Zuchao Li

Dr. Zuchao Li


Research Focus & Metrics

Academic Career Length

11Years (2016-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
1 January 2018
Verified
Conference Paper
Open access
SHShexia He
Shexia He
LZLi Zuchao
Li Zuchao
HZHai Zhao
Hai Zhao
HBHongxiao Bai
Hongxiao Bai

1 January 2024
Verified
Conference Paper
Open access
PDF file
YYYao Yao
Yao Yao
LZLi Zuchao
Li Zuchao
HZHai Zhao
Hai Zhao
Yao Yao, Zuchao Li, Hai Zhao. Findings of the Association for Computational Linguistics: NAACL 2024. 2024.

1 January 2018
Verified
Conference Paper
Open access
LZLi Zuchao
Li Zuchao
SHShexia He
Shexia He
JCJiaxun Cai
Jiaxun Cai
ZZZhuosheng Zhang
Zhuosheng Zhang
HZHai Zhao
Hai Zhao
LSLuo Si
Luo Si

22 July 2025 in IEEE Transactions on Image Processing
Verified
Journal Article
Closed access
CYCong Yang
Cong Yang
LZLi Zuchao
Li Zuchao
HJHongzan Jiao
Hongzan Jiao
ZGZHI GAO
ZHI GAO
LZLefei Zhang
Lefei Zhang
Recently, while significant progress has been made in remote sensing image change captioning, existing methods fail to filter out areas unrelated to actual changes, making models susceptible to irrelevant features. In this article, we propose a novel multimodal model for remote sensing image change captioning, guided by Key Change Features and Instruction-tuned (KCFI). This model aims to fully leverage the intrinsic knowledge of large language models through visual instructions and enhance the effectiveness and accuracy of change features using pixel-level change detection tasks. Specifically, KCFI includes a ViTs encoder for extracting bi-temporal remote sensing image features, a key feature perceiver for identifying critical change areas, a pixel-level change detection decoder to constrain key change features, and an instruction-tuned decoder based on a large language model. Moreover, to ensure that change captioning and change detection tasks are jointly optimized, we employ a dynamic weight-averaging strategy to balance the losses between the two tasks. We also explore various feature combinations for visual fine-tuning instructions and demonstrate that using only key change features to guide the large language model is the optimal choice. To validate the effectiveness of our approach, we compare it against several state-of-the-art change captioning methods on the LEVIR-CC dataset, achieving the best performance. Our code will be available at https://github.com/yangcong356/KCFI.git.

12 February 2021 in IEEE Transactions on Pattern Analysis and Machine Intelligence
Verified
Journal Article
Closed access
LZLi Zuchao
Li Zuchao
ZZZhuosheng Zhang
Zhuosheng Zhang
HZHai Zhao
Hai Zhao
RWRui Wang
Rui Wang
KCKehai Chen
Kehai Chen
ESEiichiro Sumita
Eiichiro Sumita
Text encoding is one of the most important steps in Natural Language Processing (NLP). It has been done well by the self-attention mechanism in the current state-of-the-art Transformer encoder, which has brought about significant improvements in the performance of many NLP tasks. Though the Transformer encoder may effectively capture general information in its resulting representations, the backbone information, meaning the gist of the input text, is not specifically focused on. In this paper, we propose explicit and implicit text compression approaches to enhance the Transformer encoding and evaluate models using this approach on several typical downstream tasks that rely on the encoding heavily. Our explicit text compression approaches use dedicated models to compress text, while our implicit text compression approach simply adds an additional module to the main model to handle text compression. We propose three ways of integration, namely backbone source-side fusion, target-side fusion, and both-side fusion, to integrate the backbone information into Transformer-based models for various downstream tasks. Our evaluation on benchmark datasets shows that the proposed explicit and implicit text compression approaches improve results in comparison to strong baselines. We therefore conclude, when comparing the encodings to the baseline models, text compression helps the encoders to learn better language representations.

12 June 2019 in IEEE/ACM Transactions on Audio, Speech, and Language Processing
Verified
Journal Article
Closed access
ZZZhuosheng Zhang
Zhuosheng Zhang
HZHai Zhao
Hai Zhao
KLKangwei Ling
Kangwei Ling
JLJiangtong Li
Jiangtong Li
LZLi Zuchao
Li Zuchao
GFGuohong Fu
Guohong Fu
Representation learning is the foundation of machine reading comprehension and inference. In state-of-the-art models, character-level representations have been broadly adopted to alleviate the problem of effectively representing rare or complex words. However, character itself is not a natural minimal linguistic unit for representation or word embedding composing due to ignoring the linguistic coherence of consecutive characters inside word. This paper presents a general subword-augmented embedding framework for learning and composing computationally-derived subword-level representations. We survey a series of unsupervised segmentation methods for subword acquisition and different subword-augmented strategies for text understanding, showing that subword-augmented embedding significantly improves our baselines in various types of text understanding tasks on both English and Chinese benchmarks.