336 citations · 854 across the 53 of their papers we have counts for
11 papers · 1 filter
UDA-COPE: Unsupervised Domain Adaptation for Category-level Object Pose Estimation
Taeyeop Lee, Byeong-Uk Lee, Inkyu Shin +4
Learning to estimate object pose often requires ground-truth (GT) labels, such as CAD model and absolute-scale object pose, which is expensive and laborious to obtain in the real w…
Attentive and Contrastive Learning for Joint Depth and Motion Field Estimation
Seokju Lee, Francois Rameau, Fei Pan +1
Estimating the motion of the camera together with the 3D structure of the scene from a monocular vision system is a complex task that often relies on the so-called scene rigidity a…
Discover, Hallucinate, and Adapt: Open Compound Domain Adaptation for Semantic Segmentation
KwanYong Park, Sanghyun Woo, Inkyu Shin +1
Unsupervised domain adaptation (UDA) for semantic segmentation has been attracting attention recently, as it could be beneficial for various label-scarce real-world scenarios (e.g.…
ACP++: Action Co-occurrence Priors for Human-Object Interaction Detection
Dong-Jin Kim, Xiao Sun, Jinsoo Choi +2
A common problem in the task of human-object interaction (HOI) detection is that numerous HOI classes have only a small number of labeled examples, resulting in training sets with…
Category-Level Metric Scale Object Shape and Pose Estimation
Taeyeop Lee, Byeong-Uk Lee, Myungchul Kim +1
Advances in deep learning recognition have led to accurate object detection with 2D images. However, these 2D perception methods are insufficient for complete 3D world information.…
VolumeFusion: Deep Depth Fusion for 3D Scene Reconstruction
Jaesung Choe, Sunghoon Im, Francois Rameau +2
To reconstruct a 3D scene from a set of calibrated views, traditional multi-view stereo techniques rely on two distinct stages: local depth maps computation and global depth maps f…
Learning Open-World Object Proposals without Learning to Classify
Dahun Kim, Tsung-Yi Lin, Anelia Angelova +2
Object proposals have become an integral preprocessing steps of many vision pipelines including object detection, weakly supervised detection, object discovery, tracking, etc. Comp…
Correlate-and-Excite: Real-Time Stereo Matching via Guided Cost Volume Excitation
Antyanta Bangunharcana, Jae Won Cho, Seokju Lee +3
Volumetric deep learning approach towards stereo matching aggregates a cost volume computed from input left and right images using 3D convolutions. Recent works showed that utiliza…
Unsupervised Domain Adaptation for Video Semantic Segmentation
Inkyu Shin, Kwanyong Park, Sanghyun Woo +1
Unsupervised Domain Adaptation for semantic segmentation has gained immense popularity since it can transfer knowledge from simulation to real (Sim2Real) by largely cutting out the…
MCDAL: Maximum Classifier Discrepancy for Active Learning
Jae Won Cho, Dong-Jin Kim, Yunjae Jung +1
Recent state-of-the-art active learning methods have mostly leveraged Generative Adversarial Networks (GAN) for sample acquisition; however, GAN is usually known to suffer from ins…
An Efficient Asynchronous Method for Integrating Evolutionary and Gradient-based Policy Search
Kyunghyun Lee, Byeong-Uk Lee, Ukcheol Shin +1
Deep reinforcement learning (DRL) algorithms and evolution strategies (ES) have been applied to various tasks, showing excellent performances. These have the opposite properties, w…