IEEE

Skeleton-Based Data Augmentation for Sign Language Recognition Using Adversarial Learning

Abstract: In recent years, visual-based sign language recognition (SLR) has become an active research area with the advancement of deep learning. However, it is difficult to collect sign language data ...
IEEE

TinyVLA: Toward Fast, Data-Efficient Vision-Language-Action Models for Robotic Manipulation

Vision-Language-Action (VLA) models have shown remarkable potential in visuomotor control and instruction comprehension through end-to-end learning processes. However, current VLA models face ...
GitHub

data-engineering-project

Building a next-generation hybrid data pipeline architecture that combines the power of Microsoft Fabric, Azure Cloud, and Power BI. This pipeline is engineered to tackle the challenges of real-time ...
GitHub

This is the official implementation of ICLR 2024 paper "VDC: Versatile Data Cleanser based on Visual-Linguistic Inconsistency by Multimodal Large Language Models".

We find a commonality of various dirty samples is visual-linguistic inconsistency between images and associated labels. To capture the semantic inconsistency between modalities, we propose versatile ...
Microsoft

Table Meets LLM: Can Large Language Models Understand Structured Table Data? A Benchmark and Empirical Study

The 17th ACM International Conference on Web Search and Data Mining (WSDM '24) | March 2024 ...