Institute of Software, Chinese Academy of Sciences

The Institute of Software, Chinese Academy of Sciences (ISCAS) is a leading research institute in China, which focuses on the fundamental theories of computer science as well as software technologies and their applications. As a part of the Chinese Academy of Sciences (CAS), ISCAS is a government-sponsored institution. Through our research results and innovations, we hope to establish an international reputation in academia and to assist in the development and growth of Chinas software industry.

Towards Interpretable and Robust Hand Detection via Pixel-wise Prediction

The lack of interpretability of existing CNN-based hand detection method...
01/13/2020 ∙ by Dan Liu, et al. ∙ 13 ∙ share

read it
Occluded Prohibited Items Detection: An X-ray Security Inspection Benchmark and De-occlusion Attention Module

Object detection has taken advantage of the advances in deep convolution...
04/18/2020 ∙ by Yanlu Wei, et al. ∙ 8 ∙ share

read it
CASS: Towards Building a Social-Support Chatbot for Online Health Community

Chatbots systems, despite their popularity in today's HCI and CSCW resea...
01/04/2021 ∙ by Liuping Wang, et al. ∙ 7 ∙ share

read it
Learning Semantic Neural Tree for Human Parsing

The majority of existing human parsing methods formulate the task as sem...
12/20/2019 ∙ by Ruyi Ji, et al. ∙ 6 ∙ share

read it
Sharing deep generative representation for perceived image reconstruction from human brain activity

Decoding human brain activities via functional magnetic resonance imagin...
04/25/2017 ∙ by Changde Du, et al. ∙ 0 ∙ share

read it
Joint Hand Detection and Rotation Estimation by Using CNN

Hand detection is essential for many hand related tasks, e.g. parsing ha...
12/08/2016 ∙ by Xiaoming Deng, et al. ∙ 0 ∙ share

read it
GPU-FV: Realtime Fisher Vector and Its Applications in Video Monitoring

Fisher vector has been widely used in many multimedia retrieval and visu...
04/12/2016 ∙ by Wenying Ma, et al. ∙ 0 ∙ share

read it
Joint RNN Model for Argument Component Boundary Detection

Argument Component Boundary Detection (ACBD) is an important sub-task in...
05/05/2017 ∙ by Minglan Li, et al. ∙ 0 ∙ share

read it
Crowdsourcing Argumentation Structures in Chinese Hotel Reviews

Argumentation mining aims at automatically extracting the premises-claim...
05/05/2017 ∙ by Mengxue Li, et al. ∙ 0 ∙ share

read it
Reinforcement Learning Based Argument Component Detection

Argument component detection (ACD) is an important sub-task in argumenta...
02/21/2017 ∙ by Yang Gao, et al. ∙ 0 ∙ share

read it
Parallel energy-stable phase field crystal simulations based on domain decomposition methods

In this paper, we present a parallel numerical algorithm for solving the...
03/03/2017 ∙ by Ying Wei, et al. ∙ 0 ∙ share

read it
Cutting Away the Confusion From Crowdtesting

Crowdtesting is effective especially when it comes to the feedback on GU...
05/07/2018 ∙ by Junjie Wang, et al. ∙ 0 ∙ share

read it
Effective Automated Decision Support for Managing Crowdtesting

Crowdtesting has grown to be an effective alter-native to traditional te...
05/07/2018 ∙ by Junjie Wang, et al. ∙ 0 ∙ share

read it
Crowdtesting : When is The Party Over?

Trade-offs such as "how much testing is enough" are critical yet challen...
05/08/2018 ∙ by Junjie Wang, et al. ∙ 0 ∙ share

read it
Sequence-to-Action: End-to-End Semantic Graph Generation for Semantic Parsing

This paper proposes a neural semantic parsing approach -- Sequence-to-Ac...
09/04/2018 ∙ by Bo Chen, et al. ∙ 0 ∙ share

read it
NPRF: A Neural Pseudo Relevance Feedback Framework for Ad-hoc Information Retrieval

Pseudo-relevance feedback (PRF) is commonly used to boost the performanc...
10/30/2018 ∙ by Canjia Li, et al. ∙ 0 ∙ share

read it
Sentence Rewriting for Semantic Parsing

A major challenge of semantic parsing is the vocabulary mismatch problem...
01/10/2019 ∙ by Bo Chen, et al. ∙ 0 ∙ share

read it
Optimizing seed inputs in fuzzing with machine learning

The success of a fuzzing campaign is heavily depending on the quality of...
02/07/2019 ∙ by Liang Cheng, et al. ∙ 0 ∙ share

read it
Speeding up Deep Learning with Transient Servers

Distributed training frameworks, like TensorFlow, have been proposed as ...
02/28/2019 ∙ by Shijian Li, et al. ∙ 0 ∙ share

read it
A Research and Strategy of Remote Sensing Image Denoising Algorithms

Most raw data download from satellites are useless, resulting in transmi...
05/24/2019 ∙ by Ling Li, et al. ∙ 0 ∙ share

read it
A Comparison and Strategy of Semantic Segmentation on Remote Sensing Images

In recent years, with the development of aerospace technology, we use mo...
05/24/2019 ∙ by Junxing Hu, et al. ∙ 0 ∙ share

read it
Progressive Self-Supervised Attention Learning for Aspect-Level Sentiment Analysis

In aspect-level sentiment classification (ASC), it is prevalent to equip...
06/04/2019 ∙ by Jialong Tang, et al. ∙ 0 ∙ share

read it
Sequence-to-Nuggets: Nested Entity Mention Detection via Anchor-Region Networks

Sequential labeling-based NER approaches restrict each word belonging to...
06/10/2019 ∙ by Hongyu Lin, et al. ∙ 0 ∙ share

read it
Scale Invariant Fully Convolutional Network: Detecting Hands Efficiently

Existing hand detection methods usually follow the pipeline of multiple ...
06/11/2019 ∙ by Dan Liu, et al. ∙ 0 ∙ share

read it
Cost-sensitive Regularization for Label Confusion-aware Event Detection

In supervised event detection, most of the mislabeling occurs between a ...
06/14/2019 ∙ by Hongyu Lin, et al. ∙ 0 ∙ share

read it
A Comprehensive Formal Security Analysis and Revision of the Two-phase Key Exchange Primitive of TPM 2.0

The Trusted Platform Module (TPM) version 2.0, which has been demonstrat...
06/16/2019 ∙ by Qianying Zhang, et al. ∙ 0 ∙ share

read it
Feedback-based, Automated Failure Testing of Microservice-based Applications

Modern distributed applications are moving toward a microservice archite...
08/18/2019 ∙ by Chengxu Cui, et al. ∙ 0 ∙ share

read it
Puncturable Signatures and Applications in Proof-of-Stake Blockchain Protocol

Proof-of-stake (PoS) blockchain protocols are emerging as one of the mos...
09/09/2019 ∙ by Xinyu Li, et al. ∙ 0 ∙ share

read it
SiamMan: Siamese Motion-aware Network for Visual Tracking

In this paper, we present a novel siamese motion-aware network (SiamMan)...
12/11/2019 ∙ by Wenzhang Zhou, et al. ∙ 0 ∙ share

read it
A Variational Staggered Particle Framework for Incompressible Free-Surface Flows

Smoothed particle hydrodynamics (SPH) has been extensively studied in co...
01/26/2020 ∙ by Xiaowei He, et al. ∙ 0 ∙ share

read it
PEL-BERT: A Joint Model for Protocol Entity Linking

Pre-trained models such as BERT are widely used in NLP tasks and are fin...
01/28/2020 ∙ by Shoubin Li, et al. ∙ 0 ∙ share

read it
Rethinking Object Detection in Retail Stores

The convention standard for object detection uses a bounding box to repr...
03/18/2020 ∙ by Yuanqiang Cai, et al. ∙ 0 ∙ share

read it
Efficient Alternating Least Squares Algorithms for Truncated HOSVD of Higher-Order Tensors

The truncated Tucker decomposition, also known as the truncated higher-o...
04/06/2020 ∙ by Chuanfu Xiao, et al. ∙ 0 ∙ share

read it
PFNN: A Penalty-Free Neural Network Method for Solving a Class of Second-Order Boundary-Value Problems on Complex Geometries

We present PFNN, a penalty-free neural network method, to efficiently so...
04/14/2020 ∙ by Hailong Sheng, et al. ∙ 0 ∙ share

read it
A Rigourous Study on Named Entity Recognition: Can Fine-tuning Pretrained Model Lead to the Promised Land?

Fine-tuning pretrained model has achieved promising performance on stand...
04/25/2020 ∙ by Hongyu Lin, et al. ∙ 0 ∙ share

read it
Adaptive SpMV/SpMSpV on GPUs for Input Vectors of Varied Sparsity

Despite numerous efforts for optimizing the performance of Sparse Matrix...
06/30/2020 ∙ by Min Li, et al. ∙ 0 ∙ share

read it
Parallel energy-stable solver for a coupled Allen-Cahn and Cahn-Hilliard system

In this paper, we study numerical methods for solving the coupled Allen-...
07/09/2020 ∙ by Jizu Huang, et al. ∙ 0 ∙ share

read it
Fuzzing Based on Function Importance by Attributed Call Graph

Fuzzing has become one of the important methods for vulnerability detect...
10/07/2020 ∙ by Wenshuo Wang, et al. ∙ 0 ∙ share

read it
Benchmarking Knowledge-Enhanced Commonsense Question Answering via Knowledge-to-Text Transformation

A fundamental ability of humans is to utilize commonsense knowledge in l...
01/04/2021 ∙ by Ning Bian, et al. ∙ 0 ∙ share

read it
"Brilliant AI Doctor" in Rural China: Tensions and Challenges in AI-Powered CDSS Deployment

Artificial intelligence (AI) technology has been increasingly used in th...
01/04/2021 ∙ by Dakuo Wang, et al. ∙ 0 ∙ share

read it

Institute of Software, Chinese Academy of Sciences

Featured Researchers