Using 20 past frames as temporal context improves soccer ball detection recall by about 1.5 points over a single-frame detector, with a temporal convolutional network giving the fastest inference.
In: Proceedings of 10th Workshop on Hu- manoid Soccer Robots, IEEE-RAS Int
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CV 1years
2019 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Utilizing Temporal Information in Deep Convolutional Network for Efficient Soccer Ball Detection and Tracking
Using 20 past frames as temporal context improves soccer ball detection recall by about 1.5 points over a single-frame detector, with a temporal convolutional network giving the fastest inference.