267 citations · 370 across the 23 of their papers we have counts for
26 papers
BoIR: Box-Supervised Instance Representation for Multi-Person Pose Estimation
Uyoung Jeong, Seungryul Baek, Hyung Jin Chang +1
Single-stage multi-person human pose estimation (MPPE) methods have shown great performance improvements, but existing methods fail to disentangle features by individual instances…
Active Learning Guided by Efficient Surrogate Learners
Yunpyo An, Suyeong Park, Kwang In Kim
Re-training a deep learning model each time a single data point receives a new label is impractical due to the inherent complexity of the training process. Consequently, existing a…
SContact: Graph-based Network for 3D Hand-Object Contact Estimation with Semi-Supervised Learning
Tze Ho Elden Tse, Zhongqun Zhang, Kwang In Kim +3
Despite the recent efforts in accurate 3D annotations in hand and object datasets, there still exist gaps in 3D hand and object reconstructions. Existing works leverage contact map…
Collaborative Learning for Hand and Object Reconstruction with Attention-guided Graph Convolution
Tze Ho Elden Tse, Kwang In Kim, Ales Leonardis +1
Estimating the pose and shape of hands and objects under interaction finds numerous applications including augmented and virtual reality. Existing approaches for hand and object re…
Testing using Privileged Information by Adapting Features with Statistical Dependence
Kwang In Kim, James Tompkin
Given an imperfect predictor, we exploit additional features at test time to improve the predictions made, without retraining and without knowledge of the prediction function. This…
DynaDog+T: A Parametric Animal Model for Synthetic Canine Image Generation
Jake Deane, Sinead Kearney, Kwang In Kim +1
Synthetic data is becoming increasingly common for training computer vision models for a variety of tasks. Notably, such data has been applied in tasks related to humans such as 3D…