3 papers
cs.CV2022
Interactive Multi-Class Tiny-Object Detection
Chunggi Lee, Seonwook Park, Heon Song +5
Annotating tens or hundreds of tiny objects in a given image is laborious yet crucial for a multitude of Computer Vision tasks. Such imagery typically contains objects from various…
cs.CV2021
Meta-learning of Pooling Layers for Character Recognition
Takato Otsuzuki, Heon Song, Seiichi Uchida +1
In convolutional neural network-based character recognition, pooling layers play an important role in dimensionality reduction and deformation compensation. However, their kernel s…
cs.CV2020
AAA: Adaptive Aggregation of Arbitrary Online Trackers with Theoretical Performance Guarantee
Heon Song, Daiki Suehiro, Seiichi Uchida
For visual object tracking, it is difficult to realize an almighty online tracker due to the huge variations of target appearance depending on an image sequence. This paper propose…