Search Results for author: Fan Bai

Found 28 papers, 12 papers with code

AON: Towards Arbitrarily-Oriented Text Recognition

1 code implementation CVPR 2018 Zhanzhan Cheng, Yangliu Xu, Fan Bai, Yi Niu, ShiLiang Pu, Shuigeng Zhou

Existing methods on text recognition mainly work with regular (horizontal and frontal) texts and cannot be trivially generalized to handle irregular texts.

Optical Character Recognition Optical Character Recognition (OCR) +1

PromptAgent: Strategic Planning with Language Models Enables Expert-level Prompt Optimization

1 code implementation25 Oct 2023 Xinyuan Wang, Chenxi Li, Zhen Wang, Fan Bai, Haotian Luo, Jiayou Zhang, Nebojsa Jojic, Eric P. Xing, Zhiting Hu

Highly effective, task-specific prompts are often heavily engineered by experts to integrate detailed instructions and domain insights based on a deep understanding of both instincts of large language models (LLMs) and the intricacies of the target task.

Navigate

UAE: Universal Anatomical Embedding on Multi-modality Medical Images

1 code implementation25 Nov 2023 Xiaoyu Bai, Fan Bai, Xiaofei Huo, Jia Ge, JingJing Lu, Xianghua Ye, Ke Yan, Yong Xia

They use self-supervised learning to acquire a discriminative embedding for each voxel within the image.

Self-Supervised Learning

Structured Minimally Supervised Learning for Neural Relation Extraction

1 code implementation NAACL 2019 Fan Bai, Alan Ritter

Our approach achieves state-of-the-art results on minimally supervised sentential relation extraction, outperforming a number of baselines, including a competitive approach that uses the attention layer of a purely neural model.

Relation Relation Extraction +1

Schema-Driven Information Extraction from Heterogeneous Tables

1 code implementation23 May 2023 Fan Bai, Junmo Kang, Gabriel Stanovsky, Dayne Freitag, Alan Ritter

We use this collection of annotated tables to evaluate the ability of open-source and API-based language models to extract information from tables covering diverse domains and data formats.

Attribute Extraction Instruction Following +1

Hierarchical Policy for Non-prehensile Multi-object Rearrangement with Deep Reinforcement Learning and Monte Carlo Tree Search

1 code implementation18 Sep 2021 Fan Bai, Fei Meng, Jianbang Liu, Jiankun Wang, Max Q. -H. Meng

Non-prehensile multi-object rearrangement is a robotic task of planning feasible paths and transferring multiple objects to their predefined target poses without grasping.

Object

SynKB: Semantic Search for Synthetic Procedures

1 code implementation15 Aug 2022 Fan Bai, Alan Ritter, Peter Madrid, Dayne Freitag, John Niekrasz

In this paper we present SynKB, an open-source, automatically extracted knowledge base of chemical synthesis protocols.

Pre-train or Annotate? Domain Adaptation with a Constrained Budget

1 code implementation EMNLP 2021 Fan Bai, Alan Ritter, Wei Xu

Our experiments suggest task-specific data annotation should be part of an economical strategy when adapting an NLP model to a new domain.

Domain Adaptation

Process-Level Representation of Scientific Protocols with Interactive Annotation

2 code implementations EACL 2021 Ronen Tamari, Fan Bai, Alan Ritter, Gabriel Stanovsky

We develop Process Execution Graphs (PEG), a document-level representation of real-world wet lab biochemistry protocols, addressing challenges such as cross-sentence relations, long-range coreference, grounding, and implicit arguments.

Relation Extraction Sentence

Few-Shot Anaphora Resolution in Scientific Protocols via Mixtures of In-Context Experts

1 code implementation7 Oct 2022 Nghia T. Le, Fan Bai, Alan Ritter

As far as we are aware, this is the first work to present experimental results demonstrating the effectiveness of in-context learning on the task of few-shot anaphora resolution in scientific protocols.

In-Context Learning Language Modelling +1

Entity Tracking via Effective Use of Multi-Task Learning Model and Mention-guided Decoding

2 code implementations12 Oct 2022 Janvijay Singh, Fan Bai, Zhen Wang

Cross-task knowledge transfer via multi-task learning has recently made remarkable progress in general NLP tasks.

Multi-Task Learning

Edit Probability for Scene Text Recognition

no code implementations CVPR 2018 Fan Bai, Zhanzhan Cheng, Yi Niu, ShiLiang Pu, Shuigeng Zhou

The advantage lies in that the training process can focus on the missing, superfluous and unrecognized characters, and thus the impact of the misalignment problem can be alleviated or even overcome.

Scene Text Recognition

Focusing Attention: Towards Accurate Text Recognition in Natural Images

no code implementations ICCV 2017 Zhanzhan Cheng, Fan Bai, Yunlu Xu, Gang Zheng, ShiLiang Pu, Shuigeng Zhou

FAN consists of two major components: an attention network (AN) that is responsible for recognizing character targets as in the existing methods, and a focusing network (FN) that is responsible for adjusting attention by evaluating whether AN pays attention properly on the target areas in the images.

Scene Text Recognition

Label Propagation on K-partite Graphs with Heterophily

no code implementations21 Jan 2017 Dingxiong Deng, Fan Bai, Yiqi Tang, Shuigeng Zhou, Cyrus Shahabi, Linhong Zhu

In this paper, for the first time, we study label propagation in heterogeneous graphs under heterophily assumption.

Online Learning for Wireless Distributed Computing

no code implementations9 Nov 2016 Yi-Hsuan Kao, Kwame Wright, Bhaskar Krishnamachari, Fan Bai

To the best of our knowledge, MABSTA is the first online algorithm in this domain of task assignment problems and provides provable performance guarantee.

Distributed Computing

Text Recognition in Real Scenarios with a Few Labeled Samples

no code implementations22 Jun 2020 Jinghuang Lin, Zhanzhan Cheng, Fan Bai, Yi Niu, ShiLiang Pu, Shuigeng Zhou

Scene text recognition (STR) is still a hot research topic in computer vision field due to its various applications.

Domain Adaptation Scene Text Recognition

Spatial clustering and common regulatory elements correlate with coordinated gene expression

no code implementations18 Jan 2019 Jingyu Zhang, HengYu Chen, Ruoyan Li, David A. Taft, Guang Yao, Fan Bai, Jianhua Xing

Many cellular responses to surrounding cues require temporally concerted transcriptional regulation of multiple genes.

Clustering

Federated Face Recognition

no code implementations6 May 2021 Fan Bai, Jiaxiang Wu, Pengcheng Shen, Shaoxin Li, Shuigeng Zhou

Face recognition has been extensively studied in computer vision and artificial intelligence communities in recent years.

Face Recognition Federated Learning +1

An age-of-infection model with both symptomatic and asymptomatic infections

no code implementations3 Nov 2021 Fan Bai

We formulate a general age-of-infection epidemic model with two pathways: the symptomatic infections and the asymptomatic infections.

Relation

C3-STISR: Scene Text Image Super-resolution with Triple Clues

no code implementations29 Apr 2022 Minyi Zhao, Miao Wang, Fan Bai, Bingjia Li, Jie Wang, Shuigeng Zhou

In this paper, we present a novel method C3-STISR that jointly exploits the recognizer's feedback, visual and linguistical information as clues to guide super-resolution.

Image Super-Resolution Language Modelling +1

Matching in the Wild: Learning Anatomical Embeddings for Multi-Modality Images

no code implementations7 Jul 2023 Xiaoyu Bai, Fan Bai, Xiaofei Huo, Jia Ge, Tony C. W. Mok, Zi Li, Minfeng Xu, Jingren Zhou, Le Lu, Dakai Jin, Xianghua Ye, JingJing Lu, Ke Yan

We then use this SAM to identify corresponding regions on paired images using robust grid-points matching, followed by a point-set based affine/rigid registration, and a deformable fine-tuning step to produce registered paired images.

SLPT: Selective Labeling Meets Prompt Tuning on Label-Limited Lesion Segmentation

no code implementations9 Aug 2023 Fan Bai, Ke Yan, Xiaoyu Bai, Xinyu Mao, Xiaoli Yin, Jingren Zhou, Yu Shi, Le Lu, Max Q. -H. Meng

We evaluate our method on liver tumor segmentation and achieve state-of-the-art performance, outperforming traditional fine-tuning with only 6% of tunable parameters, also achieving 94% of full-data performance by labeling only 5% of the data.

Lesion Segmentation Tumor Segmentation +1

Discrepancy-based Active Learning for Weakly Supervised Bleeding Segmentation in Wireless Capsule Endoscopy Images

no code implementations9 Aug 2023 Fan Bai, Xiaohan Xing, Yutian SHEN, Han Ma, Max Q. -H. Meng

Specifically, to liberate labor, we design a novel discrepancy decoder model and a CAMPUS (CAM, Pseudo-label and groUnd-truth Selection) criterion to replace the noisy CAMs with accurate model predictions and a few human labels.

Active Learning Pseudo Label

A Consumer-tier based Visual-Brain Machine Interface for Augmented Reality Glasses Interactions

no code implementations29 Aug 2023 Yuying Jiang, Fan Bai, ZiCheng Zhang, Xiaochen Ye, Zheng Liu, Zhiping Shi, Jianwei Yao, Xiaojun Liu, Fangkun Zhu, Junling Li Qian Guo, Xiaoan Wang, Junwen Luo

Here we develop a consumer-tier Visual-Brain Machine Inteface(V-BMI) system specialized for Augmented Reality(AR) glasses interactions.

Prediction of vaccination coverage level in the heterogeneous mixing population

no code implementations29 Feb 2024 Fan Bai, Qianyu Chen, Yizhuo Xu

Heterogeneity of population is a key factor in modeling the transmission of disease among the population and has huge impact on the outcome of the transmission.

Decision Making Management

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