4 papers
ST-LDM: A Universal Framework for Text-Grounded Object Generation in Real Images
Xiangtian Xue, Jiasong Wu, Youyong Kong +2
We present a novel image editing scenario termed Text-grounded Object Generation (TOG), defined as generating a new object in the real image spatially conditioned by textual descri…
Rethinking Referring Object Removal
Xiangtian Xue, Jiasong Wu, Youyong Kong +2
Referring object removal refers to removing the specific object in an image referred by natural language expressions and filling the missing region with reasonable semantics. To ad…
Multiscale Low-Frequency Memory Network for Improved Feature Extraction in Convolutional Neural Networks
Fuzhi Wu, Jiasong Wu, Youyong Kong +5
Deep learning and Convolutional Neural Networks (CNNs) have driven major transformations in diverse research areas. However, their limitations in handling low-frequency information…
CSLNSpeech: solving extended speech separation problem with the help of Chinese sign language
Jiasong Wu, Xuan Li, Taotao Li +5
Previous audio-visual speech separation methods use the synchronization of the speaker's facial movement and speech in the video to supervise the speech separation in a self-superv…