SOTAVerified

Referring expression generation

Generate referring expressions

Papers

Showing 51–75 of 84 papers

TitleStatusHype
Statistical NLG for Generating the Content and Form of Referring Expressions—0
Generating Texts with Integer Linear Programming—0
An Incremental Iterated Response Model of Pragmatics—0
Meteorologists and Students: A resource for language grounding of geographical descriptors—0
NeuralREG: An end-to-end approach to referring expression generationCode0
Referring Expression Generation in time-constrained communication—0
Reference production in human-computer interaction: Issues for Corpus-based Referring Expression Generation—0
A Predictive Model for Notional Anaphora in English—0
Semi-automatic definite description annotation: a first report—0
Referring Expression Generation and Comprehension via Attributes—0
Improving the generation of personalised descriptions—0
G-TUNA: a corpus of referring expressions in German, including duration information—0
Refer-iTTS: A System for Referring in Spoken Installments to Objects in Real-World Images—0
Exploring the Behavior of Classic REG Algorithms in the Description of Characters in 3D Images—0
Referring Expression Generation under Uncertainty: Algorithm and Evaluation Framework—0
The WebNLG Challenge: Generating Text from RDF Data—0
Obtaining referential word meanings from visual and distributional information: Experiments on object naming—0
Creating Training Corpora for NLG Micro-Planners—0
Squib: Effects of Cognitive Effort on the Resolution of Overspecified Descriptions—0
Trainable Referring Expression Generation using Overspecification Preferences—0
Building Multimodal Simulations for Natural Language—0
An Empirical Approach for Modeling Fuzzy Geographical Descriptors—0
Comprehension-guided referring expressions—0
On the Robustness of Standalone Referring Expression Generation Algorithms Using RDF Data—0
Easy Things First: Installments Improve Referring Expression Generation for Objects in Photographs—0
Show:102550
← PrevPage 3 of 4Next →

Benchmark Results

#ModelMetricClaimedVerifiedStatus
1ColonGPT (w/ LoRA, w/o extra data)Accuray99.96—Unverified
2LLaVA-v1.5 (w/ LoRA, w/ extra data)Accuray99.32—Unverified
3LLaVA-Med-v1.5 (w/ LoRA, w/o extra data)Accuray99.3—Unverified
4MGM-2B (w/o LoRA, w/ extra data)Accuray98.75—Unverified
5LLaVA-v1.5 (w/ LoRA, w/o extra data)Accuray98.58—Unverified
6MGM-2B (w/o LoRA, w/o extra data)Accuray98.17—Unverified
7MobileVLM-1.7B (w/ LoRA, w/ extra data)Accuray97.87—Unverified
8MobileVLM-1.7B (w/o LoRA, w/ extra data)Accuray97.78—Unverified
9LLaVA-Med-v1.0 (w/o LoRA, w/o extra data)Accuray97.74—Unverified
10LLaVA-Med-v1.0 (w/o LoRA, w/ extra data)Accuray97.35—Unverified
#ModelMetricClaimedVerifiedStatus
1LLaVA-Med-v1.5 (w/ LoRA, w/ extra data)Accuray70—Unverified
2LLaVA-v1 (w/ LoRA, w/ extra data)Accuray46.85—Unverified