Research map / Vision-language and multimodal / Cross-modal learning
Making Visual Dialogue More Engaging: A New Task, Method, and Metric
Guanghui Ye, Huan Zhao, Yingxue Gao, Zhixue Zhao, Kehan Wang, Xupeng Zha, Zhihua Jiang
Read the paperCheck your idea against 137,217 papers
AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.
Measured effects reported in the paper
| What was changed | Where | Measured | Effect |
|---|---|---|---|
| add audio utterances (ablation) | VITA-DM (7B) · Image-Chat_AVD | CIDEr: 1.08 -> 1.28 | Improved |
| add image captions (ablation) | VITA-DM (7B) · Image-Chat_AVD | CIDEr: 1.03 -> 1.28 | Improved |
| add text utterances (ablation) | VITA-DM (7B) · Image-Chat_AVD | CIDEr: 0.86 -> 1.28 | Improved |
| add ICA pre-training task (ablation) | VITA-DM (7B) · Image-Chat_AVD | CIDEr: 0.98 -> 1.28 | Improved |
| add CCL pre-training task (ablation) | VITA-DM (7B) · Image-Chat_AVD | CIDEr: 1.09 -> 1.28 | Improved |
| add NUP pre-training task (ablation) | VITA-DM (7B) · Image-Chat_AVD | CIDEr: 1.20 -> 1.28 | Improved |
| represent emotion as audio instead of text label (ablation) | VITA-DM (7B) · Image-Chat_AVD | CIDEr: 1.10 -> 1.28 | Improved |
| represent emotion as audio instead of label, Photo-Chat (ablation) | VITA-DM (7B) · Photo-Chat_AVD | CIDEr: 1.09 -> 1.24 | Improved |
| use sentiment-aware Parler-TTS instead of UniCATS (ablation) | VITA-DM (7B) · Image-Chat_AVD | CIDEr: 1.14 -> 1.28 | Improved |
| train with VITA-DM on GPT-2-Medium | GPT-2-M-345M · Image-Chat_AVD | BLEU-1: 8.01 -> 10.34 | Improved |
| train with VITA-DM on Llama-2-7B | Llama-2-7B · Image-Chat_AVD | CIDEr: 1.05 -> 1.28 | Improved |
| add audio pre-training tasks but remove all pre-training tasks, audio vs label (ablation) | VITA-DM · Image-Chat_AVD | CIDEr | Mixed |
Earlier methods this paper compares with
Named baselines from earlier accepted papers in this paper's results tables: better than 2 of 2 on most shared results.
- BI-MDRG — BI-MDRG: Bridging Image History in Multimodal Dialogue Response Generation (ECCV 2024) · better on 8 of 8 shared results
- Emotion-LLaMA — Emotion-LLaMA: Multimodal Emotion Recognition and Reasoning with Instruction Tuning (NeurIPS 2024) · better on 4 of 4 shared results
Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.
Closest papers by meaning
- SD-Eval: A Benchmark Dataset for Spoken Dialogue Understanding Beyond Words (NeurIPS 2024 · similarity 0.88)
- SayNext-Bench: Why Do LLMs Struggle with Next-Utterance Anticipation? (NeurIPS 2026 · similarity 0.87)
- V^2Dial: Unification of Video and Visual Dialog via Multimodal Experts (CVPR 2025 · similarity 0.87)
- Structure-Aware Multimodal Sequential Learning for Visual Dialog (AAAI 2024 · similarity 0.87)
- MMDU: A Multi-Turn Multi-Image Dialog Understanding Benchmark and Instruction-Tuning Dataset for LVLMs (NeurIPS 2024 · similarity 0.87)
- The Audio-Visual Conversational Graph: From an Egocentric-Exocentric Perspective (CVPR 2024 · similarity 0.86)
Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.
