Related papers: Cost-Efficient Multi-Scale Fovea for Semantic-Base…
Convolutional neural networks have enabled major progresses in addressing pixel-level prediction tasks such as semantic segmentation, depth estimation, surface normal prediction and so on, benefiting from their powerful capabilities in…
Driver attention prediction is becoming an essential research problem in human-like driving systems. This work makes an attempt to predict the driver attention in driving accident scenarios (DADA). However, challenges tread on the heels of…
We propose augmenting deep neural networks with an attention mechanism for the visual object detection task. As perceiving a scene, humans have the capability of multiple fixation points, each attended to scene content at different…
Attention mechanisms underpin modern deep learning, while the quadratic time and space complexity limit scalability for long sequences. To address this, Quantum Annealing Multi-Head Attention (QAMA) is proposed, a novel drop-in operator…
Visual Emotion Analysis (VEA) is attracting increasing attention. One of the biggest challenges of VEA is to bridge the affective gap between visual clues in a picture and the emotion expressed by the picture. As the granularity of emotions…
Identifying robust and accurate correspondences across images is a fundamental problem in computer vision that enables various downstream tasks. Recent semi-dense matching methods emphasize the effectiveness of fusing relevant cross-view…
Super-resolving medical images can help physicians in providing more accurate diagnostics. In many situations, computed tomography (CT) or magnetic resonance imaging (MRI) techniques capture several scans (modes) during a single…
Recently, video streams have occupied a large proportion of Internet traffic, most of which contain human faces. Hence, it is necessary to predict saliency on multiple-face videos, which can provide attention cues for many content based…
State-of-the-art (SoTA) models have improved the accuracy of object detection with a large margin via a FP (feature pyramid). FP is a top-down aggregation to collect semantically strong features to improve scale invariance in both two-stage…
Semantic image segmentation is one of the most challenged tasks in computer vision. In this paper, we propose a highly fused convolutional network, which consists of three parts: feature downsampling, combined feature upsampling and…
The deployment of Large Language Models (LLMs) faces a critical bottleneck when handling lengthy inputs: the prohibitive memory footprint of the Key Value (KV) cache. To address this bottleneck, the token pruning paradigm leverages…
Accurate 3D object detection in autonomous driving relies on Bird's Eye View (BEV) perception and effective temporal fusion. However, existing fusion strategies based on convolutional layers or deformable self-attention struggle to model…
Most existing salient object detection methods mostly use U-Net or feature pyramid structure, which simply aggregates feature maps of different scales, ignoring the uniqueness and interdependence of them and their respective contributions…
Scaling depth is a key driver for large language models (LLMs). Yet, as LLMs become deeper, they often suffer from signal degradation: informative features formed in shallow layers are gradually diluted by repeated residual updates, making…
Human drivers adeptly navigate complex scenarios by utilizing rich attentional semantics, but the current autonomous systems struggle to replicate this ability, as they often lose critical semantic information when converting 2D…
Top-down attention plays a crucial role in the human vision system, wherein the brain initially obtains a rough overview of a scene to discover salient cues (i.e., overview first), followed by a more careful finer-grained examination (i.e.,…
Foveated graphics is a promising approach to solving the bandwidth challenges of immersive virtual and augmented reality displays by exploiting the falloff in spatial acuity in the periphery of the visual field. However, the perceptual…
Semantic segmentation, as a basic tool for intelligent interpretation of remote sensing images, plays a vital role in many Earth Observation (EO) applications. Nowadays, accurate semantic segmentation of remote sensing images remains a…
Images captured in harsh environments often exhibit blurred details, reduced contrast, and color distortion, which hinder feature detection and matching, thereby affecting the accuracy and robustness of homography estimation. While visual…
Intelligent surveillance systems often handle perceptual tasks such as object detection, facial recognition, and emotion analysis independently, but they lack a unified, adaptive runtime scheduler that dynamically allocates computational…