3 papers
cs.CV2023
ViStruct: Visual Structural Knowledge Extraction via Curriculum Guided Code-Vision Representation
Yangyi Chen, Xingyao Wang, Manling Li +2
State-of-the-art vision-language models (VLMs) still have limited performance in structural knowledge extraction, such as relations between objects. In this work, we present ViStru…
cs.CL2021
An animated picture says at least a thousand words: Selecting Gif-based Replies in Multimodal Dialog
Xingyao Wang, David Jurgens
Online conversations include more than just text. Increasingly, image-based responses such as memes and animated gifs serve as culturally recognized and often humorous responses in…
cs.DC2020
Towards Scalable Distributed Training of Deep Learning on Public Cloud Clusters
Shaohuai Shi, Xianhao Zhou, Shutao Song +21
Distributed training techniques have been widely deployed in large-scale deep neural networks (DNNs) training on dense-GPU clusters. However, on public cloud clusters, due to the m…