We propose a novel framework, called Disjoint Mapping Network (DIMNet), for cross-modal biometric matching, in particular of voices and faces. Different from the existing methods …
In this paper, we study the associations between human faces and voices. Audiovisual integration, specifically the integration of facial and vocal information is a well-researched …
H Ning, X Zheng, X Lu, Y Yuan - IEEE Transactions on …, 2021 - ieeexplore.ieee.org
Cross-modal biometric matching (CMBM) aims to determine the corresponding voice from a face, or identify the corresponding face from a voice. Recently, many CMBM methods have …
How much can we infer about a person's looks from the way they speak? In this paper, we study the task of reconstructing a facial image of a person from a short audio recording of …
S Satoh, T Kanade - … of IEEE Computer Society Conference on …, 1997 - ieeexplore.ieee.org
This paper proposes a novel approach to extract meaningful content information from video by collaborative integration of image understanding and natural language processing. As an …
We introduce the visual acoustic matching task, in which an audio clip is transformed to sound like it was recorded in a target environment. Given an image of the target environment …
L Wolf, T Hassner, I Maoz - CVPR 2011, 2011 - ieeexplore.ieee.org
Recognizing faces in unconstrained videos is a task of mounting importance. While obviously related to face recognition in still images, it has its own unique characteristics and …
It is broadly accepted that there is a" gender gap" in| face recognition accuracy, with females having higher false| match and false non-match rates. However, relatively little is known …
X Wu, H Huang, VM Patel, R He, Z Sun - … of the AAAI conference on artificial …, 2019 - aaai.org
Visible (VIS) to near infrared (NIR) face matching is a challenging problem due to the significant domain discrepancy between the domains and a lack of sufficient data for training …