Rethinking symbolic and visual context in Referring Expression Generation

S Schüz, A Gatt, S Zarrieß - Frontiers in Artificial Intelligence, 2023 - frontiersin.org
Situational context is crucial for linguistic reference to visible objects, since the same
description can refer unambiguously to an object in one context but be ambiguous or …

Towards open-world interactive disambiguation for robotic gras**

Y Mo, H Zhang, T Kong - 2023 IEEE International Conference …, 2023 - ieeexplore.ieee.org
Language-based communications are essential in human-robot interaction, especially for
the majority of non-expert users. In this paper, we present SeeAsk, an open-world interactive …

Entity-focused dense passage retrieval for outside-knowledge visual question answering

J Wu, RJ Mooney - arxiv preprint arxiv:2210.10176, 2022 - arxiv.org
Most Outside-Knowledge Visual Question Answering (OK-VQA) systems employ a two-stage
framework that first retrieves external knowledge given the visual question and then predicts …

Whether you can locate or not? Interactive Referring Expression Generation

F Ye, Y Long, F Feng, X Wang - Proceedings of the 31st ACM …, 2023 - dl.acm.org
Referring Expression Generation (REG) aims to generate unambiguous Referring
Expressions (REs) for objects in a visual scene, with a dual task of Referring Expression …

Towards unifying reference expression generation and comprehension

D Zheng, T Kong, Y **g, J Wang, X Wang - arxiv preprint arxiv …, 2022 - arxiv.org
Reference Expression Generation (REG) and Comprehension (REC) are two highly
correlated tasks. Modeling REG and REC simultaneously for utilizing the relation between …

A unified mutual supervision framework for referring expression segmentation and generation

S Huang, F Li, H Zhang, S Liu, L Zhang… - arxiv preprint arxiv …, 2022 - arxiv.org
Reference Expression Segmentation (RES) and Reference Expression Generation (REG)
are mutually inverse tasks that can be naturally jointly trained. Though recent work has …

Towards Unsupervised Referring Expression Comprehension with Visual Semantic Parsing

Y Wang, Z Ji, D Wang, Y Pang, X Li - Knowledge-Based Systems, 2024 - Elsevier
Abstract Referring Expression Comprehension (REC) is a task that involves grounding a
specific object in an image based on a given referring query in the form of bounding boxes …

A Mutual Supervision Framework for Referring Expression Segmentation and Generation

S Huang, F Li, H Zhang, S Liu, L Zhang… - International Journal of …, 2025 - Springer
Abstract Reference Expression Segmentation (RES) and Reference Expression Generation
(REG) are mutually inverse tasks that can be naturally jointly trained. Though recent work …

Decoupling pragmatics: discriminative decoding for referring expression generation

S Schüz, S Zarrieß - Proceedings of the Reasoning and Interaction …, 2021 - aclanthology.org
The shift to neural models in Referring Expression Generation (REG) has enabled more
natural set-ups, but at the cost of interpretability. We argue that integrating pragmatic …

Unified Referring Expression Generation for Bounding Boxes and Segmentations

Z Liu, T Xu, X Song, XJ Wu - IEEE Signal Processing Letters, 2024 - ieeexplore.ieee.org
Referring expression generation (REG) is a challenging task at the intersection of computer
vision and natural language processing, which aims at generating natural language …