activity
20182025
most citedSZTU-CMU at MER2024: Improving Emotion-LLaMA with Conv-Attention for Multimodal Emotion Recognition

8 citations · 18 across the 13 of their papers we have counts for

collaborators

34 papers

cs.LG2025

MaxSup: Overcoming Representation Collapse in Label Smoothing

Yuxuan Zhou, Heng Li, Zhi-Qi Cheng +4

Label Smoothing (LS) is widely adopted to reduce overconfidence in neural network predictions and improve generalization. Despite these benefits, recent studies reveal two critical…

cs.CV2024

POPoS: Improving Efficient and Robust Facial Landmark Detection with Parallel Optimal Position Search

Chong-Yang Xiang, Jun-Yan He, Zhi-Qi Cheng +2

Achieving a balance between accuracy and efficiency is a critical challenge in facial landmark detection (FLD). This paper introduces Parallel Optimal Position Search (POPoS), a hi…

cs.MM20248 cited

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…

cs.MM2024

Music2P: A Multi-Modal AI-Driven Tool for Simplifying Album Cover Design

Joong Ho Choi, Geonyeong Choi, Ji-Eun Han +2

In today's music industry, album cover design is as crucial as the music itself, reflecting the artist's vision and brand. However, many AI-driven album cover services require subs…

cs.CV2024

Robust Adaptation of Foundation Models with Black-Box Visual Prompting

Changdae Oh, Gyeongdeok Seo, Geunyoung Jung +4

With a surge of large-scale pre-trained models, parameter-efficient transfer learning (PETL) of large models has garnered significant attention. While promising, they commonly rely…

cs.AI2024

MetaDesigner: Advancing Artistic Typography Through AI-Driven, User-Centric, and Multilingual WordArt Synthesis

Jun-Yan He, Zhi-Qi Cheng, Chenyang Li +11

MetaDesigner introduces a transformative framework for artistic typography synthesis, powered by Large Language Models (LLMs) and grounded in a user-centric design paradigm. Its fo…