Search Results for author: Jie Shao

Found 38 papers, 17 papers with code

UB-FineNet: Urban Building Fine-grained Classification Network for Open-access Satellite Images

no code implementations4 Mar 2024 Zhiyi He, Wei Yao, Jie Shao, Puzuo Wang

Then, a new fine-grained classification network with Category Information Balancing Module (CIBM) and Contrastive Supervision (CS) technique is proposed to mitigate the problem of class imbalance and improve the classification robustness and accuracy.

Classification Denoising +2

Rectify the Regression Bias in Long-Tailed Object Detection

no code implementations29 Jan 2024 Ke Zhu, Minghao Fu, Jie Shao, Tianyu Liu, Jianxin Wu

While existing methods fail to handle the regression bias, the class-specific regression head for rare classes is hypothesized to be the main cause of it in this paper.

Long-tailed Object Detection Object +3

Decoupling Meta-Reinforcement Learning with Gaussian Task Contexts and Skills

1 code implementation11 Dec 2023 Hongcai He, Anjie Zhu, Shuang Liang, Feiyu Chen, Jie Shao

We propose a framework called decoupled meta-reinforcement learning (DCMRL), which (1) contrastively restricts the learning of task contexts through pulling in similar task contexts within the same task and pushing away different task contexts of different tasks, and (2) utilizes a Gaussian quantization variational autoencoder (GQ-VAE) for clustering the Gaussian distributions of the task contexts and skills respectively, and decoupling the exploration and learning processes of their spaces.

Continuous Control Meta Reinforcement Learning +3

AdaDiff: Adaptive Step Selection for Fast Diffusion

no code implementations24 Nov 2023 HUI ZHANG, Zuxuan Wu, Zhen Xing, Jie Shao, Yu-Gang Jiang

Diffusion models, as a type of generative models, have achieved impressive results in generating images and videos conditioned on textual conditions.

Denoising Image Generation +1

Examining User-Friendly and Open-Sourced Large GPT Models: A Survey on Language, Multimodal, and Scientific GPT Models

1 code implementation27 Aug 2023 Kaiyuan Gao, Sunan He, Zhenyu He, Jiacheng Lin, Qizhi Pei, Jie Shao, Wei zhang

Generative pre-trained transformer (GPT) models have revolutionized the field of natural language processing (NLP) with remarkable performance in various tasks and also extend their power to multimodal domains.

Generalized Unbiased Scene Graph Generation

no code implementations9 Aug 2023 Xinyu Lyu, Lianli Gao, Junlin Xie, Pengpeng Zeng, Yulu Tian, Jie Shao, Heng Tao Shen

To the end, we propose the Multi-Concept Learning (MCL) framework, which ensures a balanced learning process across rare/ uncommon/ common concepts.

Graph Generation Unbiased Scene Graph Generation

StreamE: Learning to Update Representations for Temporal Knowledge Graphs in Streaming Scenarios

2 code implementations journal 2023 Jiasheng Zhang, Jie Shao, Bin Cui

To reduce the parameter size, entity representations in StreamE are decoupled from the model training to serve as the memory module to store the historical information of entities.

Knowledge Graphs

ESTISR: Adapting Efficient Scene Text Image Super-resolution for Real-Scenes

no code implementations4 Jun 2023 Minghao Fu, Xin Man, Yihan Xu, Jie Shao

While scene text image super-resolution (STISR) has yielded remarkable improvements in accurately recognizing scene text, prior methodologies have placed excessive emphasis on optimizing performance, rather than paying due attention to efficiency - a crucial factor in ensuring deployment of the STISR-STR pipeline.

Image Restoration Image Super-Resolution

Urban GeoBIM construction by integrating semantic LiDAR point clouds with as-designed BIM models

no code implementations23 Apr 2023 Jie Shao, Wei Yao, Puzuo Wang, Zhiyi He, Lei Luo

In this paper, we propose a complementary strategy that integrates LiDAR point clouds with as-designed BIM models for reconstructing urban scenes.

Point Cloud Segmentation Segmentation

W-MAE: Pre-trained weather model with masked autoencoder for multi-variable weather forecasting

2 code implementations18 Apr 2023 Xin Man, Chenghong Zhang, Jin Feng, Changyu Li, Jie Shao

On the temporal scale, we fine-tune the pre-trained W-MAE to predict the future states of meteorological variables, thereby modeling the temporal dependencies present in weather data.

Precipitation Forecasting Weather Forecasting

Generalizing Math Word Problem Solvers via Solution Diversification

1 code implementation1 Dec 2022 Zhenwen Liang, Jipeng Zhang, Lei Wang, Yan Wang, Jie Shao, Xiangliang Zhang

In this paper, we design a new training framework for an MWP solver by introducing a solution buffer and a solution discriminator.

Math

One Class One Click: Quasi Scene-level Weakly Supervised Point Cloud Semantic Segmentation with Active Learning

no code implementations23 Nov 2022 Puzuo Wang, Wei Yao, Jie Shao

It considerably outperforms genuine scene-level weakly supervised methods by up to 25\% in terms of average F1 score and achieves competitive results against full supervision schemes.

Active Learning Scene Classification +1

Temporal knowledge graph representation learning with local and global evolutions

1 code implementation Knowledge-Based Systems 2022 Jiasheng Zhang, Shuang Liang, Yongpan Sheng, Jie Shao

Temporal knowledge graph (TKG) representation learning aims to project entities and relations in TKG to low-dimensional vector space while preserving the evolutionary nature of TKG.

Graph Representation Learning

SMDT: Cross-View Geo-Localization with Image Alignment and Transformer

4 code implementations IEEE International Conference on Multimedia and Expo 2022 2022 Xiaoyang Tian, Jie Shao, Deqiang Ouyang, Anjie Zhu, Feiyu Chen.

Next, we simultaneously train dual conditional generative adversarial nets by taking the semantic segmentation images and converted images as input to synthesize the aerial image with ground view style.

Segmentation Semantic Segmentation

Diverse Preference Augmentation with Multiple Domains for Cold-start Recommendations

no code implementations1 Apr 2022 Yan Zhang, Changyu Li, Ivor W. Tsang, Hui Xu, Lixin Duan, Hongzhi Yin, Wen Li, Jie Shao

Motivated by the idea of meta-augmentation, in this paper, by treating a user's preference over items as a task, we propose a so-called Diverse Preference Augmentation framework with multiple source domains based on meta-learning (referred to as MetaDPA) to i) generate diverse ratings in a new domain of interest (known as target domain) to handle overfitting on the case of sparse interactions, and to ii) learn a preference model in the target domain via a meta-learning scheme to alleviate cold-start issues.

Domain Adaptation Meta-Learning +1

Efficient divide-and-conquer registration of UAV and ground LiDAR point clouds through canopy shape context

no code implementations27 Jan 2022 Jie Shao, Wei Yao, Peng Wan, Lei Luo, Jiaxin Lyu, Wuming Zhang

Finally, we implement coarse alignment of ULS and ground LiDAR datasets by combining the results of ground alignment and image matching and finish fine registration.

Mining Contextual Information Beyond Image for Semantic Segmentation

1 code implementation ICCV 2021 Zhenchao Jin, Tao Gong, Dongdong Yu, Qi Chu, Jian Wang, Changhu Wang, Jie Shao

To address this, this paper proposes to mine the contextual information beyond individual images to further augment the pixel representations.

Image Segmentation Segmentation +1

Contrast and Order Representations for Video Self-Supervised Learning

no code implementations ICCV 2021 Kai Hu, Jie Shao, YuAn Liu, Bhiksha Raj, Marios Savvides, Zhiqiang Shen

To address this, we present a contrast-and-order representation (CORP) framework for learning self-supervised video representations that can automatically capture both the appearance information within each frame and temporal information across different frames.

Action Recognition Self-Supervised Learning

COOKIE: Contrastive Cross-Modal Knowledge Sharing Pre-Training for Vision-Language Representation

1 code implementation ICCV 2021 Keyu Wen, Jin Xia, Yuanyuan Huang, Linyang Li, Jiayan Xu, Jie Shao

There are two key designs in it, one is the weight-sharing transformer on top of the visual and textual encoders to align text and image semantically, the other is three kinds of contrastive learning designed for sharing knowledge between different modalities.

Contrastive Learning Cross-Modal Retrieval +3

Is normalization indispensable for training deep neural network?

1 code implementation NeurIPS 2020 Jie Shao, Kai Hu, Changhu Wang, xiangyang xue, Bhiksha Raj

In this paper, we study what would happen when normalization layers are removed from the network, and show how to train deep neural networks without normalization layers and without performance degradation.

General Classification Image Classification +5

Improving Generalization in Reinforcement Learning with Mixture Regularization

2 code implementations NeurIPS 2020 Kaixin Wang, Bingyi Kang, Jie Shao, Jiashi Feng

Deep reinforcement learning (RL) agents trained in a limited set of environments tend to suffer overfitting and fail to generalize to unseen testing environments.

Data Augmentation reinforcement-learning +1

E-FCNN for tiny facial expression recognition

no code implementations Applied Intelligence 2020 Jie Shao, Qiyu Cheng

To effectively leverage the texture information of faces, we design a novel three-stream super-resolution network, which is embedded with an edge-enhancement block as one branch.

Facial Expression Recognition Facial Expression Recognition (FER) +1

Temporal Context Aggregation for Video Retrieval with Contrastive Learning

1 code implementation4 Aug 2020 Jie Shao, Xin Wen, Bingchen Zhao, xiangyang xue

The current research focus on Content-Based Video Retrieval requires higher-level video representation describing the long-range semantic dependencies of relevant incidents, events, etc.

Contrastive Learning Representation Learning +2

Graph-to-Tree Learning for Solving Math Word Problems

1 code implementation ACL 2020 Jipeng Zhang, Lei Wang, Roy Ka-Wei Lee, Yi Bin, Yan Wang, Jie Shao, Ee-Peng Lim

While the recent tree-based neural models have demonstrated promising results in generating solution expression for the math word problem (MWP), most of these models do not capture the relationships and order information among the quantities well.

Math Math Word Problem Solving

TFNet: Multi-Semantic Feature Interaction for CTR Prediction

no code implementations29 Jun 2020 Shu Wu, Feng Yu, Xueli Yu, Qiang Liu, Liang Wang, Tieniu Tan, Jie Shao, Fan Huang

The CTR (Click-Through Rate) prediction plays a central role in the domain of computational advertising and recommender systems.

Click-Through Rate Prediction Recommendation Systems

Learning in High-Dimensional Multimedia Data: The State of the Art

no code implementations10 Jul 2017 Lianli Gao, Jingkuan Song, Xingyi Liu, Junming Shao, Jiajun Liu, Jie Shao

Given the high dimensionality and the high complexity of multimedia data, it is important to investigate new machine learning algorithms to facilitate multimedia data analysis.

BIG-bench Machine Learning feature selection +3

Zero-Shot Hashing via Transferring Supervised Knowledge

no code implementations16 Jun 2016 Yang Yang, Wei-Lun Chen, Yadan Luo, Fumin Shen, Jie Shao, Heng Tao Shen

Supervised knowledge e. g. semantic labels or pair-wise relationship) associated to data is capable of significantly improving the quality of hash codes and hash functions.

Image Retrieval Retrieval +1

Learning to Point and Count

no code implementations8 Dec 2015 Jie Shao, Dequan Wang, xiangyang xue, Zheng Zhang

This paper proposes the problem of point-and-count as a test case to break the what-and-where deadlock.

General Classification

Multiple Granularity Descriptors for Fine-Grained Categorization

no code implementations ICCV 2015 Dequan Wang, Zhiqiang Shen, Jie Shao, Wei zhang, xiangyang xue, Zheng Zhang

Fine-grained categorization, which aims to distinguish subordinate-level categories such as bird species or dog breeds, is an extremely challenging task.

Modeling Based on Elman Wavelet Neural Network for Class-D Power Amplifiers

no code implementations12 Sep 2013 Li Wang, Jie Shao, Yaqin Zhong, Weisong Zhao, Reza Malekian

In Class-D Power Amplifiers (CDPAs), the power supply noise can intermodulate with the input signal, manifesting into power-supply induced intermodulation distortion (PS-IMD) and due to the memory effects of the system, there exist asymmetries in the PS-IMDs.

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