Earticle

초록

영어

Recognizing anomalies in surveillance is crucial for public safety to identify events that deviate from normal patterns. Visual information is essential for effective anomaly recognition; however, audio data can enhance recognition accuracy by providing additional context. Despite this, existing systems only utilize visual information, overlooking the potential of audio modalities in anomaly recognition. This paper introduces a multi-modal framework for anomaly recognition through active learning, integrating audio and visual modalities to enhance anomaly prediction. The framework extracts features using a pretrained ResNet-50 convolutional neural network (CNN) model from the visual and audio data. The extracted features are then forwarded to the Bi-Directional Long Short-Term Memory (Bi-LSTM) network for temporal feature learning. These features are then fused and fed into a classification layer for final prediction. The proposed framework's performance is assessed on a benchmark dataset and yields promising results.

목차

Abstract
1. INTRODUCTION
2. METHODOLOGY
2.1 Feature Extraction
2.2 Sequential Models
2.3 Fusion Mechanism and Classification Layer
3. EXPERIMENTAL RESULTS
3.1. Comparative Analysis
4. CONCLUSION
ACKNOWLEDGMENT
REFERENCES

키워드

저자

• Amjid Ali [ Sejong University ]
• Noman Khan [ Sejong University ]
• Zulfiqar Ahmad Khan [ Sejong University ]
• Su Min Lee [ Sejong University ]
• Min Je Kim [ Sejong University ]
• Sung Wook Baik [ Sejong University ] Corresponding Author

참고문헌

발행기관

간행물

표지보기 관심저널 등록

• 간행물명

  한국차세대컴퓨팅학회 학술대회

• 간기

  반년간

• 수록기간

  2021~2025

• 십진분류

  KDC 566 DDC 004