no code implementations • ICCV 2023 • Tzofi Klinghoffer, Jonah Philion, Wenzheng Chen, Or Litany, Zan Gojcic, Jungseock Joo, Ramesh Raskar, Sanja Fidler, Jose M. Alvarez
We introduce a technique for novel view synthesis and use it to transform collected data to the viewpoint of target rigs, allowing us to train BEV segmentation models for diverse target rigs without any additional data collection or labeling cost.
1 code implementation • 22 Jul 2022 • Xiaofeng Lin, Seungbae Kim, Jungseock Joo
Existing pruning techniques preserve deep neural networks' overall ability to make correct predictions but may also amplify hidden biases during the compression process.
1 code implementation • CVPR 2022 • Yu Yang, Seungbae Kim, Jungseock Joo
We also demonstrate a novel application of our method for unsupervised dataset bias analysis which allows us to automatically discover hidden biases in datasets or compare different subsets without using additional labels.
no code implementations • 1 Mar 2022 • Andrew Choi, Mohammad Khalid Jawed, Jungseock Joo
To minimize such idle time, the robot must preemptively predict the human intent of where the object will be placed.
no code implementations • 28 Nov 2021 • Shuwen Qiu, Sirui Xie, Lifeng Fan, Tao Gao, Jungseock Joo, Song-Chun Zhu, Yixin Zhu
Humans communicate with graphical sketches apart from symbolic languages.
no code implementations • ICCV 2021 • Yunliang Chen, Jungseock Joo
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.
Facial Expression Recognition Facial Expression Recognition (FER)
1 code implementation • 5 Aug 2021 • Qi Wu, Cheng-Ju Wu, Yixin Zhu, Jungseock Joo
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.
1 code implementation • Findings (ACL) 2021 • Kunwoo Park, Zhufeng Pan, Jungseock Joo
Understanding who blames or supports whom in news text is a critical research question in computational social science.
no code implementations • 21 May 2020 • Jungseock Joo, Kimmo Kärkkäinen
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.
5 code implementations • 14 Aug 2019 • Kimmo Kärkkäinen, Jungseock Joo
Images were collected from the YFCC-100M Flickr dataset and labeled with race, gender, and age groups.
Ranked #2 on Facial Attribute Classification on FairFace
no code implementations • 22 Jul 2019 • Nan Xi, Di Ma, Marcus Liou, Zachary C. Steinert-Threlkeld, Jason Anastasopoulos, Jungseock Joo
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.
no code implementations • 3 Oct 2018 • Jungseock Joo, Zachary C. Steinert-Threlkeld
Image data provide unique information about political events, actors, and their interactions which are difficult to measure from or not available in text data.
1 code implementation • 18 Sep 2017 • Donghyeon Won, Zachary C. Steinert-Threlkeld, Jungseock Joo
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.
no code implementations • 24 May 2017 • Quanzeng You, Darío García-García, Mahohar Paluri, Jiebo Luo, Jungseock Joo
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.
no code implementations • 13 Apr 2017 • Yu-I Ha, Sejeong Kwon, Meeyoung Cha, Jungseock Joo
The fashion industry is establishing its presence on a number of visual-centric social media like Instagram.
no code implementations • 15 Dec 2015 • Weixin Li, Jungseock Joo, Hang Qi, Song-Chun Zhu
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.
no code implementations • ICCV 2015 • Jungseock Joo, Francis F. Steen, Song-Chun Zhu
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).
no code implementations • CVPR 2014 • Jungseock Joo, Weixin Li, Francis F. Steen, Song-Chun Zhu
In this paper we introduce the novel problem of understanding visual persuasion.
no code implementations • CVPR 2013 • Shuo Wang, Jungseock Joo, Yizhou Wang, Song-Chun Zhu
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.