Abstract | ||
---|---|---|
In this paper, we propose a two-stream transformer networks (TSTN) approach for video-based face alignment. Unlike conventional image-based face alignment approaches which cannot explicitly model the temporal dependency in videos and motivated by the fact that consistent movements of facial landmarks usually occur across consecutive frames, our TSTN aims to capture the complementary information of... |
Year | DOI | Venue |
---|---|---|
2018 | 10.1109/TPAMI.2017.2734779 | IEEE Transactions on Pattern Analysis and Machine Intelligence |
Keywords | Field | DocType |
Face,Shape,Streaming media,Videos,Transforms,Machine learning,Indexes | Computer vision,Pattern recognition,Convolutional neural network,Computer science,Recurrent neural network,Transformer,Artificial intelligence,Biometrics,Landmark,Temporal consistency,Benchmarking,Facial motion capture | Journal |
Volume | Issue | ISSN |
40 | 11 | 0162-8828 |
Citations | PageRank | References |
11 | 0.53 | 4 |
Authors | ||
4 |
Name | Order | Citations | PageRank |
---|---|---|---|
Hao Liu | 1 | 113 | 10.67 |
Jiwen Lu | 2 | 3105 | 153.88 |
Jianjiang Feng | 3 | 814 | 62.59 |
Jie Zhou | 4 | 2103 | 190.17 |