13 citations · 13 across the 2 of their papers we have counts for
5 papers · 1 filter
Graphhopper: Multi-Hop Scene Graph Reasoning for Visual Question Answering
Rajat Koner, Hang Li, Marcel Hildebrandt +3
Visual Question Answering (VQA) is concerned with answering free-form questions about an image. Since it requires a deep semantic and linguistic understanding of the question and t…
Active learning using weakly supervised signals for quality inspection
Antoine Cordier, Deepan Das, Pierre Gutierrez
Because manufacturing processes evolve fast, and since production visual aspect can vary significantly on a daily basis, the ability to rapidly update machine vision based inspecti…
An Empirical Analysis of the Impact of Data Augmentation on Knowledge Distillation
Deepan Das, Haley Massa, Abhimanyu Kulkarni +1
Generalization Performance of Deep Learning models trained using Empirical Risk Minimization can be improved significantly by using Data Augmentation strategies such as simple tran…
Semi Supervised Phrase Localization in a Bidirectional Caption-Image Retrieval Framework
Deepan Das, Noor Mohammed Ghouse, Shashank Verma +1
We introduce a novel deep neural network architecture that links visual regions to corresponding textual segments including phrases and words. To accomplish this task, our architec…
Unsupervised Anomalous Trajectory Detection for Crowded Scenes
Deepan Das, Deepak Mishra
We present an improved clustering based, unsupervised anomalous trajectory detection algorithm for crowded scenes. The proposed work is based on four major steps, namely, extractio…