Related papers: Harnessing Geometric Constraints from Emotion Labe…

We present a new technique for learning visual-semantic embeddings for cross-modal retrieval. Inspired by hard negative mining, the use of hard negatives in structured prediction, and ranking loss functions, we introduce a simple change to…

Emotions are subjective constructs. Recent end-to-end speech emotion recognition systems are typically agnostic to the subjective nature of emotions, despite their state-of-the-art performance. In this work, we introduce an end-to-end…

Some of the most severe bottlenecks preventing widespread development of machine learning models for human behavior include a dearth of labeled training data and difficulty of acquiring high quality labels. Active learning is a paradigm for…

Human emotion recognition holds a pivotal role in facilitating seamless human-computer interaction. This paper delineates our methodology in tackling the Valence-Arousal (VA) Estimation Challenge, Expression (Expr) Classification Challenge,…

Metric learning has become an attractive field for research on the latest years. Loss functions like contrastive loss, triplet loss or multi-class N-pair loss have made possible generating models capable of tackling complex scenarios with…

We propose a novel loss function that dynamically rescales the cross entropy based on prediction difficulty regarding a sample. Deep neural network architectures in image classification tasks struggle to disambiguate visually similar…

The task of predicting affective information in the wild such as seven basic emotions or action units from human faces has gradually become more interesting due to the accessibility and availability of massive annotated datasets. In this…

Few-shot learning (FSL) is a challenging task in machine learning, demanding a model to render discriminative classification by using only a few labeled samples. In the literature of FSL, deep models are trained in a manner of metric…

A variety of modern applications exhibit multi-view multi-label learning, where each sample has multi-view features, and multiple labels are correlated via common views. Current methods usually fail to directly deal with the setting where…

The common implementation of face recognition systems as a cascade of a detection stage and a recognition or verification stage can cause problems beyond failures of the detector. When the detector succeeds, it can detect faces that cannot…

For training a video-based action recognition model that accepts multi-view video, annotating frame-level labels is tedious and difficult. However, it is relatively easy to annotate sequence-level labels. This kind of coarse annotations are…

Labeling and maintaining a commercial sound effects library is a time-consuming task exacerbated by databases that continually grow in size and undergo taxonomy updates. Moreover, sound search and taxonomy creation are complicated by…

Deep neural networks have dramatically advanced the state of the art for many areas of machine learning. Recently they have been shown to have a remarkable ability to generate highly complex visual artifacts such as images and text rather…

Due to the lack of large-scale datasets, the prevailing approach in visual sentiment analysis is to leverage models trained for object classification in large datasets like ImageNet. However, objects are sentiment neutral which hinders the…

Classification of human emotions remains an important and challenging task for many computer vision algorithms, especially in the era of humanoid robots which coexist with humans in their everyday life. Currently proposed methods for…

This paper pays close attention to the cross-modality visible-infrared person re-identification (VI Re-ID) task, which aims to match pedestrian samples between visible and infrared modes. In order to reduce the modality-discrepancy between…

Recent works have shown that deep metric learning algorithms can benefit from weak supervision from another input modality. This additional modality can be incorporated directly into the popular triplet-based loss function as distances.…

While recent advances in deep learning have led to significant improvements in facial expression classification (FEC), a major challenge that remains a bottleneck for the widespread deployment of such systems is their high architectural and…

Photometric loss is widely used for self-supervised depth and egomotion estimation. However, the loss landscapes induced by photometric differences are often problematic for optimization, caused by plateau landscapes for pixels in…

Attribute recognition, particularly facial, extracts many labels for each image. While some multi-task vision problems can be decomposed into separate tasks and stages, e.g., training independent models for each task, for a growing set of…