Transforming Model Prediction for Tracking

1 code implementation • CVPR 2022 • Christoph Mayer, Martin Danelljan, Goutam Bhat, Matthieu Paul, Danda Pani Paudel, Fisher Yu, Luc van Gool

Optimization based tracking methods have been widely successful by integrating a target model prediction module, providing effective global reasoning by minimizing an objective function.

Inductive Bias Visual Object Tracking

Robust Visual Tracking by Segmentation

2 code implementations • 21 Mar 2022 • Matthieu Paul, Martin Danelljan, Christoph Mayer, Luc van Gool

We infer a bounding box from the segmentation mask, validate our tracker on challenging tracking datasets and achieve the new state of the art on LaSOT with a success AUC score of 69. 7%.

Segmentation Semantic Segmentation +4

Local Memory Attention for Fast Video Semantic Segmentation

1 code implementation • 5 Jan 2021 • Matthieu Paul, Martin Danelljan, Luc van Gool, Radu Timofte

Our approach aggregates a rich representation of the semantic information in past frames into a memory module.

Segmentation Semantic Segmentation +1

Efficient Video Semantic Segmentation with Labels Propagation and Refinement

no code implementations • 26 Dec 2019 • Matthieu Paul, Christoph Mayer, Luc van Gool, Radu Timofte

(ii) On the GPU, two Convolutional Neural Networks: A main segmentation network that is used to predict dense semantic labels from scratch, and a Refiner that is designed to improve predictions from previous frames with the help of a fast Inconsistencies Attention Module (IAM).

Image Segmentation Optical Flow Estimation +5

Adversarial Feature Distribution Alignment for Semi-Supervised Learning

no code implementations • 22 Dec 2019 • Christoph Mayer, Matthieu Paul, Radu Timofte

We test our method on CIFAR10 and SVHN.