Výsledky vyhledávání - "Fu, XiangHua"

Report

Stain-aware Domain Alignment for Imbalance Blood Cell Classification

Autor: Li, Yongcheng, Cai, Lingcong, Lu, Ying, Fu, Xianghua, Han, Xiao, Li, Ma, Lai, Wenxing, Zhang, Xiangzhong, Fan, Xiaomao

Blood cell identification is critical for hematological analysis as it aids physicians in diagnosing various blood-related diseases. In real-world scenarios, blood cell image datasets often present the issues of domain shift and data imbalance, posin

Externí odkaz: http://arxiv.org/abs/2412.02976

Zobrazit plný text záznamu

Report

Multi-intent Aware Contrastive Learning for Sequential Recommendation

Autor: Huang, Junshu, Long, Zi, Fu, Xianghua, Chen, Yin

Intent is a significant latent factor influencing user-item interaction sequences. Prevalent sequence recommendation models that utilize contrastive learning predominantly rely on single-intent representations to direct the training process. However,

Externí odkaz: http://arxiv.org/abs/2409.08733

Zobrazit plný text záznamu

Report

Multimodal Multi-turn Conversation Stance Detection: A Challenge Dataset and Effective Model

Autor: Niu, Fuqiang, Cheng, Zebang, Fu, Xianghua, Peng, Xiaojiang, Dai, Genan, Chen, Yin, Huang, Hu, Zhang, Bowen

Stance detection, which aims to identify public opinion towards specific targets using social media data, is an important yet challenging task. With the proliferation of diverse multimodal social media content including text, and images multimodal st

Externí odkaz: http://arxiv.org/abs/2409.00597

Zobrazit plný text záznamu

Report

DATTA: Towards Diversity Adaptive Test-Time Adaptation in Dynamic Wild World

Autor: Ye, Chuyang, Wei, Dongyan, Liu, Zhendong, Pang, Yuanyi, Lin, Yixi, Liao, Jiarong, Jiang, Qinting, Fu, Xianghua, Li, Qing, Jiang, Jingyan

Test-time adaptation (TTA) effectively addresses distribution shifts between training and testing data by adjusting models on test samples, which is crucial for improving model inference in real-world applications. However, traditional TTA methods ty

Externí odkaz: http://arxiv.org/abs/2408.08056

Zobrazit plný text záznamu

Report

Exploring the Necessity of Visual Modality in Multimodal Machine Translation using Authentic Datasets

Autor: Long, Zi, Tang, Zhenhao, Fu, Xianghua, Chen, Jian, Hou, Shilong, Lyu, Jinze

Recent research in the field of multimodal machine translation (MMT) has indicated that the visual modality is either dispensable or offers only marginal advantages. However, most of these conclusions are drawn from the analysis of experimental resul

Externí odkaz: http://arxiv.org/abs/2404.06107

Zobrazit plný text záznamu

Report

Investigating Chain-of-thought with ChatGPT for Stance Detection on Social Media

Autor: Zhang, Bowen, Fu, Xianghua, Ding, Daijun, Huang, Hu, Dai, Genan, Yin, Nan, Li, Yangyang, Jing, Liwen

Stance detection predicts attitudes towards targets in texts and has gained attention with the rise of social media. Traditional approaches include conventional machine learning, early deep neural networks, and pre-trained fine-tuning models. However

Externí odkaz: http://arxiv.org/abs/2304.03087

Zobrazit plný text záznamu

Report

Multimodal Neural Machine Translation with Search Engine Based Image Retrieval

Autor: Tang, ZhenHao, Zhang, XiaoBing, Long, Zi, Fu, XiangHua

Recently, numbers of works shows that the performance of neural machine translation (NMT) can be improved to a certain extent with using visual information. However, most of these conclusions are drawn from the analysis of experimental results based

Externí odkaz: http://arxiv.org/abs/2208.00767

Zobrazit plný text záznamu