42 citations · 253 across the 45 of their papers we have counts for
47 papers
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…
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…
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…
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…
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…
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…
Human-Aware Vision-and-Language Navigation: Bridging Simulation to Reality with Dynamic Human Interactions
Heng Li, Minghan Li, Zhi-Qi Cheng +6
Vision-and-Language Navigation (VLN) aims to develop embodied agents that navigate based on human instructions. However, current VLN frameworks often rely on static environments an…
Emotion-LLaMA: Multimodal Emotion Recognition and Reasoning with Instruction Tuning
Zebang Cheng, Zhi-Qi Cheng, Jun-Yan He +6
Accurate emotion perception is crucial for various applications, including human-computer interaction, education, and counseling. However, traditional single-modality approaches of…
MotionFollower: Editing Video Motion via Lightweight Score-Guided Diffusion
Shuyuan Tu, Qi Dai, Zihao Zhang +6
Despite impressive advancements in diffusion-based video editing models in altering video attributes, there has been limited exploration into modifying motion information while pre…
MIPS at SemEval-2024 Task 3: Multimodal Emotion-Cause Pair Extraction in Conversations with Multimodal Language Models
Zebang Cheng, Fuqiang Niu, Yuxiang Lin +3
This paper presents our winning submission to Subtask 2 of SemEval 2024 Task 3 on multimodal emotion cause analysis in conversations. We propose a novel Multimodal Emotion Recognit…
UMETTS: A Unified Framework for Emotional Text-to-Speech Synthesis with Multimodal Prompts
Zhi-Qi Cheng, Xiang Li, Jun-Yan He +4
Emotional Text-to-Speech (E-TTS) synthesis has garnered significant attention in recent years due to its potential to revolutionize human-computer interaction. However, current E-T…
LEAF: Unveiling Two Sides of the Same Coin in Semi-supervised Facial Expression Recognition
Fan Zhang, Zhi-Qi Cheng, Jian Zhao +2
Semi-supervised learning has emerged as a promising approach to tackle the challenge of label scarcity in facial expression recognition (FER) task. However, current state-of-the-ar…
FaceChain-ImagineID: Freely Crafting High-Fidelity Diverse Talking Faces from Disentangled Audio
Chao Xu, Yang Liu, Jiazheng Xing +8
In this paper, we abstract the process of people hearing speech, extracting meaningful cues, and creating various dynamically audio-consistent talking faces, termed Listening and I…
IVAC-P2L: Leveraging Irregular Repetition Priors for Improving Video Action Counting
Hang Wang, Zhi-Qi Cheng, Youtian Du +1
Video Action Counting (VAC) is crucial in analyzing sports, fitness, and everyday activities by quantifying repetitive actions in videos. However, traditional VAC methods have over…
DyRoNet: Dynamic Routing and Low-Rank Adapters for Autonomous Driving Streaming Perception
Xiang Huang, Zhi-Qi Cheng, Jun-Yan He +3
The advancement of autonomous driving systems hinges on the ability to achieve low-latency and high-accuracy perception. To address this critical need, this paper introduces Dynami…
WordArt Designer API: User-Driven Artistic Typography Synthesis with Large Language Models on ModelScope
Jun-Yan He, Zhi-Qi Cheng, Chenyang Li +10
This paper introduces the WordArt Designer API, a novel framework for user-driven artistic typography synthesis utilizing Large Language Models (LLMs) on ModelScope. We address the…
Tracking with Human-Intent Reasoning
Jiawen Zhu, Zhi-Qi Cheng, Jun-Yan He +5
Advances in perception modeling have significantly improved the performance of object tracking. However, the current methods for specifying the target object in the initial frame a…
ProS: Prompting-to-simulate Generalized knowledge for Universal Cross-Domain Retrieval
Kaipeng Fang, Jingkuan Song, Lianli Gao +4
The goal of Universal Cross-Domain Retrieval (UCDR) is to achieve robust performance in generalized test scenarios, wherein data may belong to strictly unknown domains and categori…
MotionEditor: Editing Video Motion via Content-Aware Diffusion
Shuyuan Tu, Qi Dai, Zhi-Qi Cheng +4
Existing diffusion-based video editing models have made gorgeous advances for editing attributes of a source video over time but struggle to manipulate the motion information while…
WordArt Designer: User-Driven Artistic Typography Synthesis using Large Language Models
Jun-Yan He, Zhi-Qi Cheng, Chenyang Li +10
This paper introduces WordArt Designer, a user-driven framework for artistic typography synthesis, relying on the Large Language Model (LLM). The system incorporates four key modul…
Towards Calibrated Robust Fine-Tuning of Vision-Language Models
Changdae Oh, Hyesu Lim, Mijoo Kim +6
Improving out-of-distribution (OOD) generalization during in-distribution (ID) adaptation is a primary goal of robust fine-tuning of zero-shot models beyond naive fine-tuning. Howe…
Debunking Free Fusion Myth: Online Multi-view Anomaly Detection with Disentangled Product-of-Experts Modeling
Hao Wang, Zhi-Qi Cheng, Jingdong Sun +4
Multi-view or even multi-modal data is appealing yet challenging for real-world applications. Detecting anomalies in multi-view data is a prominent recent research topic. However,…
DCPT: Darkness Clue-Prompted Tracking in Nighttime UAVs
Jiawen Zhu, Huayi Tang, Zhi-Qi Cheng +5
Existing nighttime unmanned aerial vehicle (UAV) trackers follow an "Enhance-then-Track" architecture - first using a light enhancer to brighten the nighttime video, then employing…
Refined Temporal Pyramidal Compression-and-Amplification Transformer for 3D Human Pose Estimation
Hanbing Liu, Wangmeng Xiang, Jun-Yan He +4
Accurately estimating the 3D pose of humans in video sequences requires both accuracy and a well-structured architecture. With the success of transformers, we introduce the Refined…