Search Results for author: Rahul Rama Varior

Found 6 papers, 0 papers with code

Understanding the impact of mistakes on background regions in crowd counting

no code implementations30 Mar 2020 Davide Modolo, Bing Shuai, Rahul Rama Varior, Joseph Tighe

Our results show that (i) mistakes on background are substantial and they are responsible for 18-49% of the total error, (ii) models do not generalize well to different kinds of backgrounds and perform poorly on completely background images, and (iii) models make many more mistakes than those captured by the standard Mean Absolute Error (MAE) metric, as counting on background compensates considerably for misses on foreground.

Crowd Counting

Multi-Scale Attention Network for Crowd Counting

no code implementations17 Jan 2019 Rahul Rama Varior, Bing Shuai, Joseph Tighe, Davide Modolo

In crowd counting datasets, people appear at different scales, depending on their distance from the camera.

Crowd Counting

A Siamese Long Short-Term Memory Architecture for Human Re-Identification

no code implementations European Conference on Computer Vision 2016 Rahul Rama Varior, Bing Shuai, Jiwen Lu, Dong Xu, Gang Wang

Matching pedestrians across multiple camera views known as human re-identification (re-identification) is a challenging problem in visual surveillance.

Person Re-Identification

Gated Siamese Convolutional Neural Network Architecture for Human Re-Identification

no code implementations28 Jul 2016 Rahul Rama Varior, Mrinal Haloi, Gang Wang

However, current networks extract fixed representations for each image regardless of other images which are paired with it and the comparison with other images is done only at the final level.

Person Re-Identification

Hierarchical Invariant Feature Learning with Marginalization for Person Re-Identification

no code implementations30 Nov 2015 Rahul Rama Varior, Gang Wang

This paper addresses the problem of matching pedestrians across multiple camera views, known as person re-identification.

Metric Learning Person Re-Identification

Learning Invariant Color Features for Person Re-Identification

no code implementations4 Oct 2014 Rahul Rama Varior, Gang Wang, Jiwen Lu

We model color feature generation as a learning problem by jointly learning a linear transformation and a dictionary to encode pixel values.

Person Re-Identification

Cannot find the paper you are looking for? You can Submit a new open access paper.