Rotated multi-scale interaction network for referring remote sensing image segmentation
Abstract Referring Remote Sensing Image Segmentation (RRSIS) is a new challenge that
combines computer vision and natural language processing. Traditional Referring Image …
combines computer vision and natural language processing. Traditional Referring Image …
Improving Panoptic Narrative Grounding by Harnessing Semantic Relationships and Visual Confirmation
Recent advancements in single-stage Panoptic Narrative Grounding (PNG) have
demonstrated significant potential. These methods predict pixel-level masks by directly …
demonstrated significant potential. These methods predict pixel-level masks by directly …
X-RefSeg3D: Enhancing Referring 3D Instance Segmentation via Structured Cross-Modal Graph Neural Networks
Referring 3D instance segmentation is a challenging task aimed at accurately segmenting a
target instance within a 3D scene based on a given referring expression. However, previous …
target instance within a 3D scene based on a given referring expression. However, previous …
SAM as the Guide: Mastering Pseudo-Label Refinement in Semi-Supervised Referring Expression Segmentation
In this paper, we introduce SemiRES, a semi-supervised framework that effectively
leverages a combination of labeled and unlabeled data to perform RES. A significant hurdle …
leverages a combination of labeled and unlabeled data to perform RES. A significant hurdle …
Exploring Phrase-Level Grounding with Text-to-Image Diffusion Model
Recently, diffusion models have increasingly demonstrated their capabilities in vision
understanding. By leveraging prompt-based learning to construct sentences, these models …
understanding. By leveraging prompt-based learning to construct sentences, these models …
Image Captioning via Dynamic Path Customization
This paper explores a novel dynamic network for vision and language tasks, where the
inferring structure is customized on the fly for different inputs. Most previous state-of-the-art …
inferring structure is customized on the fly for different inputs. Most previous state-of-the-art …
Multi-branch Collaborative Learning Network for 3D Visual Grounding
3D referring expression comprehension (3DREC) and segmentation (3DRES) have
overlapping objectives, indicating their potential for collaboration. However, existing …
overlapping objectives, indicating their potential for collaboration. However, existing …
Hierarchical Activation Dual Backbone Network for Weakly Supervised Semantic Segmentation
C Zhang, L Zhang - IEEE Sensors Journal, 2024 - ieeexplore.ieee.org
Weakly Supervised Semantic Segmentation (WSSS) aims to achieve segmentation using
weak labels, thereby reducing annotation costs. Current mainstream WSSS methods utilize …
weak labels, thereby reducing annotation costs. Current mainstream WSSS methods utilize …