Jenny Seidenschwarz — accepted AI-conference papers

2024

SeMoLi: What Moves Together Belongs Together

Jenny Seidenschwarz, Aljosa Osep, Francesco Ferroni, Simon Lucey, Laura Leal-Taixe

CVPR 2024poster

We tackle semi-supervised object detection based on motion cues. Recent results suggest that heuristic-based clustering methods in conjunction with object trackers can be used to pseudo-label instances of moving objects and use these as supervisory signals to train 3D object detectors in Lidar data…

Cited by 8 Source ↗PDF ↗Scholar ↗

2023

Simple Cues Lead to a Strong Multi-Object Tracker

Jenny Seidenschwarz, Guillem Brasó, Víctor Castro Serrano, Ismail Elezi, Laura Leal-Taixé

CVPR 2023poster

For a long time, the most common paradigm in MultiObject Tracking was tracking-by-detection (TbD), where objects are first detected and then associated over video frames. For association, most models resourced to motion and appearance cues, e.g., re-identification networks. Recent approaches based o…

Cited by 86 Source ↗PDF ↗code ↗Scholar ↗