Related papers: American == White in Multimodal Language-and-Image…

Person Re-identification (ReID) systems that match individuals across images or video frames are essential in many real-world applications. However, existing methods are often influenced by attributes such as gender, pose, and body mass…

Vision-language models (VLMs) deliver strong zero-shot recognition but frequently inherit social biases from their training data. We systematically disentangle three design factors -- model size, training-data scale, and training-data…

Contrastive Language-Image Pretraining (CLIP) has emerged as a novel paradigm to learn visual models from language supervision. While researchers continue to push the frontier of CLIP, reproducing these works remains challenging. This is…

With the starting point that implicit human biases are reflected in the statistical regularities of language, it is possible to measure biases in English static word embeddings. State-of-the-art neural language models generate dynamic word…

Image captioning is an important task for benchmarking visual reasoning and for enabling accessibility for people with vision impairments. However, as in many machine learning settings, social biases can influence image captioning in…

Human society had a long history of suffering from cognitive biases leading to social prejudices and mass injustice. The prevalent existence of cognitive biases in large volumes of historical data can pose a threat of being manifested as…

This study investigated potential scoring biases and disparities toward English Language Learners (ELLs) when using automatic scoring systems for middle school students' written responses to science assessments. We specifically focus on…

The potential of multimodal generative artificial intelligence (mAI) to replicate human grounded language understanding, including the pragmatic, context-rich aspects of communication, remains to be clarified. Humans are known to use…

Pretrained cross-modal models, for instance, the most representative CLIP, have recently led to a boom in using pre-trained models for cross-modal zero-shot tasks, considering the generalization properties. However, we analytically discover…

A fundamental characteristic common to both human vision and natural language is their compositional nature. Yet, despite the performance gains contributed by large vision and language pretraining, recent investigations find that most-if…

The age estimation task aims to predict the age of an individual by analyzing facial features in an image. The development of age estimation can improve the efficiency and accuracy of various applications (e.g., age verification and secure…

Racial homophily refers to the tendency of individuals to associate with others of the same racial or ethnic background. A recent study found no evidence of racial homophily in responses to mass shooting data visualizations. To increase the…

Contrastive Language-Image Pre-training (CLIP) formulates image classification as an image-to-text matching task, i.e., matching images to the corresponding natural language descriptions instead of discrete category IDs. This allows for…

Despite the continued anthropomorphization of AI systems, the potential impact of racialization during human-AI interaction is understudied. This study explores how human-AI cooperation may be impacted by the belief that data used to train…

Personalization in emotion recognition (ER) is essential for an accurate interpretation of subtle and subject-specific expressive patterns. Recent advances in vision-language models (VLMs) such as CLIP demonstrate strong potential for…

Contrastive Language-Image Pre-training (CLIP) models have shown significant potential, particularly in zero-shot classification across diverse distribution shifts. Building on existing evaluations of overall classification robustness, this…

Image Captioning generates descriptive sentences from images using Vision-Language Pre-trained models (VLPs) such as BLIP, which has improved greatly. However, current methods lack the generation of detailed descriptive captions for the…

Face recognition algorithms, when used in the real world, can be very useful, but they can also be dangerous when biased toward certain demographics. So, it is essential to understand how these algorithms are trained and what factors affect…

AI in dermatology is evolving at a rapid pace but the major limitation to training trustworthy classifiers is the scarcity of data with ground-truth concept level labels, which are meta-labels semantically meaningful to humans. Foundation…

This paper strives to address image classifier bias, with a focus on both feature and label embedding spaces. Previous works have shown that spurious correlations from protected attributes, such as age, gender, or skin tone, can cause…