1 code implementation • ICCV 2023 • Si-Cun Chen, Yi-Hsin Chen, Yen-Yu Lin, Wen-Hsiao Peng
We motivate the use of forward motion from the perspective of learning individual motion trajectories, as opposed to learning a mixture of motion trajectories with backward motion.
1 code implementation • 16 Mar 2021 • Shih-Po Lee, Si-Cun Chen, Wen-Hsiao Peng
Moreover, we introduce a guided spatially-varying convolution for fusing segmentations derived from the previous and current frames, to mitigate propagation error and enable lightweight feature extraction on non-keyframes.