Rethinking symbolic and visual context in Referring Expression Generation
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 …
description can refer unambiguously to an object in one context but be ambiguous or …
Towards open-world interactive disambiguation for robotic gras**
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 …
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
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 …
framework that first retrieves external knowledge given the visual question and then predicts …
Whether you can locate or not? Interactive Referring Expression Generation
Referring Expression Generation (REG) aims to generate unambiguous Referring
Expressions (REs) for objects in a visual scene, with a dual task of Referring Expression …
Expressions (REs) for objects in a visual scene, with a dual task of Referring Expression …
Towards unifying reference expression generation and comprehension
Reference Expression Generation (REG) and Comprehension (REC) are two highly
correlated tasks. Modeling REG and REC simultaneously for utilizing the relation between …
correlated tasks. Modeling REG and REC simultaneously for utilizing the relation between …
A unified mutual supervision framework for referring expression segmentation and generation
Reference Expression Segmentation (RES) and Reference Expression Generation (REG)
are mutually inverse tasks that can be naturally jointly trained. Though recent work has …
are mutually inverse tasks that can be naturally jointly trained. Though recent work has …
Towards Unsupervised Referring Expression Comprehension with Visual Semantic Parsing
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 …
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
Abstract Reference Expression Segmentation (RES) and Reference Expression Generation
(REG) are mutually inverse tasks that can be naturally jointly trained. Though recent work …
(REG) are mutually inverse tasks that can be naturally jointly trained. Though recent work …
Decoupling pragmatics: discriminative decoding for referring expression generation
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 …
natural set-ups, but at the cost of interpretability. We argue that integrating pragmatic …
Unified Referring Expression Generation for Bounding Boxes and Segmentations
Referring expression generation (REG) is a challenging task at the intersection of computer
vision and natural language processing, which aims at generating natural language …
vision and natural language processing, which aims at generating natural language …