activity
20182021
most citedUnsupervised Transfer Learning for Spatiotemporal Predictive Networks

7 citations · 9 across the 3 of their papers we have counts for

collaborators

5 papers

cs.LG20211 cited

ModeRNN: Harnessing Spatiotemporal Mode Collapse in Unsupervised Predictive Learning

Zhiyu Yao, Yunbo Wang, Haixu Wu +2

Learning predictive models for unlabeled spatiotemporal data is challenging in part because visual dynamics can be highly entangled in real scenes, making existing approaches prone…

cs.CV2021

MotionRNN: A Flexible Model for Video Prediction with Spacetime-Varying Motions

Haixu Wu, Zhiyu Yao, Jianmin Wang +1

This paper tackles video prediction from a new dimension of predicting spacetime-varying motions that are incessantly changing across both space and time. Prior methods mainly capt…

cs.CV20201 cited

Towards Good Practices of U-Net for Traffic Forecasting

Jingwei Xu, Jianjin Zhang, Zhiyu Yao +1

This technical report presents a solution for the 2020 Traffic4Cast Challenge. We consider the traffic forecasting problem as a future frame prediction task with relatively weak te…

cs.LG20207 cited

Unsupervised Transfer Learning for Spatiotemporal Predictive Networks

Zhiyu Yao, Yunbo Wang, Mingsheng Long +1

This paper explores a new research problem of unsupervised transfer learning across multiple spatiotemporal prediction tasks. Unlike most existing transfer learning methods that fo…

cs.CV2018

Multi-Task Learning of Generalizable Representations for Video Action Recognition

Zhiyu Yao, Yunbo Wang, Mingsheng Long +3

In classic video action recognition, labels may not contain enough information about the diverse video appearance and dynamics, thus, existing models that are trained under the sta…