33 citations · 88 across the 9 of their papers we have counts for
7 papers · 1 filter
Learning Hierarchical Graph Neural Networks for Image Clustering
Yifan Xing, Tong He, Tianjun Xiao +6
We propose a hierarchical graph neural network (GNN) model that learns how to cluster a set of images into an unknown number of identities using a training set of images annotated…
Semi-TCL: Semi-Supervised Track Contrastive Representation Learning
Wei Li, Yuanjun Xiong, Shuo Yang +3
Online tracking of multiple objects in videos requires strong capacity of modeling and matching object appearances. Previous methods for learning appearance embedding mostly rely o…
Graph Neural Networks for 3D Multi-Object Tracking
Xinshuo Weng, Yongxin Wang, Yunze Man +1
3D Multi-object tracking (MOT) is crucial to autonomous systems. Recent work often uses a tracking-by-detection pipeline, where the feature of each object is extracted independentl…
GNN3DMOT: Graph Neural Network for 3D Multi-Object Tracking with Multi-Feature Learning
Xinshuo Weng, Yongxin Wang, Yunze Man +1
3D Multi-object tracking (MOT) is crucial to autonomous systems. Recent work uses a standard tracking-by-detection pipeline, where feature extraction is first performed independent…
Joint Object Detection and Multi-Object Tracking with Graph Neural Networks
Yongxin Wang, Kris Kitani, Xinshuo Weng
Object detection and data association are critical components in multi-object tracking (MOT) systems. Despite the fact that the two components are dependent on each other, prior wo…
Detecting Attended Visual Targets in Video
Eunji Chong, Yongxin Wang, Nataniel Ruiz +1
We address the problem of detecting attention targets in video. Our goal is to identify where each person in each frame of a video is looking, and correctly handle the case where t…
Connecting Gaze, Scene, and Attention: Generalized Attention Estimation via Joint Modeling of Gaze and Scene Saliency
Eunji Chong, Nataniel Ruiz, Yongxin Wang +3
This paper addresses the challenging problem of estimating the general visual attention of people in images. Our proposed method is designed to work across multiple naturalistic so…