Related papers: Ship Instance Segmentation From Remote Sensing Ima…
The spatial attention is a straightforward approach to enhance the performance for remote sensing image captioning. However, conventional spatial attention approaches consider only the attention distribution on one fixed coarse grid,…
Topic segmentation is important in understanding scientific documents since it can not only provide better readability but also facilitate downstream tasks such as information retrieval and question answering by creating appropriate…
Open-vocabulary instance segmentation aims at segmenting novel classes without mask annotations. It is an important step toward reducing laborious human supervision. Most existing works first pretrain a model on captioned images covering…
Remote sensing images pose distinct challenges for downstream tasks due to their inherent complexity. While a considerable amount of research has been dedicated to remote sensing classification, object detection and semantic segmentation,…
Cross-view object geo-localization enables high-precision object localization through cross-view matching, with critical applications in autonomous driving, urban management, and disaster response. However, existing methods rely on…
In-context segmentation aims at segmenting novel images using a few labeled example images, termed as "in-context examples", exploring content similarities between examples and the target. The resulting models can be generalized seamlessly…
We propose an approach to instance-level image segmentation that is built on top of category-level segmentation. Specifically, for each pixel in a semantic category mask, its corresponding instance bounding box is predicted using a deep…
In this paper, we present a semi supervised deep quick learning framework for instance detection and pixel-wise semantic segmentation of images in a dense clutter of items. The framework can quickly and incrementally learn novel items in an…
Compared to many other dense prediction tasks, e.g., semantic segmentation, it is the arbitrary number of instances that has made instance segmentation much more challenging. In order to predict a mask for each instance, mainstream…
Global context information is vital in visual understanding problems, especially in pixel-level semantic segmentation. The mainstream methods adopt the self-attention mechanism to model global context information. However, pixels belonging…
Reasoning segmentation aims to segment target objects in complex scenes based on human intent and spatial reasoning. While recent multimodal large language models (MLLMs) have demonstrated impressive 2D image reasoning segmentation,…
Open-set object recognition aims to identify if an object is from a class that has been encountered during training or not. To perform open-set object recognition accurately, a key challenge is how to reduce the reliance on…
The rapid advancement of large language models (LLMs) has accelerated the emergence of in-context learning (ICL) as a cutting-edge approach in the natural language processing domain. Recently, ICL has been employed in visual understanding…
Large Vision and Language Models (LVLMs) have shown strong performance across various vision-language tasks in natural image domains. However, their application to remote sensing (RS) remains underexplored due to significant domain…
LiDAR-based place recognition is an essential and challenging task both in loop closure detection and global relocalization. We propose Deep Scan Context (DSC), a general and discriminative global descriptor that captures the relationship…
Video object segmentation aims at accurately segmenting the target object regions across consecutive frames. It is technically challenging for coping with complicated factors (e.g., shape deformations, occlusion and out of the lens). Recent…
Recognizing multiple objects in an image is challenging due to occlusions, and becomes even more so when the objects are small. While promising, existing multi-label image recognition models do not explicitly learn context-based…
In this paper, we propose a conceptually novel, efficient, and fully convolutional framework for real-time instance segmentation. Previously, most instance segmentation methods heavily rely on object detection and perform mask prediction…
Panoptic segmentation combines the advantages of semantic and instance segmentation, which can provide both pixel-level and instance-level environmental perception information for intelligent vehicles. However, it is challenged with…
Object counting, which aims to count the accurate number of object instances in images, has been attracting more and more attention. However, challenges such as large scale variation, complex background interference, and non-uniform density…