Related papers: Consistency and Accuracy of CelebA Attribute Value…

Multimodal AI systems are evaluated by downstream task accuracy, but high accuracy does not mean the underlying data is coherent. A model can score well on Visual Question Answering (VQA) while its inputs contradict each other. We introduce…

In this article we propose a method for the recognition of faces with different facial expressions. For recognition we extract feature vectors by using log-Gabor filters of multiple orientations and scales. Using sliding window algorithm…

In recent years, media reports have called out bias and racism in face recognition technology. We review experimental results exploring several speculated causes for asymmetric cross-demographic performance. We consider accuracy differences…

In this paper, we evaluate the effects of occlusions in the performance of a face recognition pipeline that uses a ResNet backbone. The classifier was trained on a subset of the CelebA-HQ dataset containing 5,478 images from 307 classes, to…

Facial attribute analysis in the real world scenario is very challenging mainly because of complex face variations. Existing works of analyzing face attributes are mostly based on the cropped and aligned face images. However, this result in…

Measuring the accuracy of face recognition (FR) systems is essential for improving performance and ensuring responsible use. Accuracy is typically estimated using large annotated datasets, which are costly and difficult to obtain. We…

Strong lensed quasi-stellar objects (QSOs) are valuable probes of the universe in numerous aspects. Two of these applications, reverberation mapping and measuring time delays for determining cosmological parameters, require the source QSOs…

The proliferation of highly realistic facial forgeries necessitates robust detection methods. However, existing approaches often suffer from limited accuracy and poor generalization due to significant distribution shifts among samples…

Deep learning approaches achieve state-of-the-art performance for classifying radiology images, but rely on large labelled datasets that require resource-intensive annotation by specialists. Both semi-supervised learning and active learning…

The SOTA face swap models still suffer the problem of either target identity (i.e., shape) being leaked or the target non-identity attributes (i.e., background, hair) failing to be fully preserved in the final results. We show that this…

Balancing computational efficiency with recognition accuracy is one of the major challenges in real-world video-based face recognition. A significant design decision for any such system is whether to process and use all possible faces…

In this paper, we propose to employ semantic segmentation to improve person-related attribute prediction. The core idea lies in the fact that the probability of an attribute to appear in an image is far from being uniform in the spatial…

Deep neural networks often inherit social and demographic biases from annotated data during model training, leading to unfair predictions, especially in the presence of sensitive attributes like race, age, gender etc. Existing methods fall…

Machine learning applications in high-stakes scenarios should always operate under human oversight. Developing an optimal combination of human and machine intelligence requires an understanding of their complementarities, particularly…

Accurate facial expression analysis is an essential step in various clinical applications that involve physical and mental health assessments of older adults (e.g. diagnosis of pain or depression). Although remarkable progress has been…

Educational aspect-based sentiment analysis (ABSA) can support course improvement, but public aspect-labeled student feedback remains scarce because educational reviews are private, institution-specific, and expensive to annotate. This…

Aspect-based sentiment analysis (ABSA) is a natural language processing problem that requires analyzing user-generated reviews to determine: a) The target entity being reviewed, b) The high-level aspect to which it belongs, and c) The…

Recent advances in foundation models present new opportunities for interpretable visual recognition -- one can first query Large Language Models (LLMs) to obtain a set of attributes that describe each class, then apply vision-language…

This work explores facial expression bias as a security vulnerability of face recognition systems. Despite the great performance achieved by state-of-the-art face recognition systems, the algorithms are still sensitive to a large range of…

Despite recent advances in face recognition, robust performance remains challenging under large variations in age, pose, and occlusion. A common strategy to address these issues is to guide representation learning with auxiliary supervision…