activity
20182021
most citedIn Defense of Pseudo-Labeling: An Uncertainty-Aware Pseudo-label Selection Framework for Semi-Supervised Learning

73 citations · 73 across the 3 of their papers we have counts for

collaborators

9 papers

cs.CV2021

PLM: Partial Label Masking for Imbalanced Multi-label Classification

Kevin Duarte, Yogesh S. Rawat, Mubarak Shah

Neural networks trained on real-world datasets with long-tailed label distributions are biased towards frequent classes and perform poorly on infrequent classes. The imbalance in t…

cs.CV2021

Found a Reason for me? Weakly-supervised Grounded Visual Question Answering using Capsules

Aisha Urooj Khan, Hilde Kuehne, Kevin Duarte +3

The problem of grounding VQA tasks has seen an increased attention in the research community recently, with most attempts usually focusing on solving this task by using pretrained…

cs.CV2021

Multimodal Clustering Networks for Self-supervised Learning from Unlabeled Videos

Brian Chen, Andrew Rouditchenko, Kevin Duarte +10

Multimodal self-supervised learning is getting more and more attention as it allows not only to train large networks without human supervision but also to search and retrieve data…

cs.CV2021

Modeling Multi-Label Action Dependencies for Temporal Action Localization

Praveen Tirupattur, Kevin Duarte, Yogesh Rawat +1

Real-world videos contain many complex actions with inherent relationships between action classes. In this work, we propose an attention-based architecture that models these action…

cs.LG202173 cited

In Defense of Pseudo-Labeling: An Uncertainty-Aware Pseudo-label Selection Framework for Semi-Supervised Learning

Mamshad Nayeem Rizve, Kevin Duarte, Yogesh S Rawat +1

The recent research in semi-supervised learning (SSL) is mostly dominated by consistency regularization based methods which achieve strong performance. However, they heavily rely o…

cs.CV2020

Gabriella: An Online System for Real-Time Activity Detection in Untrimmed Security Videos

Mamshad Nayeem Rizve, Ugur Demir, Praveen Tirupattur +5

Activity detection in security videos is a difficult problem due to multiple factors such as large field of view, presence of multiple activities, varying scales and viewpoints, an…