Search Results

Modern multi-layer perceptron (MLP) models have shown competitive results in learning visual representations without self-attention. However, existing MLP models are not good at capturing local details and lack prior knowledge of human body ...

• We present, to the best of our knowledge, the first MLP-Like architecture called GraphMLP for 3D human pose estimation. It combines the advantages of modern MLPs and GCNs, including globality, locality, and connectivity.
• The novel SG-...

Low-light image enhancement is a crucial visual task, and many unsupervised methods overlook the degradation of visible information in low-light scenes, adversely affecting the fusion of complementary information and hindering the generation of ...

Traditional guided image translation methods, based on encoder–decoder or U-Net structures, often struggle with complex or contrasting images. To address this, we introduce a novel dual-stage strategy. First, we use a cascaded cross-gating MLP-...

• A novel two-phase MLP-Mixer-based framework for guided image translation.
• A unique module for uncovering latent mapping cues between source images and target semantic guidance.
• A refined pixel-level loss function to address ...

With the emergence and rapid development of Transformers, medical image segmentation has also been revolutionized by Transformers due to their ability to encode long-range dependencies. Despite their advantages, Transformers also come with some ...

Embodied navigation, which involves robotic agents exploring an unknown environment to reach target locations with egocentric observation, is a complex problem in the field of embodied AI. Audio-visual navigation extends this concept by equipping ...

Despite the impressive achievements of Deep Neural Networks (DNNs) in computer vision, their vulnerability to adversarial attacks remains a critical concern. Extensive research has demonstrated that incorporating sophisticated perturbations into input ...

The accurate diagnosis of schizophrenia spectrum disorder plays an important role in improving patient outcomes, enabling timely interventions, and optimizing treatment plans. Functional connectivity analysis, utilizing ...

• We propose a GNAS framework to build GNN model for disorder prediction.
• We compare our model with other popular ML and DL models on multi-site datasets.
• We use the GNNExplainer method to provide the explainability of the model.

In the Internet era, the exponential growth of fine-grained image databases poses a considerable challenge for efficient information retrieval. Hashing-based approaches gained traction for their computational and storage efficiency, yet fine-grained ...

The tasks of view synthesis and decoupling dynamic objects from the static environment for monocular scenes are both long-standing challenges in CV and CG. Most of the previous NeRF-based methods rely on implicit representation, which require additional ...

Story visualization aims to generate realistic and coherent images based on multi-sentence stories. However, current methods face challenges in achieving high-quality image generation while maintaining lightweight models and a fast generation speed. The ...

Fine-grained image retrieval (FGIR) is to learn visual representations that distinguish visually similar objects while maintaining generalization. Existing methods propose to generate discriminative features, but rarely consider the particularity of the ...

Diffusion models have shown impressive potential on talking head generation. While plausible appearance and talking effect are achieved, these methods still suffer from temporal, 3D or expression inconsistency due to the error accumulation and inherent ...

Designing accessible locomotion methods for individuals who are blind or have low vision (BLV) is a complex challenge, particularly in mobile VR environments with limited interface options. In this paper, we propose a novel locomotion technique on ...

In this paper, we propose 3DSS-VLG, a weakly supervised approach for 3DSemantic Segmentation with 2D Vision-Language Guidance, an alternative approach that a 3D model predicts dense-embedding for each point which is co-embedded with both the ...

Semantic image synthesis (SIS) shows good promises for sensor simulation. However, current best practices in this field, based on GANs, have not yet reached the desired level of quality. As latent diffusion models make significant strides in image ...

Recent advances in image editing have been driven by the development of denoising diffusion models, marking a significant leap forward in this field. Despite these advances, the generalization capabilities of recent image editing approaches remain ...

This paper proposes a simple, yet effective framework, called GiT, simultaneously applicable for various vision tasks only with a vanilla ViT. Motivated by the universality of the Multi-layer Transformer architecture (e.g., GPT) widely used in ...

Recovering camera poses from a set of images is a foundational task in 3D computer vision, which powers key applications such as 3D scene/object reconstructions. Classic methods often depend on feature correspondence, such as keypoints, which ...

Story visualization aims to generate a series of realistic and coherent images based on a storyline. Current models adopt a frame-by-frame architecture by transforming the pre-trained text-to-image model into an auto-regressive manner. Although ...

Deep learning benefits from the growing abundance of available data. Meanwhile, efficiently dealing with the growing data scale has become a challenge. Data publicly available are from different sources with various qualities, and it is ...