A comparative study of video-based object recognition from an egocentric viewpoint

Shao, Mang; Tang, Dajun; Yang, Linjun; Kim, Taekyun

doi:10.1016/j.neucom.2015.07.023

Cited by 4 publications

(1 citation statement)

References 48 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…They then measure the betweendistribution similarity to match two image sets. The downside of image set modeling is that it is sensitive to the variable volume of video frames and complex facial variations that exist in real-world scenarios [26].…”

Section: Video-based Face Recognitionmentioning

confidence: 99%

Trunk-Branch Ensemble Convolutional Neural Networks for Video-Based Face Recognition

Ding

Tao

2018

IEEE Trans. Pattern Anal. Mach. Intell.

363

160

View full text Add to dashboard Cite

Abstract-Human faces in surveillance videos often suffer from severe image blur, dramatic pose variations, and occlusion. In this paper, we propose a comprehensive framework based on Convolutional Neural Networks (CNN) to overcome challenges in video-based face recognition (VFR). First, to learn blur-robust face representations, we artificially blur training data composed of clear still images to account for a shortfall in real-world video training data. Using training data composed of both still images and artificially blurred data, CNN is encouraged to learn blurinsensitive features automatically. Second, to enhance robustness of CNN features to pose variations and occlusion, we propose a Trunk-Branch Ensemble CNN model (TBE-CNN), which extracts complementary information from holistic face images and patches cropped around facial components. TBE-CNN is an end-to-end model that extracts features efficiently by sharing the low-and middle-level convolutional layers between the trunk and branch networks. Third, to further promote the discriminative power of the representations learnt by TBE-CNN, we propose an improved triplet loss function. Systematic experiments justify the effectiveness of the proposed techniques. Most impressively, TBE-CNN achieves state-of-the-art performance on three popular video face databases: PaSC, COX Face, and YouTube Faces. With the proposed techniques, we also obtain the first place in the BTAS 2016 Video Person Recognition Evaluation.Index Terms-Video-based face recognition, video surveillance, blur-and pose-robust representations, convolutional neural networks.

show abstract

Section: Video-based Face Recognitionmentioning

confidence: 99%