activity
20162020
most citedTemporal 3D ConvNets: New Architecture and Transfer Learning for Video Classification

187 citations · 192 across the 2 of their papers we have counts for

collaborators

7 papers

cs.CV20205 cited

Self-Supervised Ranking for Representation Learning

Ali Varamesh, Ali Diba, Tinne Tuytelaars +1

We present a new framework for self-supervised representation learning by formulating it as a ranking problem in an image retrieval context on a large number of random views (augme…

cs.CV2020

3D CNNs with Adaptive Temporal Feature Resolutions

Mohsen Fayyaz, Emad Bahrami, Ali Diba +4

While state-of-the-art 3D Convolutional Neural Networks (CNN) achieve very good results on action recognition datasets, they are computationally very expensive and require many GFL…

cs.CV2019

DynamoNet: Dynamic Action and Motion Network

Ali Diba, Vivek Sharma, Luc Van Gool +1

In this paper, we are interested in self-supervised learning the motion cues in videos using dynamic motion filters for a better motion representation to finally boost human action…

cs.CV2019

Large Scale Holistic Video Understanding

Ali Diba, Mohsen Fayyaz, Vivek Sharma +4

Video recognition has been advanced in recent years by benchmarks with rich annotations. However, research is still mainly limited to human action or sports recognition - focusing…

cs.CV2018

Spatio-Temporal Channel Correlation Networks for Action Classification

Ali Diba, Mohsen Fayyaz, Vivek Sharma +4

The work in this paper is driven by the question if spatio-temporal correlations are enough for 3D convolutional neural networks (CNN)? Most of the traditional 3D networks use loca…

cs.CV2017187 cited

Temporal 3D ConvNets: New Architecture and Transfer Learning for Video Classification

Ali Diba, Mohsen Fayyaz, Vivek Sharma +4

The work in this paper is driven by the question how to exploit the temporal cues available in videos for their accurate classification, and for human action recognition in particu…