Search Results for author:
Found 6 papers, 0 papers with code
Fiducial Focus Augmentation for Facial Landmark Detection
To effectively utilize the newly proposed augmentation technique, we employ a Siamese architecture-based training mechanism with a Deep Canonical Correlation Analysis (DCCA)-based loss to achieve collective learning of high-level feature representations from two different views of the input images.
Ranked #1 on
Facial Landmark Detection
on WFLW
Estimation of individual causal effects in network setup for multiple treatments
To measure the representation loss, we extend existing metrics such as Wasserstein and Maximum Mean Discrepancy (MMD) from the binary treatment setting to the multiple treatments scenario.
Revisiting Class Imbalance for End-to-end Semi-Supervised Object Detection
Semi-supervised object detection (SSOD) has made significant progress with the development of pseudo-label-based end-to-end methods.
Nonparallel Emotional Voice Conversion For Unseen Speaker-Emotion Pairs Using Dual Domain Adversarial Network & Virtual Domain Pairing
Primary goal of an emotional voice conversion (EVC) system is to convert the emotion of a given speech signal from one style to another style without modifying the linguistic content of the signal.
M2FNet: Multi-modal Fusion Network for Emotion Recognition in Conversation
We introduce a new feature extractor to extract latent features from the audio and visual modality.
Ranked #15 on
Emotion Recognition in Conversation
on MELD
A Unified Model for Fingerprint Authentication and Presentation Attack Detection
Therefore, rather than performing the two tasks separately, we propose a joint model for spoof detection and matching to simultaneously perform both tasks without compromising the accuracy of either task.
