conftrace_

caption evaluation

5 papers

Explore in graph

Co-occurring keywords · papers mentioning both

image captioning (4) open vocabulary hallucination (1) reference-less metric (1) deaf and hard of hearing (1) visual fidelity assessment (1) object label matching (1) semantic similarity metric (1) multi-objective reward (1) generative foundation model (1) conversational transcript (1)

Papers

G-VEval: A Versatile Metric for Evaluating Image and Video Captions Using GPT-4o AAAI 2025 Mitigating Open-Vocabulary Caption Hallucinations EMNLP 2024 Using BERT Embeddings to Model Word Importance in Conversational Transcripts for Deaf and Hard of Hearing Users ACL 2022 QACE: Asking Questions to Evaluate an Image Caption EMNLP 2021 VIFIDEL: Evaluating the Visual Fidelity of Image Descriptions ACL 2019