1.4k citations · 1.5k across the 42 of their papers we have counts for
6 papers · 1 filter
Survey of Bias In Text-to-Image Generation: Definition, Evaluation, and Mitigation
Yixin Wan, Arjun Subramonian, Anaelia Ovalle +6
The recent advancement of large and powerful models with Text-to-Image (T2I) generation abilities -- such as OpenAI's DALLE-3 and Google's Gemini -- enables users to generate high-…
GenEARL: A Training-Free Generative Framework for Multimodal Event Argument Role Labeling
Hritik Bansal, Po-Nien Kung, P. Jeffrey Brantingham +2
Multimodal event argument role labeling (EARL), a task that assigns a role for each event participant (object) in an image is a complex challenge. It requires reasoning over the en…
VideoCon: Robust Video-Language Alignment via Contrast Captions
Hritik Bansal, Yonatan Bitton, Idan Szpektor +2
Despite being (pre)trained on a massive amount of data, state-of-the-art video-language alignment models are not robust to semantically-plausible contrastive changes in the video c…
Dataset Bias Mitigation in Multiple-Choice Visual Question Answering and Beyond
Zhecan Wang, Long Chen, Haoxuan You +6
Vision-language (VL) understanding tasks evaluate models' comprehension of complex visual scenes through multiple-choice questions. However, we have identified two dataset biases t…
CoBIT: A Contrastive Bi-directional Image-Text Generation Model
Haoxuan You, Mandy Guo, Zhecan Wang +3
The field of vision and language has witnessed a proliferation of pre-trained foundation models. Most existing methods are independently pre-trained with contrastive objective like…
SGEITL: Scene Graph Enhanced Image-Text Learning for Visual Commonsense Reasoning
Zhecan Wang, Haoxuan You, Liunian Harold Li +5
Answering complex questions about images is an ambitious goal for machine intelligence, which requires a joint understanding of images, text, and commonsense knowledge, as well as…