COMET: Context-aware IoU-guided network for small object tracking
SM Marvasti-Zadeh, J Khaghani… - Proceedings of the …, 2020 - openaccess.thecvf.com
We consider the problem of tracking an unknown small target from aerial videos of medium
to high altitudes. This is a challenging problem, which is even more pronounced in
unavoidable scenarios of drastic camera motion and high density. To address this problem,
we introduce a context-aware IoU-guided tracker (COMET) that exploits a multitask two-
stream network and an offline reference proposal generation strategy. The proposed
network fully exploits target-related information by multi-scale feature learning and attention …
to high altitudes. This is a challenging problem, which is even more pronounced in
unavoidable scenarios of drastic camera motion and high density. To address this problem,
we introduce a context-aware IoU-guided tracker (COMET) that exploits a multitask two-
stream network and an offline reference proposal generation strategy. The proposed
network fully exploits target-related information by multi-scale feature learning and attention …
COMET: Context-Aware IoU-Guided Network for Small Object Tracking
S Mojtaba Marvasti-Zadeh, J Khaghani… - arXiv e …, 2020 - ui.adsabs.harvard.edu
We consider the problem of tracking an unknown small target from aerial videos of medium
to high altitudes. This is a challenging problem, which is even more pronounced in
unavoidable scenarios of drastic camera motion and high density. To address this problem,
we introduce a context-aware IoU-guided tracker (COMET) that exploits a multitask two-
stream network and an offline reference proposal generation strategy. The proposed
network fully exploits target-related information by multi-scale feature learning and attention …
to high altitudes. This is a challenging problem, which is even more pronounced in
unavoidable scenarios of drastic camera motion and high density. To address this problem,
we introduce a context-aware IoU-guided tracker (COMET) that exploits a multitask two-
stream network and an offline reference proposal generation strategy. The proposed
network fully exploits target-related information by multi-scale feature learning and attention …
Showing the best results for this search. See all results