no code implementations • 20 Dec 2022 • Dipika Singhania, Rahul Rahaman, Angela Yao
For the task of temporal action segmentation, we propose an encoder-decoder-style architecture named C2F-TCN featuring a "coarse-to-fine" ensemble of decoder outputs.
no code implementations • 20 Jul 2022 • Rahul Rahaman, Dipika Singhania, Alexandre Thiery, Angela Yao
In temporal action segmentation, Timestamp supervision requires only a handful of labelled frames per video sequence.
1 code implementation • 2 Dec 2021 • Dipika Singhania, Rahul Rahaman, Angela Yao
Our method hinges on unsupervised representation learning, which, for temporal action segmentation, poses unique challenges.
1 code implementation • 23 May 2021 • Dipika Singhania, Rahul Rahaman, Angela Yao
In this work, we propose a novel temporal encoder-decoder to tackle the problem of sequence fragmentation.
Ranked #3 on Action Segmentation on Assembly101
no code implementations • 7 Apr 2021 • Rahul Rahaman, Atin Ghosh, Alexandre H. Thiery
Locating semantically meaningful landmark points is a crucial component of a large number of computer vision pipelines.
1 code implementation • NeurIPS 2021 • Rahul Rahaman, Alexandre H. Thiery
In fact, we show that standard ensembling methods, when used in conjunction with modern techniques such as mixup regularization, can lead to less calibrated models.