Search Results for author:
Found 10 papers, 3 papers with code
Text-Guided Face Recognition using Multi-Granularity Cross-Modal Contrastive Learning
However, learning a discriminative joint embedding within the multimodal space poses a considerable challenge due to the semantic gap in the unaligned image-text representations, along with the complexities arising from ambiguous and incoherent textual descriptions of the face.
A Universal Anti-Spoofing Approach for Contactless Fingerprint Biometric Systems
Finally, we evaluate the performance of the model using unseen types of spoof attacks and live data.
Synthetic Latent Fingerprint Generation Using Style Transfer
Limited data availability is a challenging problem in the latent fingerprint domain.
Improving Face Recognition from Caption Supervision with Multi-Granular Contextual Feature Aggregation
Additionally, we design a textual feature refinement module (TFRM) that refines the textual features of the pre-trained BERT encoder by updating the contextual embeddings.
Benchmarking Human Face Similarity Using Identical Twins
The proposed network provides a quantitative similarity score for any two given faces and has been applied to large-scale face datasets to identify similar face pairs.
Synthesis-Guided Feature Learning for Cross-Spectral Periocular Recognition
We propose a novel approach to cross-spectral periocular verification that primarily focuses on learning a mapping from visible and NIR periocular images to a shared latent representational subspace, and supports this effort by simultaneously learning intra-spectral image reconstruction.
Deep Hashing for Secure Multimodal Biometrics
The efficacy of the proposed approach is shown using a multimodal database of face and iris and it is observed that the matching performance is improved due to the fusion of multiple biometrics.
Quality Guided Sketch-to-Photo Image Synthesis
We incorporate a hybrid discriminator which performs attribute classification of multiple target attributes, a quality guided encoder that minimizes the perceptual dissimilarity of the latent space embedding of the synthesized and real image at different layers in the network and an identity preserving network that maintains the identity of the synthesised image throughout the training process.
A data-driven proxy to Stoke's flow in porous media
To develop the model, the detailed pore space geometry and simulation runs data from 3500 two-dimensional high-fidelity Lattice Boltzmann simulation runs are used to train and to predict the solutions with a high accuracy in much less computational time.
Learning a Mixture of Deep Networks for Single Image Super-Resolution
This paper proposes the method of learning a mixture of SR inference modules in a unified framework to tackle this problem.
