6 citations · 6 across the 1 of their papers we have counts for
2 papers
cs.CV2022★ 6 cited
MatteFormer: Transformer-Based Image Matting via Prior-Tokens
GyuTae Park, SungJoon Son, JaeYoung Yoo +2
In this paper, we propose a transformer-based image matting model called MatteFormer, which takes full advantage of trimap information in the transformer block. Our method first in…
cs.CV2018
Motion Feature Network: Fixed Motion Filter for Action Recognition
Myunggi Lee, Seungeui Lee, Sungjoon Son +2
Spatio-temporal representations in frame sequences play an important role in the task of action recognition. Previously, a method of using optical flow as a temporal information in…