5 papers
DPDEdit: Detail-Preserved Diffusion Models for Multimodal Fashion Image Editing
Xiaolong Wang, Zhi-Qi Cheng, Jue Wang +1
Fashion image editing is a crucial tool for designers to convey their creative ideas by visualizing design concepts interactively. Current fashion image editing techniques, though…
Emotion-Qwen: A Unified Framework for Emotion and Vision Understanding
Dawei Huang, Qing Li, Chuan Yan +9
Accurate emotion understanding in videos necessitates effectively recognizing and interpreting emotional states by integrating visual, textual, auditory, and contextual cues. Altho…
FlexEdit: Marrying Free-Shape Masks to VLLM for Flexible Image Editing
Tianshuo Yuan, Yuxiang Lin, Jue Wang +5
Combining Vision Large Language Models (VLLMs) with diffusion models offers a powerful method for executing image editing tasks based on human language instructions. However, langu…
Why We Feel: Breaking Boundaries in Emotional Reasoning with Multimodal Large Language Models
Yuxiang Lin, Jingdong Sun, Zhi-Qi Cheng +7
Most existing emotion analysis emphasizes which emotion arises (e.g., happy, sad, angry) but neglects the deeper why. We propose Emotion Interpretation (EI), focusing on causal fac…
SZTU-CMU at MER2024: Improving Emotion-LLaMA with Conv-Attention for Multimodal Emotion Recognition
Zebang Cheng, Shuyuan Tu, Dawei Huang +4
This paper presents our winning approach for the MER-NOISE and MER-OV tracks of the MER2024 Challenge on multimodal emotion recognition. Our system leverages the advanced emotional…