no code implementations • 30 Jan 2024 • Mehdi Noroozi, Isma Hadji, Brais Martinez, Adrian Bulat, Georgios Tzimiropoulos
We show that the combination of spatially distilled U-Net and fine-tuned decoder outperforms state-of-the-art methods requiring 200 steps with only one single step.
2 code implementations • 1 Sep 2022 • Nadine Behrmann, S. Alireza Golestaneh, Zico Kolter, Juergen Gall, Mehdi Noroozi
This paper introduces a unified framework for video action segmentation via sequence to sequence (seq2seq) translation in a fully and timestamp supervised setup.
Ranked #4 on Action Segmentation on Assembly101
1 code implementation • 27 Jan 2022 • David T. Hoffmann, Nadine Behrmann, Juergen Gall, Thomas Brox, Mehdi Noroozi
This paper introduces Ranking Info Noise Contrastive Estimation (RINCE), a new member in the family of InfoNCE losses that preserves a ranked ordering of positive samples.
no code implementations • 27 Oct 2021 • Saber Pourheydari, Emad Bahrami, Mohsen Fayyaz, Gianpiero Francesca, Mehdi Noroozi, Juergen Gall
While recurrent neural networks (RNNs) demonstrate outstanding capabilities for future video frame prediction, they model dynamics in a discrete time space, i. e., they predict the frames sequentially with a fixed temporal step.
no code implementations • ICCV 2021 • Nadine Behrmann, Mohsen Fayyaz, Juergen Gall, Mehdi Noroozi
We argue that a single representation to capture both types of features is sub-optimal, and propose to decompose the representation space into stationary and non-stationary features via contrastive learning from long and short views, i. e. long video sequences and their shorter sub-sequences.
no code implementations • 3 Dec 2020 • Mehdi Noroozi
This paper introduces a novel and fully unsupervised framework for conditional GAN training in which labels are automatically obtained from data.
1 code implementation • CVPR 2021 • Mohsen Fayyaz, Emad Bahrami, Ali Diba, Mehdi Noroozi, Ehsan Adeli, Luc van Gool, Juergen Gall
While the GFLOPs of a 3D CNN can be decreased by reducing the temporal feature resolution within the network, there is no setting that is optimal for all input clips.
no code implementations • 11 Nov 2020 • Nadine Behrmann, Juergen Gall, Mehdi Noroozi
This paper introduces a novel method for self-supervised video representation learning via feature prediction.
no code implementations • CVPR 2018 • Mehdi Noroozi, Ananth Vinjimoor, Paolo Favaro, Hamed Pirsiavash
We use this framework to design a novel self-supervised task, which achieves state-of-the-art performance on the common benchmarks in PASCAL VOC 2007, ILSVRC12 and Places by a significant margin.
2 code implementations • ICCV 2017 • Mehdi Noroozi, Hamed Pirsiavash, Paolo Favaro
In this paper, we use two image transformations in the context of counting: scaling and tiling.
no code implementations • 22 Aug 2017 • Paramanand Chandramouli, Mehdi Noroozi, Paolo Favaro
In this paper, we address the problem of reflection removal and deblurring from a single image captured by a plenoptic camera.
no code implementations • 5 Jan 2017 • Mehdi Noroozi, Paramanand Chandramouli, Paolo Favaro
The task of image deblurring is a very ill-posed problem as both the image and the blur are unknown.
9 code implementations • 30 Mar 2016 • Mehdi Noroozi, Paolo Favaro
By following the principles of self-supervision, we build a convolutional neural network (CNN) that can be trained to solve Jigsaw puzzles as a pretext task, which requires no manual labeling, and then later repurposed to solve object classification and detection.