B
Bing Han
Publications - 5
Citations - 44
Bing Han is an academic researcher. The author has contributed to research in topics: Computer science & Pattern recognition (psychology). The author has an hindex of 2, co-authored 2 publications receiving 30 citations.
Papers
More filters
Posted Content
iQIYI-VID: A Large Dataset for Multi-modal Person Identification.
Yuanliu Liu,Peipei Shi,Bo Peng,He Yan,Yong Zhou,Bing Han,Yi Zheng,Chao Lin,Jianbin Jiang,Yin Fan,Tingwei Gao,Ganwen Wang,Jian Liu,Xiangju Lu,Danming Xie +14 more
TL;DR: This paper introduces iQIYI-VID, the largest video dataset for multi-modal person identification, and proposed a Multi- modal Attention module to fuse multi-Modal features that can improve person identification considerably.
Proceedings ArticleDOI
iQIYI Celebrity Video Identification Challenge
Yuanliu Liu,Peipei Shi,Bo Peng,He Yan,Yong Zhou,Bing Han,Yi Zheng,Chao Lin,Jianbin Jiang,Yin Fan,Tingwei Gao,Ganwen Wang,Jian Liu,Xiangju Lu,Junhui Liu,Danming Xie +15 more
TL;DR: This paper introduces the organization of the challenge, the dataset, the evaluation process, and the results, and releases the iQIYI-VID-2019 dataset, which contains 200K videos of celebrities.
Journal ArticleDOI
Signal Modulation Recognition Algorithm Based on Improved Spatiotemporal Multi-Channel Network
TL;DR: Wang et al. as mentioned in this paper proposed an improved spatiotemporal multi-channel network (IQ-related features Multi-channel Convolutional Bi-LSTM with Gaussian noise, IQGMCL).
Journal ArticleDOI
Multi-Object Multi-Camera Tracking Based on Deep Learning for Intelligent Transportation: A Review
TL;DR: In this article , a comprehensive review of multi-object multi-camera tracking based on deep learning for intelligent transportation is provided, where the main object detectors for MOMCT are introduced in detail.
Proceedings ArticleDOI
SIGMA-DF: Single-Side Guided Meta-Learning for Deepfake Detection
TL;DR: In this paper , a single-sIde guided meta-learning framework for DeepFake detection (SIGMA-DF) is proposed, which simulates the cross-domain scenarios during training by synthesizing virtual testing domain through meta learning.