the limited data. Current general-purpose models are typically…

While tactile sensing is widely accepted as an important and useful sensing modality, its use pales in comparison to other sensory modalities like vision and proprioception. AnySkin addresses the critical challenges that impede the use of…

High-fidelity visuo-tactile sensing is important for precise robotic manipulation. However, most vision-based tactile sensors face a fundamental trade-off: opaque coatings enable tactile sensing but block pre-contact vision. To address…

Humans sense of distance depends on the integration of multi sensory cues. The incoming visual luminance, auditory pitch and tactile vibration could all contribute to the ability of distance judgement. This ability can be enhanced if the…

We present ImageBind, an approach to learn a joint embedding across six different modalities - images, text, audio, depth, thermal, and IMU data. We show that all combinations of paired data are not necessary to train such a joint…

Learning an effective attention mechanism for multimodal data is important in many vision-and-language tasks that require a synergic understanding of both the visual and textual contents. Existing state-of-the-art approaches use…