We demonstrate that many expression datasets contain significant annotation biases between genders, especially when it comes to the happy and angry expressions, and that traditional methods cannot fully mitigate such biases in trained models.
In a series of experiments, we demonstrate that human gesture cues, even without predefined semantics, improve the object-goal navigation for an embodied agent, outperforming various state-of-the-art methods.
Understanding who blames or supports whom in news text is a critical research question in computational social science.
Automated computer vision systems have been applied in many domains including security, law enforcement, and personal devices, but recent reports suggest that these systems may produce biased results, discriminating against people in certain demographic groups.
Images were collected from the YFCC-100M Flickr dataset and labeled with race, gender, and age groups.
Ranked #1 on Facial Attribute Classification on FairFace
In this paper, we seek to understand how politicians use images to express ideological rhetoric through Facebook images posted by members of the U. S. House and Senate.
Image data provide unique information about political events, actors, and their interactions which are difficult to measure from or not available in text data.
We also release the UCLA Protest Image Dataset, our novel dataset of 40, 764 images (11, 659 protest images and hard negatives) with various annotations of visual attributes and sentiments.
Online social media is a social vehicle in which people share various moments of their lives with their friends, such as playing sports, cooking dinner or just taking a selfie for fun, via visual means, that is, photographs.
The AOG embeds a context sensitive grammar that can describe the hierarchical composition of news topics by semantic elements about people involved, related places and what happened, and model contextual relationships between elements in the hierarchy.
Secondly, our model can categorize the political party affiliations of politicians, i. e., Democrats vs. Republicans, with the accuracy of 62. 6% (male) and 60. 1% (female).
We evaluate the proposed method by (i) showing the improvement of attribute recognition accuracy; and (ii) comparing the average precision of localizing attributes to the scene parts.