Related papers: Cost-Efficient Multi-Scale Fovea for Semantic-Base…

In this work, we aim to predict human eye fixation with view-free scenes based on an end-to-end deep learning architecture. Although Convolutional Neural Networks (CNNs) have made substantial improvement on human attention prediction, it is…

Current high-resolution vision-language models encode images as high-resolution image tokens and exhaustively take all these tokens to compute attention, which significantly increases the computational cost. To address this problem, we…

Many indoor workspaces are quasi-static: global layout is stable but local semantics change continually, producing repetitive geometry, dynamic clutter, and perceptual noise that defeat vision-based localization. We present ShelfAware, a…

Category-level object pose estimation is fundamental for embodied intelligence, yet achieving robust generalization to unseen instances remains challenging. However, existing methods mainly rely on simple feature extraction and aggregation,…

Representation-based Siamese networks have risen to popularity in lightweight text matching due to their low deployment and inference costs. While word-level attention mechanisms have been implemented within Siamese networks to improve…

Rich and dense human labeled datasets are among the main enabling factors for the recent advance on vision-language understanding. Many seemingly distant annotations (e.g., semantic segmentation and visual question answering (VQA)) are…

This paper presents a holistic approach to saliency-guided visual attention modeling (SVAM) for use by autonomous underwater robots. Our proposed model, named SVAM-Net, integrates deep visual features at various scales and semantics for…

One of appealing approaches to guiding learnable parameter optimization, such as feature maps, is global attention, which enlightens network intelligence at a fraction of the cost. However, its loss calculation process still falls short:…

Current methods aggregate multi-level features or introduce edge and skeleton to get more refined saliency maps. However, little attention is paid to how to obtain the complete salient object in cluttered background, where the targets are…

Attention is the critical component of a transformer. Yet the quadratic computational complexity of vanilla full attention in the input size and the inability of its linear attention variant to focus have been challenges for computer vision…

Satellite imagery analysis plays a pivotal role in remote sensing; however, information loss due to cloud cover significantly impedes its application. Although existing deep cloud removal models have achieved notable outcomes, they scarcely…

Algorithms for robotic visual search can benefit from the use of visual attention methods in order to reduce computational costs. Here, we describe how three distinct mechanisms of visual attention can be integrated and productively used to…

In this paper, we present a novel neural network using multi scale feature fusion at various scales for accurate and efficient semantic image segmentation. We used ResNet based feature extractor, dilated convolutional layers in downsampling…

Multi-task learning (MTL) paradigm focuses on jointly learning two or more tasks, aiming for significant improvement w.r.t model's generalizability, performance, and training/inference memory footprint. The aforementioned benefits become…

Over the past decade, many computational saliency prediction models have been proposed for 2D images and videos. Considering that the human visual system has evolved in a natural 3D environment, it is only natural to want to design visual…

Large Vision-Language Models (LVLMs) achieve strong performance on many multimodal tasks, but object hallucinations severely undermine their reliability. Most existing studies focus on the text modality, attributing hallucinations to overly…

Interpretable driver attention prediction is crucial for human-like autonomous driving. However, existing datasets provide only scene-level global gaze rather than fine-grained object-level annotations, inherently failing to support…

This work introduces an innovative method for estimating attention levels (cognitive load) using an ensemble of facial analysis techniques applied to webcam videos. Our method is particularly useful, among others, in e-learning…

Efficient visual perception using mobile systems is crucial, particularly in unknown environments such as search and rescue operations, where swift and comprehensive perception of objects of interest is essential. In such real-world…

Multi-head Latent Attention (MLA) is an innovative architecture proposed by DeepSeek, designed to ensure efficient and economical inference by significantly compressing the Key-Value (KV) cache into a latent vector. Compared to MLA,…