Prototypical Cross-Attention Networks for Multiple Object Tracking and Segmentation
Open access
Datum
2021Typ
- Conference Paper
ETH Bibliographie
yes
Altmetrics
Abstract
Multiple object tracking and segmentation requires detecting, tracking, and segmenting objects belonging to a set of given classes. Most approaches only exploit the temporal dimension to address the association problem, while relying on single frame predictions for the segmentation mask itself. We propose Prototypical Cross-Attention Network (PCAN), capable of leveraging rich spatio-temporal information for online multiple object tracking and segmentation. PCAN first distills a space-time memory into a set of prototypes and then employs cross-attention to retrieve rich information from the past frames. To segment each object, PCAN adopts a prototypical appearance module to learn a set of contrastive foreground and background prototypes, which are then propagated over time. Extensive experiments demonstrate that PCAN outperforms current video instance tracking and segmentation competition winners on both Youtube-VIS and BDD100K datasets, and shows efficacy to both one-stage and two-stage segmentation frameworks. Code and video resources are available at http://vis.xyz/pub/pcan. Mehr anzeigen
Persistenter Link
https://doi.org/10.3929/ethz-b-000517118Publikationsstatus
publishedHerausgeber(in)
Buchtitel
Advances in Neural Information Processing Systems 34Seiten / Artikelnummer
Verlag
CurranKonferenz
Organisationseinheit
09688 - Yu, Fisher / Yu, Fisher
Anmerkungen
Conference lecture held at the poster session on December 8, 2021ETH Bibliographie
yes
Altmetrics