no code implementations • 29 May 2024 • Xuelin Qian, Ruiqi Wu, Gong Cheng, Junwei Han
On the one hand, the appropriate adapters are selected for the inputs to process ReID, and on the other hand, the knowledge interaction and fusion between adapters are enhanced to improve the generalization ability of the model.
1 code implementation • 27 May 2024 • Zixian Huang, Wenhao Zhu, Gong Cheng, Lei LI, Fei Yuan
In order to better utilize the minds of reasoning and language understanding in LLMs, we propose a new method, namely MindMerger, which merges LLMs with the external language understanding capabilities from multilingual models to boost the multilingual reasoning performance.
1 code implementation • 17 Apr 2024 • Xiao Li, Yong Jiang, Shen Huang, Pengjun Xie, Gong Cheng, Fei Huang
Our objective is to train a generative model that can simultaneously provide a score indicating the presence of shared key point between a pair of arguments and generate the shared key point.
no code implementations • 11 Mar 2024 • Weiqing Luo, Chonggang Song, Lingling Yi, Gong Cheng
Combining semantic information with behavioral data is a crucial research area in recommender systems.
no code implementations • 20 Feb 2024 • Xiao Li, Sichen Liu, Bolin Zhu, Yin Zhu, Yiwei Liu, Gong Cheng
The application of formulas is a fundamental ability of humans when addressing numerical reasoning problems.
no code implementations • 19 Feb 2024 • Xiaxia Wang, Gong Cheng
With the continuous growth of large Knowledge Graphs (KGs), extractive KG summarization becomes a trending task.
1 code implementation • 22 Oct 2023 • Tianyu Yan, Zifu Wan, Pingping Zhang, Gong Cheng, Huchuan Lu
To relieve these issues, in this work we propose a novel Transformer-based learning framework named TransY-Net for remote sensing image CD, which improves the feature extraction from a global view and combines multi-level visual features in a pyramid manner.
no code implementations • 22 Sep 2023 • Yin Zhu, Zhiling Luo, Gong Cheng
On one hand, Information Retriever (IR) is hindered by the low quality of generated queries by LLM.
1 code implementation • ICCV 2023 • Xiang Yuan, Gong Cheng, Kebing Yan, Qinghua Zeng, Junwei Han
The past few years have witnessed the immense success of object detection, while current excellent detectors struggle on tackling size-limited instances.
Ranked #1 on Small Object Detection on SODA-D
3 code implementations • 7 Jun 2023 • Zixian Huang, Jiaying Zhou, Gengyang Xiao, Gong Cheng
Previous researches found that in-context learning is an effective approach to exploiting LLM, by using a few task-related labeled data as demonstration examples to construct a few-shot prompt for answering new questions.
1 code implementation • 13 Feb 2023 • Xuxiang Sun, Gong Cheng, Lei Pei, Hongda Li, Junwei Han
Advanced Patch Attacks (PAs) on object detection in natural images have pointed out the great safety vulnerability in methods based on deep neural networks.
1 code implementation • 26 Dec 2022 • Xingxing Xie, Gong Cheng, Qingyang Li, Shicheng Miao, Ke Li, Junwei Han
Current mainstream object detection methods for large aerial images usually divide large images into patches and then exhaustively detect the objects of interest on all patches, no matter whether there exist objects or not.
1 code implementation • 23 Nov 2022 • Xiao Li, Yin Zhu, Sichen Liu, Jiangzhou Ju, Yuzhong Qu, Gong Cheng
Numerical reasoning over hybrid data containing tables and long texts has recently received research attention from the AI community.
no code implementations • 22 Sep 2022 • Dongzhuoran Zhou, Baifan Zhou, Jieying Chen, Gong Cheng, Egor V. Kostylev, Evgeny Kharlamov
One important approach of KG generation is to map the raw data to a given KG schema, namely a domain ontology, and construct the entities and properties according to the ontology.
no code implementations • 22 Sep 2022 • Zhuoxun Zheng, Baifan Zhou, Dongzhuoran Zhou, Gong Cheng, Ernesto Jiménez-Ruiz, Ahmet Soylu, Evgeny Kharlamo
Industrial analytics that includes among others equipment diagnosis and anomaly detection heavily relies on integration of heterogeneous production data.
no code implementations • 12 Sep 2022 • Yu Gu, Vardaan Pahuja, Gong Cheng, Yu Su
In this survey, we situate KBQA in the broader literature of semantic parsing and give a comprehensive account of how existing KBQA approaches attempt to address the unique challenges.
no code implementations • 28 Jul 2022 • Gong Cheng, Xiang Yuan, Xiwen Yao, Kebing Yan, Qinghua Zeng, Xingxing Xie, Junwei Han
Then, to catalyze the development of SOD, we construct two large-scale Small Object Detection dAtasets (SODA), SODA-D and SODA-A, which focus on the Driving and Aerial scenarios respectively.
1 code implementation • NAACL 2022 • Zixian Huang, Ao Wu, Jiaying Zhou, Yu Gu, Yue Zhao, Gong Cheng
A trending paradigm for multiple-choice question answering (MCQA) is using a text-to-text framework.
Ranked #10 on Question Answering on OpenBookQA
1 code implementation • 21 Apr 2022 • Chunbo Lang, Binfei Tu, Gong Cheng, Junwei Han
Few-shot segmentation, which aims to segment unseen-class objects given only a handful of densely labeled samples, has received widespread attention from the community.
Ranked #49 on Few-Shot Semantic Segmentation on COCO-20i (1-shot)
1 code implementation • ACL 2022 • Xiao Li, Gong Cheng, Ziheng Chen, Yawei Sun, Yuzhong Qu
Recent machine reading comprehension datasets such as ReClor and LogiQA require performing logical reasoning over text.
1 code implementation • CVPR 2022 • Chunbo Lang, Gong Cheng, Binfei Tu, Junwei Han
Specifically, we apply an additional branch (base learner) to the conventional FSS model (meta learner) to explicitly identify the targets of base classes, i. e., the regions that do not need to be segmented.
Ranked #19 on Few-Shot Semantic Segmentation on PASCAL-5i (1-Shot)
no code implementations • 14 Mar 2022 • Gong Cheng, Wei zhang, Jr-Shin Li
In the study of induced bilinear systems, the classical Lie algebra rank condition (LARC) is known to be impractical since it requires computing the rank everywhere.
no code implementations • 20 Jan 2022 • Kun Song, Junwei Han, Gong Cheng, Jiwen Lu, Feiping Nie
In this paper, we reveal that metric learning would suffer from serious inseparable problem if without informative sample mining.
no code implementations • 6 Jan 2022 • Yang Long, Gui-Song Xia, Liangpei Zhang, Gong Cheng, Deren Li
Finally, we perform ASP by unifying the tile-level scene classification and object-based image analysis to achieve pixel-wise semantic labeling.
1 code implementation • CVPR 2022 • Xuxiang Sun, Gong Cheng, Hongda Li, Lei Pei, Junwei Han
Finally, in accordance with the in-depth observations for the methods based on proxy data, we argue that leveraging the proxy data is still an effective way for surrogate training.
1 code implementation • CVPR 2022 • Xiaoxu Feng, Xiwen Yao, Gong Cheng, Junwei Han
Object rotation is among long-standing, yet still unexplored, hard issues encountered in the task of weakly supervised object detection (WSOD) from aerial images.
no code implementations • 28 Dec 2021 • Wei Miao, Gong Cheng, Jr-Shin Li
In this paper, we study the problem of learning dynamical properties of ensemble systems from their collective behaviors using statistical approaches in reproducing kernel Hilbert space (RKHS).
1 code implementation • 5 Oct 2021 • Gong Cheng, Jiabao Wang, Ke Li, Xingxing Xie, Chunbo Lang, Yanqing Yao, Junwei Han
Nowadays, oriented detectors mostly use horizontal boxes as intermedium to derive oriented boxes from them.
1 code implementation • Findings (EMNLP) 2021 • Zixian Huang, Ao Wu, Yulin Shen, Gong Cheng, Yuzhong Qu
Scenario-based question answering (SQA) requires retrieving and reading paragraphs from a large corpus to answer a question which is contextualized by a long scenario description.
4 code implementations • ICCV 2021 • Xingxing Xie, Gong Cheng, Jiabao Wang, Xiwen Yao, Junwei Han
Current state-of-the-art two-stage detectors generate oriented proposals through time-consuming schemes.
Ranked #10 on Object Detection In Aerial Images on DOTA (using extra training data)
no code implementations • 16 Apr 2021 • Dingwen Zhang, Junwei Han, Gong Cheng, Ming-Hsuan Yang
As an emerging and challenging problem in the computer vision community, weakly supervised object localization and detection plays an important role for developing new generation computer vision systems and has received significant attention in the past decade.
1 code implementation • 14 Jan 2021 • Xiao Li, Yawei Sun, Gong Cheng
To solve the task, we extend state-of-the-art MRC methods with TTGen, a novel table-to-text generator.
no code implementations • 3 May 2020 • Gong Cheng, Xingxing Xie, Junwei Han, Lei Guo, Gui-Song Xia
Considering the rapid evolution of this field, this paper provides a systematic survey of deep learning methods for remote sensing image scene classification by covering more than 160 papers.
1 code implementation • 1 May 2020 • Shuxin Li, Zixian Huang, Gong Cheng, Evgeny Kharlamov, Kalpa Gunaratna
A prominent application of knowledge graph (KG) is document enrichment.
1 code implementation • 1 May 2020 • Junyou Li, Gong Cheng, Qingxia Liu, Wen Zhang, Evgeny Kharlamov, Kalpa Gunaratna, Huajun Chen
In a large-scale knowledge graph (KG), an entity is often described by a large number of triple-structured facts.
1 code implementation • 31 Mar 2020 • Yawei Sun, Lingling Zhang, Gong Cheng, Yuzhong Qu
This dedicated coarse-grained formalism with a BERT-based parsing algorithm helps to improve the accuracy of the downstream fine-grained semantic parsing.
no code implementations • 8 Mar 2020 • Qingxia Liu, Gong Cheng, Kalpa Gunaratna, Yuzhong Qu
In this paper, we create an Entity Summarization BenchMark (ESBM) which overcomes the limitations of existing benchmarks and meets standard desiderata for a benchmark.
1 code implementation • 8 Mar 2020 • Qingxia Liu, Gong Cheng, Yuzhong Qu
Entity summarization has been a prominent task over knowledge graphs.
1 code implementation • 24 Feb 2020 • Shuxin Li, Gong Cheng, Chengkai Li
We prove that verifying the success of a sub-query turns into finding an entity (called a certificate) that satisfies a distance-based condition about the query entities.
no code implementations • 18 Oct 2019 • Qingxia Liu, Gong Cheng, Kalpa Gunaratna, Yuzhong Qu
This has motivated fruitful research on automated generation of summaries for entity descriptions to satisfy users' information needs efficiently and effectively.
no code implementations • 11 Oct 2019 • Tianshuo Zhou, Ziyang Li, Gong Cheng, Jun Wang, Yu'Ang Wei
The model applies to meta-path based relevance where a meta-path characterizes a particular type of semantics of relating the query entity to answer entities.
1 code implementation • 31 Aug 2019 • Ke Li, Gang Wan, Gong Cheng, Liqiu Meng, Junwei Han
However, the current survey of datasets and deep learning based methods for object detection in optical remote sensing images is not adequate.
no code implementations • 29 Aug 2019 • Jinchi Chen, Xiaxia Wang, Gong Cheng, Evgeny Kharlamov, Yuzhong Qu
Reusing published datasets on the Web is of great interest to researchers and developers.
no code implementations • IJCNLP 2019 • Zixian Huang, Yulin Shen, Xiao Li, Yuang Wei, Gong Cheng, Lin Zhou, Xin-yu Dai, Yuzhong Qu
Scenario-based question answering (SQA) has attracted increasing research attention.
no code implementations • 2 Jul 2019 • Xiaxia Wang, Jinchi Chen, Shuxin Li, Gong Cheng, Jeff Z. Pan, Evgeny Kharlamov, Yuzhong Qu
Reusing existing datasets is of considerable significance to researchers and developers.
no code implementations • COLING 2018 • Yawei Sun, Gong Cheng, Yuzhong Qu
Complex questions in reading comprehension tasks require integrating information from multiple sentences.
no code implementations • 15 May 2018 • Seyedamin Pouriyeh, Mehdi Allahyari, Qingxia Liu, Gong Cheng, Hamid Reza Arabnia, Yuzhong Qu, Krys Kochut
Ontologies have been widely used in numerous and varied applications, e. g., to support data modeling, information integration, and knowledge management.
Information Retrieval
no code implementations • IJCNLP 2017 • Seyedamin Pouriyeh, Mehdi Allahyari, Krzysztof Kochut, Gong Cheng, Hamid Reza Arabnia
With the advent of the Internet, the amount of Semantic Web documents that describe real-world entities and their inter-links as a set of statements have grown considerably.
4 code implementations • 1 Mar 2017 • Gong Cheng, Junwei Han, Xiaoqiang Lu
During the past years, significant efforts have been made to develop various datasets or present a variety of approaches for scene classification from remote sensing images.
no code implementations • CVPR 2016 • Gong Cheng, Peicheng Zhou, Junwei Han
This is achieved by introducing and learning a rotation-invariant layer and a Fisher discriminative layer, respectively, on the basis of the existing high-capacity CNN architectures.
no code implementations • 20 Mar 2016 • Gong Cheng, Junwei Han
This paper aims to provide a review of the recent progress in this field.
no code implementations • CVPR 2015 • Gong Cheng, Junwei Han, Lei Guo, Tianming Liu
Part model-based methods have been successfully applied to object detection and scene classification and have achieved state-of-the-art results.