3d-stmn: Dependency-driven superpoint-text matching network for end-to-end 3d referring expression segmentation
In 3D Referring Expression Segmentation (3D-RES), the earlier approach adopts a two-
stage paradigm, extracting segmentation proposals and then matching them with referring …
stage paradigm, extracting segmentation proposals and then matching them with referring …
X-RefSeg3D: Enhancing Referring 3D Instance Segmentation via Structured Cross-Modal Graph Neural Networks
Z Qian, Y Ma, J Ji, X Sun - Proceedings of the AAAI Conference on …, 2024 - ojs.aaai.org
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 …
Gres: Generalized referring expression segmentation
Abstract Referring Expression Segmentation (RES) aims to generate a segmentation mask
for the object described by a given language expression. Existing classic RES datasets and …
for the object described by a given language expression. Existing classic RES datasets and …
Multi-task collaborative network for joint referring expression comprehension and segmentation
Referring expression comprehension (REC) and segmentation (RES) are two highly-related
tasks, which both aim at identifying the referent according to a natural language expression …
tasks, which both aim at identifying the referent according to a natural language expression …
Cross-modality synergy network for referring expression comprehension and segmentation
Referring expression comprehension and segmentation aim to locate and segment a
referred instance in an image according to a natural language expression. However …
referred instance in an image according to a natural language expression. However …
Advancing referring expression segmentation beyond single image
Abstract Referring Expression Segmentation (RES) is a widely explored multi-modal task,
which endeavors to segment the pre-existing object within a single image with a given …
which endeavors to segment the pre-existing object within a single image with a given …
Rethinking Two-Stage Referring Expression Comprehension: A Novel Grounding and Segmentation Method Modulated by Point
P Zhao, S Zheng, W Zhao, D Xu, P Li, Y Cai… - Proceedings of the …, 2024 - ojs.aaai.org
As a fundamental and challenging task in the vision and language domain, Referring
Expression Comprehension (REC) has shown impressive improvements recently. However …
Expression Comprehension (REC) has shown impressive improvements recently. However …
Meta compositional referring expression segmentation
Referring expression segmentation aims to segment an object described by a language
expression from an image. Despite the recent progress on this task, existing models tackling …
expression from an image. Despite the recent progress on this task, existing models tackling …
Fully and weakly supervised referring expression segmentation with end-to-end learning
Referring Expression Segmentation (RES), which is aimed at localizing and segmenting the
target according to the given language expression, has drawn increasing attention. Existing …
target according to the given language expression, has drawn increasing attention. Existing …
Unveiling Parts Beyond Objects: Towards Finer-Granularity Referring Expression Segmentation
Referring expression segmentation (RES) aims at segmenting the foreground masks of the
entities that match the descriptive natural language expression. Previous datasets and …
entities that match the descriptive natural language expression. Previous datasets and …