相关论文: MSCMNet: Multi-scale Semantic Correlation Mining f…
As a promising field, Multi-Query Image Retrieval (MQIR) aims at searching for the semantically relevant image given multiple region-specific text queries. Existing works mainly focus on a single-level similarity between image regions and…
Matching individuals across non-overlapping camera networks, known as person re-identification, is a fundamentally challenging problem due to the large visual appearance changes caused by variations of viewpoints, lighting, and occlusion.…
With the advancement of remote sensing satellite technology and the rapid progress of deep learning, remote sensing change detection (RSCD) has become a key technique for regional monitoring. Traditional change detection (CD) methods and…
Multimodal remote sensing semantic segmentation enhances scene interpretation by exploiting complementary physical cues from heterogeneous data. Although pretrained Vision Foundation Models (VFMs) provide strong general-purpose…
Grounded Multimodal Named Entity Recognition (GMNER) aims to extract text-based entities, assign them semantic categories, and ground them to corresponding visual regions. In this work, we explore the potential of Multimodal Large Language…
Multi-modal image fusion (MMIF) enhances the information content of the fused image by combining the unique as well as common features obtained from different modality sensor images, improving visualization, object detection, and many more…
Image dehazing poses significant challenges in environmental perception. Recent research mainly focus on deep learning-based methods with single modality, while they may result in severe information loss especially in dense-haze scenarios.…
Person re-identification (re-ID) aims to retrieve the same person across different cameras. In practice, it still remains a challenging task due to background clutter, variations on body poses and view conditions, inaccurate bounding box…
Although unsupervised person re-identification (Re-ID) has drawn increasing research attention recently, it remains challenging to learn discriminative features without annotations across disjoint camera views. In this paper, we address the…
Recent guided depth super-resolution methods are premised on the assumption of strict spatial alignment between depth and RGB, achieving high-quality depth reconstruction. However, in real-world scenarios, the acquisition of strictly…
Human Activity Recognition is a field of research where input data can take many forms. Each of the possible input modalities describes human behaviour in a different way, and each has its own strengths and weaknesses. We explore the…
Maritime vessel re-identification (Re-ID) plays a crucial role in advancing maritime monitoring and intelligent situational awareness systems. However, some existing vessel Re-ID methods are directly adapted from pedestrian-focused…
Automated and accurate segmentation of individual vertebra in 3D CT and MRI images is essential for various clinical applications. Due to the limitations of current imaging techniques and the complexity of spinal structures, existing…
Cross-modal entity linking refers to the ability to align entities and their attributes across different modalities. While cross-modal entity linking is a fundamental skill needed for real-world applications such as multimodal code…
Text-based person retrieval aims to find the query person based on a textual description. The key is to learn a common latent space mapping between visual-textual modalities. To achieve this goal, existing works employ segmentation to…
In this paper, we propose a novel deep convolutional neural network to solve the general multi-modal image restoration (MIR) and multi-modal image fusion (MIF) problems. Different from other methods based on deep learning, our network…
Relic landslide, formed over a long period, possess the potential for reactivation, making them a hazardous geological phenomenon. While reliable relic landslide detection benefits the effective monitoring and prevention of landslide…
This paper focuses on the visible-thermal cross-modality person re-identification (VT Re-ID) task, whose goal is to match person images between the daytime visible modality and the nighttime thermal modality. The two-stream network is…
Visible-infrared person re-identification (VI-ReID) technique could associate the pedestrian images across visible and infrared modalities in the practical scenarios of background illumination changes. However, a substantial gap inherently…
In the conventional person re-id setting, it is assumed that the labeled images are the person images within the bounding box for each individual; this labeling across multiple nonoverlapping camera views from raw video surveillance is…