12 citations · 13 across the 3 of their papers we have counts for
3 papers
cs.RO2020★ 12 cited
Topological Planning with Transformers for Vision-and-Language Navigation
Kevin Chen, Junshen K. Chen, Jo Chuang +2
Conventional approaches to vision-and-language navigation (VLN) are trained end-to-end but struggle to perform well in freely traversable environments. Inspired by the robotics com…
cs.CV2020
JIT-Masker: Efficient Online Distillation for Background Matting
Jo Chuang, Qian Dong
We design a real-time portrait matting pipeline for everyday use, particularly for "virtual backgrounds" in video conferences. Existing segmentation and matting methods prioritize…
cs.CV2018★ 1 cited
ParaNet - Using Dense Blocks for Early Inference
Joseph Chuang, Eric Tsai, Kevin Huang +1
DenseNets have been shown to be a competitive model among recent convolutional network architectures. These networks utilize Dense Blocks, which are groups of densely connected lay…