Existing face forgery detection models try to discriminate fake images by detecting only
spatial artifacts (eg, generative artifacts, blending) or mainly temporal artifacts (eg, flickering …

Referring video object segmentation aims to predict foreground labels for objects referred by
natural language expressions in videos. Previous methods either depend on 3D ConvNets …

Video prediction is a challenging task due to its nature of uncertainty especially for
forecasting a long period. To model the temporal dynamics advanced methods benefit from …

Generating a video given the first several static frames is challenging as it anticipates
reasonable future frames with temporal coherence. Besides video prediction, the ability to …

Despite having promising results, style transfer, which requires preparing style images in
advance, may result in lack of creativity and accessibility. Following human instruction, on …

Referring image segmentation, the task of segmenting any arbitrary entities described in free-
form texts, opens up a variety of vision applications. However, manual labeling of training …

For decades, co-relating different data domains to attain the maximum potential of machines
has driven research, especially in neural networks. Similarly, text and visual data (images …

Referring video object segmentation (RVOS), as a supervised learning task, relies on
sufficient annotated data for a given scene. However, in more realistic scenarios, only …

Abstract Referring Video Object Segmentation (RVOS) requires segmenting the object in
video referred by a natural language query. Existing methods mainly rely on sophisticated …

Text response generation for multimodal task-oriented dialog systems, which aims to
generate the proper text response given the multimodal context, is an essential yet …