Institute of Computing Technology, Chinese Academy of Sciences

∙ BEIJING , China ∙ 0 followers

Graph Wavelet Neural Network

We present graph wavelet neural network (GWNN), a novel graph convolutio...
04/12/2019 ∙ by Bingbing Xu, et al. ∙ 64 ∙ share

read it
Self-supervised Equivariant Attention Mechanism for Weakly Supervised Semantic Segmentation

Image-level weakly supervised semantic segmentation is a challenging pro...
04/09/2020 ∙ by Yude Wang, et al. ∙ 52 ∙ share

read it
Learning a Self-inverse Network for Unpaired Bidirectional Image-to-image Translation

Recently image-to-image translation has attracted significant interests ...
09/09/2019 ∙ by Zengming Shen, et al. ∙ 33 ∙ share

read it
Pixel-Semantic Revise of Position Learning A One-Stage Object Detector with A Shared Encoder-Decoder

We analyze that different methods based channel or position attention me...
01/04/2020 ∙ by Qian Li, et al. ∙ 23 ∙ share

read it
Style Separation and Synthesis via Generative Adversarial Networks

Style synthesis attracts great interests recently, while few works focus...
11/07/2018 ∙ by Rui Zhang, et al. ∙ 18 ∙ share

read it
Easy Transfer Learning By Exploiting Intra-domain Structures

Transfer learning aims at transferring knowledge from a well-labeled dom...
04/02/2019 ∙ by Jindong Wang, et al. ∙ 18 ∙ share

read it
Towards Learning a Self-inverse Network for Bidirectional Image-to-image Translation

The one-to-one mapping is necessary for many bidirectional image-to-imag...
09/09/2019 ∙ by Zengming Shen, et al. ∙ 18 ∙ share

read it
F3Net: Fusion, Feedback and Focus for Salient Object Detection

Most of existing salient object detection models have achieved great pro...
11/26/2019 ∙ by Jun Wei, et al. ∙ 17 ∙ share

read it
UniViLM: A Unified Video and Language Pre-Training Model for Multimodal Understanding and Generation

We propose UniViLM: a Unified Video and Language pre-training Model for ...
02/15/2020 ∙ by Huaishao Luo, et al. ∙ 16 ∙ share

read it
Self-supervised Scale Equivariant Network for Weakly Supervised Semantic Segmentation

Weakly supervised semantic segmentation has attracted much research inte...
09/09/2019 ∙ by Yude Wang, et al. ∙ 13 ∙ share

read it
Tattoo Image Search at Scale: Joint Detection and Compact Representation Learning

The explosive growth of digital images in video surveillance and social ...
11/01/2018 ∙ by Hu Han, et al. ∙ 10 ∙ share

read it
Knowledge-guided Pairwise Reconstruction Network for Weakly Supervised Referring Expression Grounding

Weakly supervised referring expression grounding (REG) aims at localizin...
09/05/2019 ∙ by Xuejing Liu, et al. ∙ 10 ∙ share

read it
Learning from Suspected Target: Bootstrapping Performance for Breast Cancer Detection in Mammography

Deep learning object detection algorithm has been widely used in medical...
03/01/2020 ∙ by Li Xiao, et al. ∙ 10 ∙ share

read it
Learning Effective RGB-D Representations for Scene Recognition

Deep convolutional networks (CNN) can achieve impressive results on RGB ...
09/17/2018 ∙ by Xinhang Song, et al. ∙ 8 ∙ share

read it
Radiative Transport Based Flame Volume Reconstruction from Videos

We introduce a novel approach for flame volume reconstruction from video...
09/17/2018 ∙ by Liang Shen, et al. ∙ 8 ∙ share

read it
CGNet: A Light-weight Context Guided Network for Semantic Segmentation

The demand of applying semantic segmentation model on mobile devices has...
11/20/2018 ∙ by Tianyi Wu, et al. ∙ 8 ∙ share

read it
PBRnet: Pyramidal Bounding Box Refinement to Improve Object Localization Accuracy

Many recently developed object detectors focused on coarse-to-fine frame...
03/10/2020 ∙ by Li Xiao, et al. ∙ 8 ∙ share

read it
Temporal Knowledge Propagation for Image-to-Video Person Re-identification

In many scenarios of Person Re-identification (Re-ID), the gallery set c...
08/11/2019 ∙ by Xinqian Gu, et al. ∙ 7 ∙ share

read it
Transfer Learning with Dynamic Distribution Adaptation

Transfer learning aims to learn robust classifiers for the target domain...
09/17/2019 ∙ by Jindong Wang, et al. ∙ 7 ∙ share

read it
Visual Domain Adaptation with Manifold Embedded Distribution Alignment

Visual domain adaptation aims to learn robust classifiers for the target...
07/19/2018 ∙ by Jindong Wang, et al. ∙ 6 ∙ share

read it
Dense Scale Network for Crowd Counting

Crowd counting has been widely studied by computer vision community in r...
06/24/2019 ∙ by Feng Dai, et al. ∙ 6 ∙ share

read it
Mesh Variational Autoencoders with Edge Contraction Pooling

3D shape analysis is an important research topic in computer vision and ...
08/07/2019 ∙ by Yu-Jie Yuan, et al. ∙ 6 ∙ share

read it
Utilizing the Instability in Weakly Supervised Object Detection

Weakly supervised object detection (WSOD) focuses on training object det...
06/14/2019 ∙ by Yan Gao, et al. ∙ 5 ∙ share

read it
Interaction-and-Aggregation Network for Person Re-identification

Person re-identification (reID) benefits greatly from deep convolutional...
07/19/2019 ∙ by Ruibing Hou, et al. ∙ 5 ∙ share

read it
SiamRPN++: Evolution of Siamese Visual Tracking with Very Deep Networks

Siamese network based trackers formulate tracking as convolutional featu...
12/31/2018 ∙ by Bo Li, et al. ∙ 4 ∙ share

read it
Harmonic Unpaired Image-to-image Translation

The recent direction of unpaired image-to-image translation is on one ha...
02/26/2019 ∙ by Rui Zhang, et al. ∙ 4 ∙ share

read it
Consensus Feature Network for Scene Parsing

Scene parsing is challenging as it aims to assign one of the semantic ca...
07/29/2019 ∙ by Tianyi Wu, et al. ∙ 4 ∙ share

read it
From Two Graphs to N Questions: A VQA Dataset for Compositional Reasoning on Vision and Commonsense

Visual Question Answering (VQA) is a challenging task for evaluating the...
08/08/2019 ∙ by Difei Gao, et al. ∙ 4 ∙ share

read it
VRSTC: Occlusion-Free Video Person Re-Identification

Video person re-identification (re-ID) plays an important role in survei...
07/19/2019 ∙ by Ruibing Hou, et al. ∙ 3 ∙ share

read it
LoadCNN: A Efficient Green Deep Learning Model for Day-ahead Individual Resident Load Forecasting

Accurate day-ahead individual resident load forecasting is very importan...
08/01/2019 ∙ by Yunyou Huang, et al. ∙ 3 ∙ share

read it
Cross-domain Face Presentation Attack Detection via Multi-domain Disentangled Representation Learning

Face presentation attack detection (PAD) has been an urgent problem to b...
04/04/2020 ∙ by Guoqing Wang, et al. ∙ 3 ∙ share

read it
Shift-Net: Image Inpainting via Deep Feature Rearrangement

Deep convolutional networks (CNNs) have exhibited their potential in ima...
01/29/2018 ∙ by Zhaoyi Yan, et al. ∙ 2 ∙ share

read it
Tree-structured Kronecker Convolutional Networks for Semantic Segmentation

Most existing semantic segmentation methods employ atrous convolution to...
12/12/2018 ∙ by Tianyi Wu, et al. ∙ 2 ∙ share

read it
Deep Line Art Video Colorization with a Few References

Coloring line art images based on the colors of reference images is an i...
03/24/2020 ∙ by Min Shi, et al. ∙ 2 ∙ share

read it
PosNeg-Balanced Anchors with Aligned Features for Single-Shot Object Detection

We introduce a novel single-shot object detector to ease the imbalance o...
08/09/2019 ∙ by Qiankun Tang, et al. ∙ 1 ∙ share

read it
Realtime Simulation of Thin-Shell Deformable Materials using CNN-Based Mesh Embedding

We address the problem of accelerating thin-shell deformable object simu...
09/26/2019 ∙ by Qingyang Tan, et al. ∙ 1 ∙ share

read it
DWM: A Decomposable Winograd Method for Convolution Acceleration

Winograd's minimal filtering algorithm has been widely used in Convoluti...
02/03/2020 ∙ by Di Huang, et al. ∙ 1 ∙ share

read it
BestConfig: Tapping the Performance Potential of Systems via Automatic Configuration Tuning

An ever increasing number of configuration parameters are provided to sy...
10/10/2017 ∙ by Yuqing Zhu, et al. ∙ 0 ∙ share

read it
Sequential Prediction of Social Media Popularity with Deep Temporal Context Networks

Prediction of popularity has profound impact for social media, since it ...
12/12/2017 ∙ by Bo Wu, et al. ∙ 0 ∙ share

read it
Locally Smoothed Neural Networks

Convolutional Neural Networks (CNN) and the locally connected layer are ...
11/22/2017 ∙ by Liang Pang, et al. ∙ 0 ∙ share

read it
Deep Learning for Sensor-based Activity Recognition: A Survey

Sensor-based activity recognition seeks the profound high-level knowledg...
07/12/2017 ∙ by Jindong Wang, et al. ∙ 0 ∙ share

read it
A Causal And-Or Graph Model for Visibility Fluent Reasoning in Human-Object Interactions

Tracking humans that are interacting with the other subjects or environm...
09/16/2017 ∙ by Lei Qin, et al. ∙ 0 ∙ share

read it
Weighted parallel SGD for distributed unbalanced-workload training system

Stochastic gradient descent (SGD) is a popular stochastic optimization m...
08/16/2017 ∙ by Cheng Daning, et al. ∙ 0 ∙ share

read it
Fast and Efficient Calculations of Structural Invariants of Chirality

Chirality plays an important role in physics, chemistry, biology, and ot...
10/20/2017 ∙ by He Zhang, et al. ∙ 0 ∙ share

read it
Match-SRNN: Modeling the Recursive Matching Structure with Spatial RNN

Semantic matching, which aims to determine the matching degree between t...
04/15/2016 ∙ by Shengxian Wan, et al. ∙ 0 ∙ share

read it
GLAD: Global-Local-Alignment Descriptor for Pedestrian Retrieval

The huge variance of human pose and the misalignment of detected human i...
09/13/2017 ∙ by Longhui Wei, et al. ∙ 0 ∙ share

read it
Hyperspectral Light Field Stereo Matching

In this paper, we describe how scene depth can be extracted using a hype...
09/04/2017 ∙ by Kang Zhu, et al. ∙ 0 ∙ share

read it
Tree-Structured Neural Machine for Linguistics-Aware Sentence Generation

Different from other sequential data, sentences in natural language are ...
04/30/2017 ∙ by Ganbin Zhou, et al. ∙ 0 ∙ share

read it
A Deep Architecture for Semantic Matching with Multiple Positional Sentence Representations

Matching natural language sentences is central for many applications suc...
11/26/2015 ∙ by Shengxian Wan, et al. ∙ 0 ∙ share

read it
Deep Trans-layer Unsupervised Networks for Representation Learning

Learning features from massive unlabelled data is a vast prevalent topic...
09/27/2015 ∙ by Wentao Zhu, et al. ∙ 0 ∙ share

read it

Institute of Computing Technology, Chinese Academy of Sciences

Featured Researchers