Related papers: Customized Fusion: A Closed-Loop Dynamic Network f…
Visible images offer rich texture details, while infrared images emphasize salient targets. Fusing these complementary modalities enhances scene understanding, particularly for advanced vision tasks under challenging conditions. Recently,…
The integration of vision-language models such as CLIP and Concept Bottleneck Models (CBMs) offers a promising approach to explaining deep neural network (DNN) decisions using concepts understandable by humans, addressing the black-box…
Despite the growing discriminative capabilities of modern deep learning methods for recognition tasks, the inner workings of the state-of-art models still remain mostly black-boxes. In this paper, we propose a systematic interpretation of…
With the rapid progress of controllable generation, training data synthesis has become a promising way to expand labeled datasets and alleviate manual annotation in remote sensing (RS). However, the complexity of semantic mask control and…
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…
The vision-based semantic scene completion task aims to predict dense geometric and semantic 3D scene representations from 2D images. However, the presence of dynamic objects in the scene seriously affects the accuracy of the model…
The composed image retrieval (CIR) task aims to retrieve the desired target image for a given multimodal query, i.e., a reference image with its corresponding modification text. The key limitations encountered by existing efforts are two…
The "CNN-RNN" design pattern is increasingly widely applied in a variety of image annotation tasks including multi-label classification and captioning. Existing models use the weakly semantic CNN hidden layer or its transform as the image…
Recently, Referring Remote Sensing Image Segmentation (RRSIS) has aroused wide attention. To handle drastic scale variation of remote targets, existing methods only use the full image as input and nest the saliency-preferring techniques of…
Pooling is a crucial operation in computer vision, yet the unique structure of skeletons hinders the application of existing pooling strategies to skeleton graph modelling. In this paper, we propose an Improved Graph Pooling Network,…
A split-transform-merge strategy has been broadly used as an architectural constraint in convolutional neural networks for visual recognition tasks. It approximates sparsely connected networks by explicitly defining multiple branches to…
Multilayer graph has garnered plenty of research attention in many areas due to their high utility in modeling interdependent systems. However, clustering of multilayer graph, which aims at dividing the graph nodes into categories or…
Robust semantic perception for autonomous vehicles relies on effectively combining multiple sensors with complementary strengths and weaknesses. State-of-the-art sensor fusion approaches to semantic perception often treat sensor data…
Underwater images suffer from severe degradations, including color distortions, reduced visibility, and loss of structural details due to wavelength-dependent attenuation and scattering. Existing enhancement methods primarily focus on…
Recent progress has shown great potential of visual prompt tuning (VPT) when adapting pre-trained vision transformers to various downstream tasks. However, most existing solutions independently optimize prompts at each layer, thereby…
Data-driven Clinical Decision Support Systems (CDSS) have the potential to improve and standardise care with personalised probabilistic guidance. However, the size of data required necessitates collaborative learning from analogous CDSS's,…
3D Referring Expression Segmentation (3D-RES) aims to segment point cloud scenes based on a given expression. However, existing 3D-RES approaches face two major challenges: feature ambiguity and intent ambiguity. Feature ambiguity arises…
Learned image compression (LIC) methods have exhibited promising progress and superior rate-distortion performance compared with classical image compression standards. Most existing LIC methods are Convolutional Neural Networks-based…
Deep neural networks have achieved promising results in automatic image captioning due to their effective representation learning and context-based content generation capabilities. As a prominent type of deep features used in many of the…
Multimodal fusion of remote sensing images serves as a core technology for overcoming the limitations of single-source data and improving the accuracy of surface information extraction, which exhibits significant application value in fields…