Related papers: Borrow from Anywhere: Pseudo Multi-modal Object De…

Graphical elements: particularly tables and figures contain a visual summary of the most valuable information contained in a document. Therefore, localization of such graphical objects in the document images is the initial step to…

Recently, the use of synthetic training data has been on the rise as it offers correctly labelled datasets at a lower cost. The downside of this technique is that the so-called domain gap between the real target images and synthetic…

Geometric navigation is nowadays a well-established field of robotics and the research focus is shifting towards higher-level scene understanding, such as Semantic Mapping. When a robot needs to interact with its environment, it must be…

Existing RGB-thermal salient object detection (RGB-T SOD) methods aim to identify visually significant objects by leveraging both RGB and thermal modalities to enable robust performance in complex scenarios, but they often suffer from…

We propose a domain adaptation approach for object detection. We introduce a two-step method: the first step makes the detector robust to low-level differences and the second step adapts the classifiers to changes in the high-level…

Multi-label image recognition is a practical and challenging task compared to single-label image classification. However, previous works may be suboptimal because of a great number of object proposals or complex attentional region…

Change detection in heterogeneous multitemporal satellite images is an emerging topic in remote sensing. In this paper we propose a framework, based on image regression, to perform change detection in heterogeneous multitemporal satellite…

Although most existing multi-modal salient object detection (SOD) methods demonstrate effectiveness through training models from scratch, the limited multi-modal data hinders these methods from reaching optimality. In this paper, we propose…

Deep learning inference that needs to largely take place on the 'edge' is a highly computational and memory intensive workload, making it intractable for low-power, embedded platforms such as mobile nodes and remote security applications.…

This paper proposes a novel algorithm for multi-focus thermal image fusion. The algorithm is based on local activity analysis and advanced pre-selection of images into fusion process. The algorithm improves the object temperature…

This paper addresses the problem of translating night-time thermal infrared images, which are the most adopted image modalities to analyze night-time scenes, to daytime color images (NTIT2DC), which provide better perceptions of objects. We…

Extreme amodal detection is the task of inferring the 2D location of objects that are not fully visible in the input image but are visible within an expanded field-of-view. This differs from amodal detection, where the object is partially…

Radar is usually more robust than the camera in severe driving scenarios, e.g., weak/strong lighting and bad weather. However, unlike RGB images captured by a camera, the semantic information from the radar signals is noticeably difficult…

The majority of human detection methods rely on the sensor using visible lights (e.g., RGB cameras) but such sensors are limited in scenarios with degraded vision conditions. In this paper, we present a multimodal human detection system…

Cross modal face matching between the thermal and visible spectrum is a much de- sired capability for night-time surveillance and security applications. Due to a very large modality gap, thermal-to-visible face recognition is one of the…

We introduce a novel unsupervised domain adaptation approach for object detection. We aim to alleviate the imperfect translation problem of pixel-level adaptations, and the source-biased discriminativity problem of feature-level adaptations…

Visible-to-thermal face image matching is a challenging variate of cross-modality recognition. The challenge lies in the large modality gap and low correlation between visible and thermal modalities. Existing approaches employ image…

Deformation detection is vital for enabling accurate assessment and prediction of structural changes in materials, ensuring timely and effective interventions to maintain safety and integrity. Automating deformation detection through…

In this paper, we propose a novel end-to-end unsupervised deep domain adaptation model for adaptive object detection by exploiting multi-label object recognition as a dual auxiliary task. The model exploits multi-label prediction to reveal…

In this paper, we propose a new correlated and individual multi-modal deep learning (CIMDL) method for RGB-D object recognition. Unlike most conventional RGB-D object recognition methods which extract features from the RGB and depth…