Publications (5)
Squared Earth Mover's Distance-based Loss for Training Deep Neural Networks
Le Hou, Chen-Ping Yu, Dimitris Samaras
In the context of single-label classification, despite the huge success of deep learning, the commonly used cross-entropy loss function ignores the intricate inter-class relationsh…
Beyond Words: Multimodal LLM Knows When to Speak
Zikai Liao, Yi Ouyang, Yi-Lun Lee +3
Chatbots via large language models (LLMs) generate fluent responses but often struggle with when to speak, especially for brief, timely listener reactions during ongoing dialogue.…
Geodesic Distance Histogram Feature for Video Segmentation
Hieu Le, Vu Nguyen, Chen-Ping Yu +1
This paper proposes a geodesic-distance-based feature that encodes global information for improved video segmentation algorithms. The feature is a joint histogram of intensity and…
Low-Rank Head Avatar Personalization with Registers
Sai Tanmay Reddy Chakkera, Aggelina Chatziagapi, Md Moniruzzaman +3
We introduce a novel method for low-rank personalization of a generic model for head avatar generation. Prior work proposes generic models that achieve high-quality face animation…
Co-localization with Category-Consistent Features and Geodesic Distance Propagation
Hieu Le, Chen-Ping Yu, Gregory Zelinsky +1
Co-localization is the problem of localizing objects of the same class using only the set of images that contain them. This is a challenging task because the object detector must b…