activity
20162021
most citedTemporal 3D ConvNets: New Architecture and Transfer Learning for Video Classification

187 citations · 221 across the 8 of their papers we have counts for

collaborators
Showing cs.CVShow all

14 papers · 1 filter

cs.CV2021

Temporally-Weighted Hierarchical Clustering for Unsupervised Action Segmentation

M. Saquib Sarfraz, Naila Murray, Vivek Sharma +3

Action segmentation refers to inferring boundaries of semantically consistent visual concepts in videos and is an important requirement for many video understanding tasks. For this…

cs.CV2020

DISCO: Dynamic and Invariant Sensitive Channel Obfuscation for deep neural networks

Abhishek Singh, Ayush Chopra, Vivek Sharma +4

Recent deep learning models have shown remarkable performance in image classification. While these deep learning systems are getting closer to practical deployment, the common assu…

cs.CV20206 cited

Deep Multimodal Feature Encoding for Video Ordering

Vivek Sharma, Makarand Tapaswi, Rainer Stiefelhagen

True understanding of videos comes from a joint analysis of all its modalities: the video frames, the audio track, and any accompanying text such as closed captions. We present a w…

cs.CV2020

Clustering based Contrastive Learning for Improving Face Representations

Vivek Sharma, Makarand Tapaswi, M. Saquib Sarfraz +1

A good clustering algorithm can discover natural groupings in data. These groupings, if used wisely, provide a form of weak supervision for learning representations. In this work,…

cs.CV20197 cited

ExpertMatcher: Automating ML Model Selection for Clients using Hidden Representations

Vivek Sharma, Praneeth Vepakomma, Tristan Swedish +3

Recently, there has been the development of Split Learning, a framework for distributed computation where model components are split between the client and server (Vepakomma et al.…

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…