Alert button
Picture for Jianbing Zhang

Jianbing Zhang

Alert button

Cobra Effect in Reference-Free Image Captioning Metrics

Feb 18, 2024
Zheng Ma, Changxin Wang, Yawen Ouyang, Fei Zhao, Jianbing Zhang, Shujian Huang, Jiajun Chen

Viaarxiv icon

EFUF: Efficient Fine-grained Unlearning Framework for Mitigating Hallucinations in Multimodal Large Language Models

Feb 15, 2024
Shangyu Xing, Fei Zhao, Zhen Wu, Tuo An, Weihao Chen, Chunhui Li, Jianbing Zhang, Xinyu Dai

Viaarxiv icon

SeeClick: Harnessing GUI Grounding for Advanced Visual GUI Agents

Jan 17, 2024
Kanzhi Cheng, Qiushi Sun, Yougang Chu, Fangzhi Xu, Yantao Li, Jianbing Zhang, Zhiyong Wu

Viaarxiv icon

M2DF: Multi-grained Multi-curriculum Denoising Framework for Multimodal Aspect-based Sentiment Analysis

Oct 23, 2023
Fei Zhao, Chunhui Li, Zhen Wu, Yawen Ouyang, Jianbing Zhang, Xinyu Dai

Figure 1 for M2DF: Multi-grained Multi-curriculum Denoising Framework for Multimodal Aspect-based Sentiment Analysis
Figure 2 for M2DF: Multi-grained Multi-curriculum Denoising Framework for Multimodal Aspect-based Sentiment Analysis
Figure 3 for M2DF: Multi-grained Multi-curriculum Denoising Framework for Multimodal Aspect-based Sentiment Analysis
Figure 4 for M2DF: Multi-grained Multi-curriculum Denoising Framework for Multimodal Aspect-based Sentiment Analysis
Viaarxiv icon

Bounding and Filling: A Fast and Flexible Framework for Image Captioning

Oct 15, 2023
Zheng Ma, Changxin Wang, Bo Huang, Zixuan Zhu, Jianbing Zhang

Viaarxiv icon

DRIN: Dynamic Relation Interactive Network for Multimodal Entity Linking

Oct 09, 2023
Shangyu Xing, Fei Zhao, Zhen Wu, Chunhui Li, Jianbing Zhang, Xinyu Dai

Figure 1 for DRIN: Dynamic Relation Interactive Network for Multimodal Entity Linking
Figure 2 for DRIN: Dynamic Relation Interactive Network for Multimodal Entity Linking
Figure 3 for DRIN: Dynamic Relation Interactive Network for Multimodal Entity Linking
Figure 4 for DRIN: Dynamic Relation Interactive Network for Multimodal Entity Linking
Viaarxiv icon

Food-500 Cap: A Fine-Grained Food Caption Benchmark for Evaluating Vision-Language Models

Aug 06, 2023
Zheng Ma, Mianzhi Pan, Wenhan Wu, Kanzhi Cheng, Jianbing Zhang, Shujian Huang, Jiajun Chen

Figure 1 for Food-500 Cap: A Fine-Grained Food Caption Benchmark for Evaluating Vision-Language Models
Figure 2 for Food-500 Cap: A Fine-Grained Food Caption Benchmark for Evaluating Vision-Language Models
Figure 3 for Food-500 Cap: A Fine-Grained Food Caption Benchmark for Evaluating Vision-Language Models
Figure 4 for Food-500 Cap: A Fine-Grained Food Caption Benchmark for Evaluating Vision-Language Models
Viaarxiv icon

ADS-Cap: A Framework for Accurate and Diverse Stylized Captioning with Unpaired Stylistic Corpora

Aug 02, 2023
Kanzhi Cheng, Zheng Ma, Shi Zong, Jianbing Zhang, Xinyu Dai, Jiajun Chen

Viaarxiv icon

Beyond Generic: Enhancing Image Captioning with Real-World Knowledge using Vision-Language Pre-Training Model

Aug 02, 2023
Kanzhi Cheng, Wenpo Song, Zheng Ma, Wenhao Zhu, Zixuan Zhu, Jianbing Zhang

Figure 1 for Beyond Generic: Enhancing Image Captioning with Real-World Knowledge using Vision-Language Pre-Training Model
Figure 2 for Beyond Generic: Enhancing Image Captioning with Real-World Knowledge using Vision-Language Pre-Training Model
Figure 3 for Beyond Generic: Enhancing Image Captioning with Real-World Knowledge using Vision-Language Pre-Training Model
Figure 4 for Beyond Generic: Enhancing Image Captioning with Real-World Knowledge using Vision-Language Pre-Training Model
Viaarxiv icon

Probing Cross-modal Semantics Alignment Capability from the Textual Perspective

Oct 18, 2022
Zheng Ma, Shi Zong, Mianzhi Pan, Jianbing Zhang, Shujian Huang, Xinyu Dai, Jiajun Chen

Figure 1 for Probing Cross-modal Semantics Alignment Capability from the Textual Perspective
Figure 2 for Probing Cross-modal Semantics Alignment Capability from the Textual Perspective
Figure 3 for Probing Cross-modal Semantics Alignment Capability from the Textual Perspective
Figure 4 for Probing Cross-modal Semantics Alignment Capability from the Textual Perspective
Viaarxiv icon