DL-O.3: Deep Learning for Intelligent Multimedia Analytics & Security III |
| Symposium: Symposium on Deep Learning for Intelligent Multimedia Analytics & Security |
| Session Type: Oral |
| Time: Wednesday, November 15, 16:00 - 17:30 |
| Location: Verdun |
| Session Chair: Zhenyu Guo, Postmates |
| 16:00 - 16:18 |
| DL-O.3.1: A NEW DATASET FOR HAND GESTURE ESTIMATION |
| Biyao Shao; Hangzhou Dianzi University |
| Yifeng Xie; Hangzhou Dianzi University |
| Hongnan Yang; Hangzhou Dianzi University |
| Yatong Jiang; Hangzhou Dianzi University |
| Chenggang Yan; Hangzhou Dianzi University |
| Hongtao Xie; Institute of Information Engineering, Chinese Academy of Sciences |
| Yangang Wang; Southeast University |
| 16:18 - 16:36 |
| DL-O.3.2: SINGLE IMAGE DENSITY MAP ESTIMATION BASED ON MULTI-COLUMN CNN AND BOOSTING |
| Xiaoyu Liu; Simon Fraser University |
| Denning Campbell; Sengled Canada |
| Zhenyu Guo; Sengled Canada |
| 16:36 - 16:54 |
| DL-O.3.3: BIMODAL CODEBOOKS BASED ADULT VIDEO DETECTION |
| Yizhi Liu; School of Computer Science and Engineering, Hunan University of Science and Technology |
| Junlin Ouyang; School of Computer Science and Engineering, Hunan University of Science and Technology |
| Jianxun Liu; School of Computer Science and Engineering, Hunan University of Science and Technology |
| 16:54 - 17:12 |
| DL-O.3.4: A CNN BASED FRAMEWORK FOR STABLE IMAGE FEATURE SELECTION |
| Chaoyi Han; Tsinghua University |
| Xiaoming Tao; Tsinghua University |
| Yiping Duan; Tsinghua University |
| Xijia Liu; Tsinghua University |
| Jianhua Lu; Tsinghua University |
| 17:12 - 17:30 |
| DL-O.3.5: END-TO-END CHINESE TEXT RECOGNITION |
| Jie Hu; Tsinghua University |
| Tszhang Guo; Tsinghua University |
| Ji Cao; Beijing SinoVoice Technology Co.,Ltd. |
| Changshui Zhang; Tsinghua University |