Gabriella: An Online System for Real-Time Activity Detection in Untrimmed Security Videos

Rizve, Mamshad Nayeem; Demir, Uğur; Tirupattur, Praveen; Rana, Aayush Jung; Duarte, Kevin; Dave, Ishan Rajendrakumar; Rawat, Yogesh Singh; Shah, Mubarak

doi:10.1109/icpr48806.2021.9412791

Cited by 8 publications

(1 citation statement)

References 22 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Video understanding is an essential task for security, automation, and robotics (Rizve et al 2021a) as video data enables information extraction for detection (Hou, Sukthankar, and Shah 2017;Yang et al 2019), recognition (Hara, Kataoka, and Satoh 2018;Kumar et al 2023), tracking (Vondrick et al 2018), and scene understanding (Lei et al 2018). Video understanding in general requires a large amount of labeled data to train an effective model.…”

Section: Introductionmentioning

confidence: 99%

Semi-supervised Active Learning for Video Action Detection

Singh,

Rana,

Kumar

et al. 2024

AAAI

View full text Add to dashboard Cite

In this work, we focus on label efficient learning for video action detection. We develop a novel semi-supervised active learning approach which utilizes both labeled as well as un- labeled data along with informative sample selection for ac- tion detection. Video action detection requires spatio-temporal localization along with classification, which poses several challenges for both active learning (informative sample se- lection) as well as semi-supervised learning (pseudo label generation). First, we propose NoiseAug, a simple augmenta- tion strategy which effectively selects informative samples for video action detection. Next, we propose fft-attention, a novel technique based on high-pass filtering which enables effective utilization of pseudo label for SSL in video action detection by emphasizing on relevant activity region within a video. We evaluate the proposed approach on three different bench- mark datasets, UCF-101-24, JHMDB-21, and Youtube-VOS. First, we demonstrate its effectiveness on video action detec- tion where the proposed approach outperforms prior works in semi-supervised and weakly-supervised learning along with several baseline approaches in both UCF101-24 and JHMDB- 21. Next, we also show its effectiveness on Youtube-VOS for video object segmentation demonstrating its generalization capability for other dense prediction tasks in videos.

show abstract