1 code implementation • 7 Oct 2022 • Andreu Girbau, Ferran Marqués, Shin'ichi Satoh
Current approaches in Multiple Object Tracking (MOT) rely on the spatio-temporal coherence between detections combined with object appearance to match objects from consecutive frames.
Ranked #10 on Multi-Object Tracking on MOT17
no code implementations • 21 Jun 2021 • Andreu Girbau, Xavier Giró-i-Nieto, Ignasi Rius, Ferran Marqués
In this work, we show that trajectory estimation can become a key factor for tracking, and present TrajE, a trajectory estimator based on recurrent mixture density networks, as a generic module that can be added to existing object trackers.
Ranked #26 on Multi-Object Tracking on MOT17 (MOTA metric)
1 code implementation • CVPR 2019 • Carles Ventura, Miriam Bellver, Andreu Girbau, Amaia Salvador, Ferran Marques, Xavier Giro-i-Nieto
Multiple object video object segmentation is a challenging task, specially for the zero-shot case, when no object mask is given at the initial frame and the model has to find the objects to be segmented along the sequence.
Ranked #1 on One-shot visual object segmentation on YouTube-VOS