Related papers: DALG: Deep Attentive Local and Global Modeling for…

Informative features play a crucial role in the single image super-resolution task. Channel attention has been demonstrated to be effective for preserving information-rich features in each layer. However, channel attention treats each…

Existing deep architectures cannot operate on very large signals such as megapixel images due to computational and memory constraints. To tackle this limitation, we propose a fully differentiable end-to-end trainable model that samples and…

Global contexts in images are quite valuable in image-to-image translation problems. Conventional attention-based and graph-based models capture the global context to a large extent, however, these are computationally expensive. Moreover,…

Traditional point-based image editing methods rely on iterative latent optimization or geometric transformations, which are either inefficient in their processing or fail to capture the semantic relationships within the image. These methods…

Recently, Transformer-based architecture has been introduced into single image deraining task due to its advantage in modeling non-local information. However, existing approaches tend to integrate global features based on a dense…

Anatomical landmark detection (ALD) from a medical image is crucial for a wide array of clinical applications. While existing methods achieve quite some success in ALD, they often struggle to balance global context with computational…

Most of current display devices are with eight or higher bit-depth. However, the quality of most multimedia tools cannot achieve this bit-depth standard for the generating images. De-quantization can improve the visual quality of low…

Vision Transformer and its variants have demonstrated great potential in various computer vision tasks. But conventional vision transformers often focus on global dependency at a coarse level, which suffer from a learning challenge on…

High-dimensional, heterogeneous data with complex feature interactions pose significant challenges for traditional predictive modeling approaches. While Projection to Latent Structures (PLS) remains a popular technique, it struggles to…

Image retrieval systems conventionally use a two-stage paradigm, leveraging global features for initial retrieval and local features for reranking. However, the scalability of this method is often limited due to the significant storage and…

Transformer-based models have made remarkable progress in image restoration (IR) tasks. However, the quadratic complexity of self-attention in Transformer hinders its applicability to high-resolution images. Existing methods mitigate this…

Fine-grained image classification is a challenging problem, since the difficulty of finding discriminative features. To handle this circumstance, basically, there are two ways to go. One is use attention based method to focus on informative…

Appearance-based gaze estimation, aiming to predict accurate 3D gaze direction from a single facial image, has made promising progress in recent years. However, most methods suffer significant performance degradation in cross-domain…

Since the Transformer architecture was introduced in 2017 there has been many attempts to bring the self-attention paradigm in the field of computer vision. In this paper we propose a novel self-attention module that can be easily…

Previous studies have demonstrated the effectiveness of point-based neural models on the point cloud analysis task. However, there remains a crucial issue on producing the efficient input embedding for raw point coordinates. Moreover,…

Although Generative Adversarial Networks have shown remarkable performance in image generation, there are some challenges in image realism and convergence speed. The results of some models display the imbalances of quality within a…

Deep learning has achieved impressive results in camera localization, but current single-image techniques typically suffer from a lack of robustness, leading to large outliers. To some extent, this has been tackled by sequential…

Vector-quantized image modeling has shown great potential in synthesizing high-quality images. However, generating high-resolution images remains a challenging task due to the quadratic computational overhead of the self-attention process.…

Conventional algorithms in autonomous exploration face challenges due to their inability to accurately and efficiently identify the spatial distribution of convex regions in the real-time map. These methods often prioritize navigation…

Deep reinforcement learning (DRL) methods have demonstrated potential for autonomous navigation and obstacle avoidance of unmanned ground vehicles (UGVs) in crowded environments. Most existing approaches rely on single-frame observation and…