Related papers: Underage Detection through a Multi-Task and MultiA…

One of the main motivations of MTL is to develop neural networks capable of inferring multiple tasks simultaneously. While countless methods have been proposed in the past decade investigating robust model architectures and efficient…

Face Anti-spoofing (FAS) is a challenging problem due to complex serving scenarios and diverse face presentation attack patterns. Especially when captured images are low-resolution, blurry, and coming from different domains, the performance…

Large-scale pre-trained models have achieved remarkable success in language and image tasks, leading an increasing number of studies to explore the application of pre-trained image models, such as CLIP, in the domain of few-shot action…

Facial expression data is characterized by a significant imbalance, with most collected data showing happy or neutral expressions and fewer instances of fear or disgust. This imbalance poses challenges to facial expression recognition (FER)…

Face recognition has the perception of a solved problem, however when tested at the million-scale exhibits dramatic variation in accuracies across the different algorithms. Are the algorithms very different? Is access to good/big training…

Prior work has shown that Visual Recognition datasets frequently underrepresent bias groups $B$ (\eg Female) within class labels $Y$ (\eg Programmers). This dataset bias can lead to models that learn spurious correlations between class…

Recent contrastive multimodal vision-language models like CLIP have demonstrated robust open-world semantic understanding, becoming the standard image backbones for vision-language applications. However, recent findings suggest high…

Automatic Speech Recognition (ASR) systems are known to exhibit difficulties when transcribing children's speech. This can mainly be attributed to the absence of large children's speech corpora to train robust ASR models and the resulting…

We propose using performance metrics derived from zero-failure testing to assess binary classifiers. The principal characteristic of the proposed approach is the asymmetric treatment of the two types of error. In particular, we construct a…

Real-world datasets are often biased with respect to key demographic factors such as race and gender. Due to the latent nature of the underlying factors, detecting and mitigating bias is especially challenging for unsupervised machine…

The rise of generative models has raised concerns about image authenticity online, highlighting the urgent need for a detector that is (1) highly generalizable, capable of handling unseen forgery techniques, and (2) data-efficient,…

We image 104 newly identified low-mass (mostly M-dwarf) pre-main sequence members of nearby young moving groups with Magellan Adaptive Optics (MagAO) and identify 27 binaries with instantaneous projected separation as small as 40 mas. 15…

Real-world surveillance often renders faces and license plates unrecognizable in individual low-resolution (LR) frames, hindering reliable identification. To advance temporal recognition models, we present FANVID, a novel video-based…

Detecting deepfake images is crucial in combating misinformation. We present a lightweight, generalizable binary classification model based on EfficientNet-B6, fine-tuned with transformation techniques to address severe class imbalances. By…

Current multilingual vision-language models either require a large number of additional parameters for each supported language, or suffer performance degradation as languages are added. In this paper, we propose a Scalable Multilingual…

Presently, the task of few-shot object detection (FSOD) in remote sensing images (RSIs) has become a focal point of attention. Numerous few-shot detectors, particularly those based on two-stage detectors, face challenges when dealing with…

Unsupervised learning algorithms are beginning to achieve accuracies comparable to their supervised counterparts on benchmark computer vision tasks, but their utility for practical applications has not yet been demonstrated. In this work,…

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…

On existing public benchmarks, face forgery detection techniques have achieved great success. However, when used in multi-person videos, which often contain many people active in the scene with only a small subset having been manipulated,…

A light-weight low-resolution face gender classification method, called FaceHop, is proposed in this research. We have witnessed rapid progress in face gender classification accuracy due to the adoption of deep learning (DL) technology.…