Time | Session | Name | Title |
09:01 - 09:07 |
1 |
Jingchuan XU |
Recognizing Different Sign Language with Deep Learning TAiC: Kai Kang [paper] [poster] [slides] |
09:08 - 09:14 |
1 |
Xinxin ZHANG |
Learning based image registration TAiC: Wei Yang
|
09:15 - 09:21 |
1 |
Xintao WANG |
Semantically Image Super-Resolution TAiC: Wei Yang
|
09:22 - 09:28 |
1 |
Ran WANG |
Protein-Ligand Binding Affinity Prediction Using 3D Convolutional Neural Network TAiC: Hongyang [paper] [poster] [slides] |
09:29 - 09:35 |
1 |
Wai Ho CHAK |
Learning 3D Shape Classification on Normal Featured Convnet TAiC: Tong Xiao [paper] [poster] [slides] |
09:36 - 09:42 |
1 |
Di QIU |
Deep Compression of Faster R-CNN Model TAiC: Wei Yang [paper] [poster] [slides] |
09:43 - 09:49 |
1 |
Dehua TAO |
Person Re-identification in the Video TAiC: Tong Xiao [paper] [poster] [slides] |
09:50 - 09:56 |
1 |
Yuxin SHI |
Image Style Transfer TAiC: Wei Yang [paper] [poster] [slides] |
|
|
Coffee break |
Around 9:30, Reading Room, 6F SHB |
|
|
Keynote |
10:00 - 11:00, T.Y. Wong Hall, SHB |
11:08 - 11:14 |
1 |
Lingcao HUANG |
Building Footprints Extraction from High-resolution Remote Sensing Images Based on DeepLab TAiC: Wei Yang [poster] [slides] |
11:15 - 11:21 |
1 |
Xiaowei HU |
Scale-Insensitive Network for Fast Object Detection TAiC: Xiao Chu
|
11:22 - 11:28 |
1 |
Xianzhi LI |
A Deep Learning Scheme for MI-EEG Classification
based on LSTM-RNN: A Preliminary Study TAiC: Xiao Chu
|
11:29 - 11:35 |
1 |
Liliang REN |
Recurrent Soft Attention Model for Common Object Recognition TAiC: Tong Xiao [poster] [slides] |
11:36 - 11:42 |
1 |
Kun WANG |
Object Detection with Hierarchical Fully-connected Conditional Random Fields TAiC: Kai Kang [paper] [poster] [slides] |
11:43 - 11:49 |
1 |
Shilin HE |
D-lead: Deep Log Embedding Anomaly Detection TAiC: Tong Xiao [poster] [slides] |
11:50 - 11:56 |
1 |
Danny HO |
Controlling Lunar Lander by Deep Reinforcement Learning TAiC: Hongyang [poster] [slides] |
11:57 - 12:03 |
2 |
Zhizhong LI |
Geometric View of GAN and Visualization TAiC: Xiao Chu [paper] [poster] [slides] |
12:04 - 12:10 |
2 |
Pengpeng LIU |
2D to 3D: Predicting 3D information from a single RGB image TAiC: Tong Xiao
|
12:11 - 12:17 |
2 |
Zhibo ZHU |
Research On Stacked Hourglass Structure in Human Pose estimation TAiC: Xiao Chu [paper] [poster] [slides] |
12:18 - 12:24 |
2 |
Zhou FANG |
Human Pose estimation in Video TAiC: Wei Yang [poster] [slides] |
12:25 - 12:31 |
2 |
Qinghua DING |
Understanding Human Activity via Pose Estimation TAiC: Wei Yang
|
12:32 - 12:38 |
2 |
Hao CHEN |
Deep Face Recognition TAiC: Tong Xiao
|
12:39 - 12:45 |
2 |
Yinpeng GUO |
Complex Evolutionary Neural Networks for Natural
Language Model TAiC: Xiao Chu [poster] [slides] |
12:46 - 12:52 |
2 |
Jian ZHANG |
Exploring Image Generating Effects of DCGAN and WGAN by Face Generators TAiC: Tong Xiao [poster] [slides] |
12:53 - 12:59 |
2 |
Chenye GUAN |
Automatic Video Monitoring TAiC: Hongyang [paper] [poster] [slides] |
12:60 - 13:06 |
2 |
Kai CHEN |
Discover and Learn New Objects from Documentaries TAiC: Kai Kang
|
13:07 - 13:13 |
2 |
Qingqiu HUANG |
From Trailers to Storylines: An Efficient Way to Learn from Movies TAiC: Tong Xiao [poster] [slides] |
13:14 - 13:20 |
2 |
Yikang LI |
Scene Graph Generation from Objects, Phrases and Caption Regions TAiC: Xiao Chu |
13:21 - 13:27 |
2 |
Yining LI |
Learning to Disambiguate by Asking Discriminative Questions TAiC: Tong Xiao [poster] [slides] |
13:28 - 13:34 |
2 |
Xin XU |
Image captioning and soft attention TAiC: Hongyang [paper] [poster] [slides] |
|
|
Lunch |
13:30 - 14:30 |
14:31 - 14:37 |
3 |
Xi FU |
Exploring Deep Learning on FANTOM5 Data TAiC: Hongyang [poster] [slides] |
14:38 - 14:44 |
3 |
Han WANG |
Playing TORCS with Deep Determinisitc Policy Gradient TAiC: Hongyang [paper] [poster] [slides] |
14:45 - 14:51 |
3 |
Haoyu YANG |
Fully Convolutional Neural Networks for Layout Hotspot Detection TAiC: Kai Kang [paper] [poster] [slides] |
14:52 - 14:58 |
3 |
Weiwen LIU |
A Personalized Recommender System based on Deep Learning TAiC: Kai Kang [poster] [slides] |
14:59 - 15:05 |
3 |
Yuqi LIU |
A Mobile Application for the Visually Impaired
Based on Deep Learning TAiC: Kai Kang [paper] [poster] [slides] |
15:06 - 15:12 |
3 |
Yantao SHEN |
Learning Deep Neural Networks for Vehicle Re-ID with Visual-spatio-temporal Path Proposals TAiC: N/A [paper] [poster] [slides] |
15:13 - 15:19 |
3 |
Jie CHEN |
Adversarial Learning for Super-Resolution TAiC: Tong Xiao [paper] [poster] [slides] |
15:20 - 15:26 |
3 |
Huangjing LIN |
ScanNet: A Fast and Dense Scanning Framework for Metastatic Breast Cancer Detection TAiC: Tong Xiao [poster] [slides] |
15:27 - 15:33 |
3 |
Xi WANG |
Mitosis Detection in Breast Cancer Histology Image TAiC: Tong Xiao
|
15:34 - 15:40 |
3 |
Xiaoxiao LI |
Not All Pixels Are Equal: Difficulty-Aware Semantic Segmentation via Deep Layer Cascade TAiC: N/A [paper] [poster] [slides] |
15:41 - 15:47 |
3 |
Xiangyu LIU |
Mathematical Expression Recognition by Recurrent Neural Networks TAiC: Xiao Chu [paper] [poster] [slides] |
15:48 - 15:54 |
3 |
Yi LI |
Deep Reinforcement Learning with Recurrent Convolutional Networks TAiC: Hongyang [paper] [poster] [slides] |
15:55 - 16:01 |
3 |
Yuqi FANG |
Feature Extraction and Prediction of Motion-related EEG Based on Deep Neural Network: a novel method of signal processing TAiC: Wei Yang [paper] [poster] [slides] |
16:02 - 16:08 |
3 |
Xubo LENG |
Classification of EEG During Motor Imagery Tasks Using Time-domain Generative LSTM and Topology-preserving CNN TAiC: Kai Kang [paper] [poster] [slides] |
|
|
Coffee break |
Around 16:00, Reading Room, 6F SHB |
16:23 - 16:29 |
4 |
Shuaijun LI |
Vehicle localization based on Fine-grained Vehicle Model Classification TAiC: Xiao Chu
|
16:30 - 16:36 |
4 |
Tsz Kin TSE |
Generating Motif by Recurrent Neural Network TAiC: Hongyang [poster] [slides] |
16:37 - 16:43 |
4 |
Jiarui WANG |
Deep Neural Network for Speaker Verification TAiC: Hongyang [paper] [poster] [slides] |
16:44 - 16:50 |
4 |
Wang CHEN |
Adding Secondary Information into Deep Neural Network for Knowledge Tracing TAiC: Hongyang [poster] [slides] |
16:51 - 16:57 |
4 |
Shuiyang MAO |
Sentiment Analysis with Parallel Combination of LSTM and CNN TAiC: Hongyang
|
16:58 - 17:04 |
4 |
Sijie YAN |
Unconstrained Fashion Landmark Detection TAiC: N/A [paper] [poster] [slides] |
17:05 - 17:11 |
4 |
Jinkai YU |
Quora Duplicate Question Pairs Detection TAiC: Kai Kang [paper] [poster] [slides] |
17:12 - 17:18 |
4 |
Haozhi LIN |
Duplicate questions discovery in Quora using deep neural network TAiC: Wei Yang [paper] [poster] [slides] |
17:19 - 17:25 |
4 |
Minhao LIU |
Deep Learning Applied to Surface Electromyography Data Classification TAiC: Xiao Chu [poster] [slides] |
17:26 - 17:32 |
4 |
Yuqi ZHANG |
Visual Relationship Detection TAiC: Xiao Chu [paper] [poster] [slides] |
17:33 - 17:39 |
4 |
Yue WANG |
A Study of Image Style Transfer TAiC: Wei Yang [paper] [poster] [slides] |
17:40 - 17:46 |
4 |
Yuzhong WU |
Attention Network for Acoustic Scene Classification TAiC: Xiao Chu
|
17:47 - 17:53 |
4 |
Shuai LI |
Akid: A Neural Network Library From Dataism Approach TAiC: N/A
|
17:54 - 18:00 |
4 |
Shuang LI |
Person Search with Natural Language Description TAiC: N/A [paper] [poster] [slides] |
| | | |