Related papers: LVFace: Progressive Cluster Optimization for Large…

Federated learning (FL) has emerged as a promising paradigm for privacy-preserving multi-camera video understanding. However, applying FL to cross-view scenarios faces three major challenges: (i) heterogeneous viewpoints and backgrounds…

Face images appeared in multimedia applications, e.g., social networks and digital entertainment, usually exhibit dramatic pose, illumination, and expression variations, resulting in considerable performance degradation for traditional face…

As Vision-Language Models (VLMs) advance, human-centered Assistive Technologies (ATs) for helping People with Visual Impairments (PVIs) are evolving into generalists, capable of performing multiple tasks simultaneously. However,…

Unsupervised vision clustering, a cornerstone in computer vision, has been studied for decades, yielding significant outcomes across numerous vision tasks. However, these algorithms involve substantial computational demands when confronted…

Vision transformers (ViTs) have been trending in image classification tasks due to their promising performance when compared to convolutional neural networks (CNNs). As a result, many researchers have tried to incorporate ViTs in…

Advanced image tampering techniques are increasingly challenging the trustworthiness of multimedia, leading to the development of Image Manipulation Localization (IML). But what makes a good IML model? The answer lies in the way to capture…

This paper investigates the effectiveness of self-supervised pre-trained vision transformers (ViTs) compared to supervised pre-trained ViTs and conventional neural networks (ConvNets) for detecting facial deepfake images and videos. It…

Transformer has been applied in the field of computer vision due to its excellent performance in natural language processing, surpassing traditional convolutional neural networks and achieving new state-of-the-art. ViT divides an image into…

We present an algorithm for simultaneous face detection, landmarks localization, pose estimation and gender recognition using deep convolutional neural networks (CNN). The proposed method called, HyperFace, fuses the intermediate layers of…

Recent studies have shown that Large Vision-Language Models (VLMs) tend to neglect image content and over-rely on language-model priors, resulting in errors in visually grounded tasks and hallucinations. We hypothesize that this issue…

Due to its deficiency in prior knowledge (inductive bias), Vision Transformer (ViT) requires pre-training on large-scale datasets to perform well. Moreover, the growing layers and parameters in ViT models impede their applicability to…

Face Anti-Spoofing (FAS) remains challenging due to the requirement for robust domain generalization across unseen environments. While recent trends leverage Vision-Language Models (VLMs) for semantic supervision, these multimodal…

Learning discriminative spatiotemporal representation is the key problem of video understanding. Recently, Vision Transformers (ViTs) have shown their power in learning long-term video dependency with self-attention. Unfortunately, they…

Owing to large-scale image-text contrastive training, pre-trained vision language model (VLM) like CLIP shows superior open-vocabulary recognition ability. Most existing open-vocabulary object detectors attempt to utilize the pre-trained…

Facial Beauty Prediction (FBP) has made significant strides with the application of deep learning, yet state-of-the-art models often exhibit critical limitations, including architectural constraints, inherent demographic biases, and a lack…

Video face restoration faces a critical challenge in maintaining temporal consistency while recovering fine facial details from degraded inputs. This paper presents a novel approach that extends Vector-Quantized Variational Autoencoders…

Despite the widespread adoption of transformers in medical applications, the exploration of multi-scale learning through transformers remains limited, while hierarchical representations are considered advantageous for computer-aided medical…

Vision transformers (ViTs) achieve remarkable performance on large datasets, but tend to perform worse than convolutional neural networks (CNNs) when trained from scratch on smaller datasets, possibly due to a lack of local inductive bias…

As the quality of optical sensors improves, there is a need for processing large-scale images. In particular, the ability of devices to capture ultra-high definition (UHD) images and video places new demands on the image processing…

Vision Transformers (ViT) become widely-adopted architectures for various vision tasks. Masked auto-encoding for feature pretraining and multi-scale hybrid convolution-transformer architectures can further unleash the potentials of ViT,…