ICCV23 Visual-Dialog Emotion Explanation Challenge: SEU_309 Team Technical Report
This addresses the challenge of explaining emotions in art discussions for AI and vision-language communities, but it is incremental as it combines existing models.
The paper tackled the problem of generating emotion explanations from visual-dialog interactions in art discussions, achieving top rank in the ICCV23 challenge with significant scores in F1 and BLEU metrics.
The Visual-Dialog Based Emotion Explanation Generation Challenge focuses on generating emotion explanations through visual-dialog interactions in art discussions. Our approach combines state-of-the-art multi-modal models, including Language Model (LM) and Large Vision Language Model (LVLM), to achieve superior performance. By leveraging these models, we outperform existing benchmarks, securing the top rank in the ICCV23 Visual-Dialog Based Emotion Explanation Generation Challenge, which is part of the 5th Workshop On Closing The Loop Between Vision And Language (CLCV) with significant scores in F1 and BLEU metrics. Our method demonstrates exceptional ability in generating accurate emotion explanations, advancing our understanding of emotional impacts in art.