35 citations · 61 across the 10 of their papers we have counts for
6 papers · 1 filter
Balanced Activation for Long-tailed Visual Recognition
Jiawei Ren, Cunjun Yu, Zhongang Cai +1
Deep classifiers have achieved great success in visual recognition. However, real-world data is long-tailed by nature, leading to the mismatch between training and testing distribu…
Leveraging Localization for Multi-camera Association
Zhongang Cai, Cunjun Yu, Junzhe Zhang +2
We present McAssoc, a deep learning approach to the as-sociation of detection bounding boxes in different views ofa multi-camera system. The vast majority of the academiahas been d…
MessyTable: Instance Association in Multiple Camera Views
Zhongang Cai, Junzhe Zhang, Daxuan Ren +5
We present an interesting and challenging dataset that features a large number of scenes with messy tables captured from multiple camera views. Each scene in this dataset is highly…
Balanced Meta-Softmax for Long-Tailed Visual Recognition
Jiawei Ren, Cunjun Yu, Shunan Sheng +4
Deep classifiers have achieved great success in visual recognition. However, real-world data is long-tailed by nature, leading to the mismatch between training and testing distribu…
Leveraging Temporal Information for 3D Detection and Domain Adaptation
Cunjun Yu, Zhongang Cai, Daxuan Ren +1
Ever since the prevalent use of the LiDARs in autonomous driving, tremendous improvements have been made to the learning on the point clouds. However, recent progress largely focus…
Spatio-Temporal Graph Transformer Networks for Pedestrian Trajectory Prediction
Cunjun Yu, Xiao Ma, Jiawei Ren +2
Understanding crowd motion dynamics is critical to real-world applications, e.g., surveillance systems and autonomous driving. This is challenging because it requires effectively m…