Related papers: FoveaTer: Foveated Transformer for Image Classific…

Visual question answering (VQA) is challenging because it requires a simultaneous understanding of both the visual content of images and the textual content of questions. The approaches used to represent the images and questions in a…

Convolutional neural networks have emerged as the leading method for the classification and segmentation of images. In some cases, it is desirable to focus the attention of the net on a specific region in the image; one such case is the…

In this work, we explore neat yet effective Transformer-based frameworks for visual grounding. The previous methods generally address the core problem of visual grounding, i.e., multi-modal fusion and reasoning, with manually-designed…

Recognizing target objects using an event-based camera draws more and more attention in recent years. Existing works usually represent the event streams into point-cloud, voxel, image, etc, and learn the feature representations using…

Humans intuitively recognize objects' physical properties and predict their motion, even when the objects are engaged in complicated interactions. The abilities to perform physical reasoning and to adapt to new environments, while intrinsic…

Classifying facial expressions into different categories requires capturing regional distortions of facial landmarks. We believe that second-order statistics such as covariance is better able to capture such distortions in regional facial…

Automatic face recognition has received significant performance improvement by developing specialised facial image representations. On the other hand, generic object recognition has rarely been applied to the face recognition. Spatial…

By and large, existing computational models of visual attention tacitly assume perfect vision and full access to the stimulus and thereby deviate from foveated biological vision. Moreover, modeling top-down attention is generally reduced to…

A major goal of neuroscience is to understand brain computations during visual processing in naturalistic settings. A dominant approach is to use image-computable deep neural networks trained with different task objectives as a basis for…

Human decision-making often relies on visual information from multiple perspectives or views. In contrast, machine learning-based object recognition utilizes information from a single image of the object. However, the information conveyed…

Novel display technologies can deliver high-quality images across a wide field of view, creating immersive experiences. While rendering for such devices is expensive, most of the content falls into peripheral vision, where human perception…

VAEs, or variational autoencoders, are autoencoders that explicitly learn the distribution of the input image space rather than assuming no prior information about the distribution. This allows it to classify similar samples close to each…

Deep ConvNets have shown its good performance in image classification tasks. However it still remains as a problem in deep video representation for action recognition. The problem comes from two aspects: on one hand, current video ConvNets…

Transformer-based deep neural networks have achieved remarkable success across various computer vision tasks, largely attributed to their long-range self-attention mechanism and scalability. However, most transformer architectures embed…

Video prediction is a pixel-level task that generates future frames by employing the historical frames. There often exist continuous complex motions, such as object overlapping and scene occlusion in video, which poses great challenges to…

Current state-of-the-art segmentation models encode entire images before focusing on specific objects. As a result, they waste computational resources - particularly when small objects are to be segmented in high-resolution scenes. We…

Prior foveated rendering methods often suffer from a limitation where the shading load escalates with increasing display resolution, leading to decreased efficiency, particularly when dealing with retinal-level resolutions. To tackle this…

Facial Expression Recognition (FER) in the wild is an extremely challenging task. Recently, some Vision Transformers (ViT) have been explored for FER, but most of them perform inferiorly compared to Convolutional Neural Networks (CNN). This…

Recent studies have shown remarkable success in face manipulation task with the advance of GANs and VAEs paradigms, but the outputs are sometimes limited to low-resolution and lack of diversity. In this work, we propose Additive Focal…

The recently proposed Visual image Transformers (ViT) with pure attention have achieved promising performance on image recognition tasks, such as image classification. However, the routine of the current ViT model is to maintain a…