paper-with-me

Papers

OPCap:Object-aware Prompting Captioning

2024-11-27 · Feiyang Huang

In the field of image captioning, the phenomenon where missing or nonexistent objects are used to explain an image is referred to as object bias (or hallucination). To mitigate this issue, we propose a target-aware prompting strategy. This method first extracts object labels and their spatial information from the image using an object detector. Then, an attribute predictor further refines the semantic features of the objects. These refined features are subsequently integrated and fed into the decoder, enhancing the model's understanding of the image context. Experimental results on the COCO and nocaps datasets demonstrate that OPCap effectively mitigates hallucination and significantly improves the quality of generated captions.

📄 PDF Abstract BibTeX arXiv:2412.00095

Code (0)

등록된 구현이 없습니다.

Tasks

AttributeDecoderHallucinationImage CaptioningObject

Similar Papers 제목 키워드 기반

CropCap: Embedding Visual Cross-Partition Dependency for Image Captioning

2023-10-27 · journal 2023 10 · Bo wang, Zhao Zhang, Suiyi Zhao, Haijun Zhang 외

Transformer-based approaches to image captioning have shown great success by utilizing long-term dependency for visual embedding. However, their coarse long-term dependency, using the multi-head self-attention mechanism …

Image Captioning

RACap: Relation-Aware Prompting for Lightweight Retrieval-Augmented Image Captioning

2025-09-19 · Xiaosheng Long, Hanyu Wang, Zhentao Song, Kun Luo 외 arxiv

Recent retrieval-augmented image captioning methods incorporate external knowledge to compensate for the limitations in comprehending complex scenes. However, current approaches face challenges in relation modeling: (1) …

Image Captioning

Topology combined machine learning for consonant recognition

2023-11-26 · Pingyao Feng, Siheng Yi, Qingrui Qu, Zhiwang Yu 외

In artificial-intelligence-aided signal processing, existing deep learning models often exhibit a black-box structure, and their validity and comprehensibility remain elusive. The integration of topological methods, desp…

Time Series

ViTOC: Vision Transformer and Object-aware Captioner

2024-11-09 · Feiyang Huang

This paper presents ViTOC (Vision Transformer and Object-aware Captioner), a novel vision-language model for image captioning that addresses the challenges of accuracy and diversity in generated descriptions. Unlike conv…

DiversityImage CaptioningLanguage ModelingLanguage Modelling+1

Caption Anything in Video: Fine-grained Object-centric Captioning via Spatiotemporal Multimodal Prompting

2025-04-07 · Yunlong Tang, Jing Bi, Chao Huang, Susan Liang 외

We present CAT-V (Caption AnyThing in Video), a training-free framework for fine-grained object-centric video captioning that enables detailed descriptions of user-selected objects through time. CAT-V integrates three ke…

Boundary DetectionObjectSemantic SegmentationVideo Captioning