4 citations · 9 across the 8 of their papers we have counts for
12 papers
Narrative Aligned Long Form Video Question Answering
Rahul Jain, Keval Doshi, Burak Uzkent +1
Recent progress in multimodal large language models (MLLMs) has led to a surge of benchmarks for long-video reasoning. However, most existing benchmarks rely on localized cues and…
Adversarial Machine Learning Attacks Against Video Anomaly Detection Systems
Furkan Mumcu, Keval Doshi, Yasin Yilmaz
Anomaly detection in videos is an important computer vision problem with various applications including automated video surveillance. Although adversarial attacks on image understa…
TiSAT: Time Series Anomaly Transformer
Keval Doshi, Shatha Abudalou, Yasin Yilmaz
While anomaly detection in time series has been an active area of research for several years, most recent approaches employ an inadequate evaluation criterion leading to an inflate…
End-to-End Semantic Video Transformer for Zero-Shot Action Recognition
Keval Doshi, Yasin Yilmaz
While video action recognition has been an active area of research for several years, zero-shot action recognition has only recently started gaining traction. In this work, we prop…
An Efficient Approach for Anomaly Detection in Traffic Videos
Keval Doshi, Yasin Yilmaz
Due to its relevance in intelligent transportation systems, anomaly detection in traffic videos has recently received much interest. It remains a difficult problem due to a variety…
A Modular and Unified Framework for Detecting and Localizing Video Anomalies
Keval Doshi, Yasin Yilmaz
Anomaly detection in videos has been attracting an increasing amount of attention. Despite the competitive performance of recent methods on benchmark datasets, they typically lack…