Search Results for author: Shan Zhao

Found 11 papers, 3 papers with code

Efficient Subseasonal Weather Forecast using Teleconnection-informed Transformers

no code implementations31 Jan 2024 Shan Zhao, Zhitong Xiong, Xiao Xiang Zhu

Subseasonal forecasting, which is pivotal for agriculture, water resource management, and early warning of disasters, faces challenges due to the chaotic nature of the atmosphere.

Weather Forecasting

A Dual-way Enhanced Framework from Text Matching Point of View for Multimodal Entity Linking

1 code implementation19 Dec 2023 Shezheng Song, Shan Zhao, Chengyu Wang, Tianwei Yan, Shasha Li, Xiaoguang Mao, Meng Wang

Multimodal Entity Linking (MEL) aims at linking ambiguous mentions with multimodal information to entity in Knowledge Graph (KG) such as Wikipedia, which plays a key role in many applications.

Entity Linking Text Matching

How to Bridge the Gap between Modalities: A Comprehensive Survey on Multimodal Large Language Model

no code implementations10 Nov 2023 Shezheng Song, Xiaopeng Li, Shasha Li, Shan Zhao, Jie Yu, Jun Ma, Xiaoguang Mao, Weimin Zhang

The study surveys existing modal alignment methods in MLLMs into four groups: (1) Multimodal Converters that change data into something LLMs can understand; (2) Multimodal Perceivers to improve how LLMs perceive different types of data; (3) Tools Assistance for changing data into one common format, usually text; and (4) Data-Driven methods that teach LLMs to understand specific types of data in a dataset.

Language Modelling Large Language Model

Exploring Geometric Deep Learning For Precipitation Nowcasting

no code implementations11 Sep 2023 Shan Zhao, Sudipan Saha, Zhitong Xiong, Niklas Boers, Xiao Xiang Zhu

Motivated by this, we explore a geometric deep learning-based temporal Graph Convolutional Network (GCN) for precipitation nowcasting.

Rt-Track: Robust Tricks for Multi-Pedestrian Tracking

no code implementations16 Mar 2023 Yukuan Zhang, Yunhua Jia, Housheng Xie, Mengzhen Li, Limin Zhao, Yang Yang, Shan Zhao

However, modeling the motion and appearance models of objects in complex scenes still faces various challenging issues.

Multi-Object Tracking Object +1

InterFace:Adjustable Angular Margin Inter-class Loss for Deep Face Recognition

no code implementations5 Oct 2022 Meng Sang, Jiaxuan Chen, Mengzhen Li, Pan Tan, Anning Pan, Shan Zhao, Yang Yang

In the field of face recognition, it is always a hot research topic to improve the loss solution to make the face features extracted by the network have greater discriminative power.

Face Model Face Recognition

Reiterative Domain Aware Multi-Target Adaptation

no code implementations26 Aug 2021 Sudipan Saha, Shan Zhao, Nasrullah Sheikh, Xiao Xiang Zhu

Multi-target domain adaptation is a powerful extension in which a single classifier is learned for multiple unlabeled target domains.

Domain Adaptation Multi-target Domain Adaptation

Modeling Dense Cross-Modal Interactions for Joint Entity-Relation Extraction

no code implementations1 Jul 2020 Shan Zhao, Minghao Hu, Zhiping Cai, Fang Liu

The network is carefully constructed by stacking multiple attention units in depth to fully model dense interactions over token-label spaces, in which two basic attention units are proposed to explicitly capture fine-grained correlations across different modalities (e. g., token-to-token and labelto-token).

Joint Entity and Relation Extraction Relation +1

The Utility of General Domain Transfer Learning for Medical Language Tasks

no code implementations16 Feb 2020 Daniel Ranti, Katie Hanss, Shan Zhao, Varun Arvind, Joseph Titano, Anthony Costa, Eric Oermann

The BERT models using either set of pretrained checkpoints outperformed the logistic regression model, achieving sample-weighted average F1-scores of 0. 87 and 0. 87 for the general domain model and the combined general and biomedical-domain model.

General Classification Multi-class Classification +4

Cannot find the paper you are looking for? You can Submit a new open access paper.