research
∙
12/06/2022
Unifying Short and Long-Term Tracking with Graph Hierarchies
Tracking objects over long videos effectively means solving a spectrum o...
share
research
∙
10/11/2022
The Unreasonable Effectiveness of Fully-Connected Layers for Low-Data Regimes
Convolutional neural networks were the standard for solving many compute...
research
∙
08/03/2022
PolarMOT: How Far Can Geometric Relations Take Us in 3D Multi-Object Tracking?
Most (3D) multi-object tracking methods rely on appearance-based cues fo...
research
∙
07/22/2022
DeVIS: Making Deformable Transformers Work for Video Instance Segmentation
Video Instance Segmentation (VIS) jointly tackles multi-object detection...
research
∙
07/15/2022
Multi-Object Tracking and Segmentation via Neural Message Passing
Graphs offer a natural way to formulate Multiple Object Tracking (MOT) a...
research
∙
06/09/2022
Simple Cues Lead to a Strong Multi-Object Tracker
For a long time, the most common paradigm in Multi-Object Tracking was t...
research
∙
10/11/2021
The Center of Attention: Center-Keypoint Grouping via Attention for Multi-Person Pose Estimation
We introduce CenterGroup, an attention-based framework to estimate human...
research
∙
08/21/2021
MOTSynth: How Can Synthetic Data Help Pedestrian Detection and Tracking?
Deep learning-based methods for video pedestrian detection and tracking ...
research
∙
12/16/2019