Research map / Vision-language and multimodal / Cross-modal learning
Emotion and Intention Guided Multi-Modal Learning for Sticker Response Selection
Yuxuan Hu, Jian Chen, Yuhao Wang, Zixuan Li, Jing Xiong, Pengyue Jia, Wei Wang, Chengming Li, Xiangyu Zhao
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 inter-modality emotion/intention alignment and SAMM (ablation) | EIGML · StickerChat | MAP: 80.29 -> 81.15 | Improved |
| add intra-modality alignment (ablation) | EIGML · StickerChat | MAP: 80.99 -> 81.15 | Improved |
| add EIKS (emotion-guided intention knowledge selection) (ablation) | EIGML · StickerChat | MAP: 80.64 -> 81.15 | Improved |
| add IEGA attention fusion (ablation) | EIGML · StickerChat | MAP: 80.58 -> 81.15 | Improved |
| add SAMM similarity adjustment (ablation) | EIGML · StickerChat | MAP: 80.48 -> 81.15 | Improved |
| add intention modules (ablation) | EIGML · StickerChat matching score | matching score: 0.51 -> 0.54 | Improved |
| add emotion modules (ablation) | EIGML · StickerChat matching score | matching score: 0.43 -> 0.54 | Improved |
| set emotion loss weight to 0 versus 0.5 (ablation) | EIGML · StickerChat | MAP: peak 81.15 at we=0.5 | Improved |
| use EIGML instead of PBR | EIGML · StickerChat | MAP: 79.2 -> 81.2 | Improved |
| use EIGML instead of PBR | EIGML · DSTC10-MOD | MAP: 65.0 -> 67.4 | Improved |
| use EIGML instead of PBR on cost | EIGML · computational cost | FLOPs / params: FLOPs 3.577 -> 2.053 T; params 212.65 -> 196.64 M | Improved |
Earlier methods this paper compares with
Named baselines from earlier accepted papers in this paper's results tables: better than 1 of 1 on most shared results.
- MMBERT — MMBERT: Scaled Mixture-of-Experts Multimodal BERT for Robust Chinese Hate Speech Detection Under Cloaking Perturbations (AAAI 2026) · 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
- Uncertain Multimodal Intention and Emotion Understanding in the Wild (CVPR 2025 · similarity 0.87)
- A New Formula for Sticker Retrieval: Reply with Stickers in Multi-Modal and Multi-Session Conversation (AAAI 2025 · similarity 0.87)
- Emotion-Coherent Reasoning for Multimodal LLMs via Emotional Rationale Verifier (AAAI 2026 · similarity 0.86)
- Adaptive Graph Learning for Multimodal Conversational Emotion Detection (AAAI 2024 · similarity 0.85)
- EmotionThinker: Prosody-Aware Reinforcement Learning for Explainable Speech Emotion Reasoning (ICLR 2026 · similarity 0.85)
- EMOE: Modality-Specific Enhanced Dynamic Emotion Experts (CVPR 2025 · similarity 0.84)
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.
