Search Results for author:
Found 10 papers, 4 papers with code
Multi-Task Multi-Modal Self-Supervised Learning for Facial Expression Recognition
To that end, we examine the performance of learning through different combinations of self-supervised tasks on the facial expression recognition downstream task.
Ranked #1 on
Emotion Recognition in Conversation
on MELD
(Weighted Accuracy metric)
Emotion Classification
Emotion Recognition in Conversation
+2
Decomposer: Semi-supervised Learning of Image Restoration and Image Decomposition
We present Decomposer, a semi-supervised reconstruction model that decomposes distorted image sequences into their fundamental building blocks - the original image and the applied augmentations, i. e., shadow, light, and occlusions.
DIAR: Deep Image Alignment and Reconstruction using Swin Transformers
When taking images of some occluded content, one is often faced with the problem that every individual image frame contains unwanted artifacts, but a collection of images contains all relevant information if properly aligned and aggregated.
SIDAR: Synthetic Image Dataset for Alignment & Restoration
Our data generation pipeline is customizable and can be applied to any existing dataset, serving as a data augmentation to further improve the feature learning of any existing method.
Image-based Detection of Surface Defects in Concrete during Construction
Our experiments demonstrate that both approaches are suitable for solving and automating honeycomb detection.
Content-Based Landmark Retrieval Combining Global and Local Features using Siamese Neural Networks
A Siamese network is used for global feature extraction and metric learning, which gives an initial ranking of the landmark search.
Action-based Contrastive Learning for Trajectory Prediction
To that end, we propose a novel action-based contrastive learning loss, that utilizes pedestrian action information to improve the learned trajectory embeddings.
A modular framework for object-based saccadic decisions in dynamic scenes
We model this active scene exploration as a sequential decision making process.
Learning Disentangled Expression Representations from Facial Images
One common strategy to tackle such a problem is to learn disentangled representations for the different factors of variation of the observed data using adversarial learning.
Iterative Bilateral Filtering of Polarimetric SAR Data
In this paper, we introduce an iterative speckle filtering method for polarimetric SAR (PolSAR) images based on the bilateral filter.
