Search Results for author: Shuzhi Yu

Found 6 papers, 1 papers with code

Unsupervised Flow Refinement near Motion Boundaries

no code implementations3 Aug 2022 Shuzhi Yu, Hannah Halin Kim, Shuai Yuan, Carlo Tomasi

Unsupervised optical flow estimators based on deep learning have attracted increasing attention due to the cost and difficulty of annotating for ground truth.

Optical Flow Estimation

Cross-Attention Transformer for Video Interpolation

no code implementations8 Jul 2022 Hannah Halin Kim, Shuzhi Yu, Shuai Yuan, Carlo Tomasi

To account for occlusions in the CS features, we propose an Image Attention (IA) module to allow the network to focus on CS features from one frame over those of the other.

TDT: Teaching Detectors to Track without Fully Annotated Videos

no code implementations11 May 2022 Shuzhi Yu, Guanhang Wu, Chunhui Gu, Mohammed E. Fathy

However, their success depends on the availability of videos that are fully annotated with tracking data, which is expensive and hard to obtain.

Multi-Object Tracking

Optical Flow Training under Limited Label Budget via Active Learning

no code implementations9 Mar 2022 Shuai Yuan, Xian Sun, Hannah Kim, Shuzhi Yu, Carlo Tomasi

Our experiments on both synthetic and real optical flow datasets show that our semi-supervised networks generally need around 50% of the labels to achieve close to full-label accuracy, and only around 20% with active learning on Sintel.

Active Learning Optical Flow Estimation

Joint Detection of Motion Boundaries and Occlusions

1 code implementation1 Nov 2021 Hannah Halin Kim, Shuzhi Yu, Carlo Tomasi

Since appearance mismatches between frames often signal vicinity to MBs or Occs, we construct a cost block that for each feature in one frame records the lowest discrepancy with matching features in a search range.

Optical Flow Estimation

Identity Connections in Residual Nets Improve Noise Stability

no code implementations27 May 2019 Shuzhi Yu, Carlo Tomasi

Residual Neural Networks (ResNets) achieve state-of-the-art performance in many computer vision problems.

Cannot find the paper you are looking for? You can Submit a new open access paper.