activity
20182023
most citedA Self-Reasoning Framework for Anomaly Detection Using Video-Level Labels

115 citations · 127 across the 4 of their papers we have counts for

collaborators
Showing cs.CVShow all

12 papers · 1 filter

cs.CV2023

Detection and Localization of Firearm Carriers in Complex Scenes for Improved Safety Measures

Arif Mahmood, Abdul Basit, M. Akhtar Munir +1

Detecting firearms and accurately localizing individuals carrying them in images or videos is of paramount importance in security, surveillance, and content customization. However,…

cs.CV20209 cited

Masked Linear Regression for Learning Local Receptive Fields for Facial Expression Synthesis

Nazar Khan, Arbish Akram, Arif Mahmood +2

Compared to facial expression recognition, expression synthesis requires a very high-dimensional mapping. This problem exacerbates with increasing image sizes and limits existing e…

cs.CV2020115 cited

A Self-Reasoning Framework for Anomaly Detection Using Video-Level Labels

Muhammad Zaigham Zaheer, Arif Mahmood, Hochul Shin +1

Anomalous event detection in surveillance videos is a challenging and practical research problem among image and video processing community. Compared to the frame-level annotations…

cs.CV2020

Cross-modal Speaker Verification and Recognition: A Multilingual Perspective

Muhammad Saad Saeed, Shah Nawaz, Pietro Morerio +4

Recent years have seen a surge in finding association between faces and voices within a cross-modal biometric application along with speaker recognition. Inspired from this, we int…

cs.CV2019

Deep Latent Space Learning for Cross-modal Mapping of Audio and Visual Signals

Shah Nawaz, Muhammad Kamran Janjua, Ignazio Gallo +2

We propose a novel deep training algorithm for joint representation of audio and visual information which consists of a single stream network (SSNet) coupled with a novel loss func…

cs.CV2019

Do Cross Modal Systems Leverage Semantic Relationships?

Shah Nawaz, Muhammad Kamran Janjua, Ignazio Gallo +3

Current cross-modal retrieval systems are evaluated using R@K measure which does not leverage semantic relationships rather strictly follows the manually marked image text query pa…