Chih-Yao Ma
Chih-Yao Ma
Research Scientist @ Facebook
Geverifieerd e-mailadres voor fb.com - Homepage
Titel
Geciteerd door
Geciteerd door
Jaar
TS-LSTM and temporal-inception: Exploiting spatiotemporal dynamics for activity recognition
CY Ma*, MH Chen*, Z Kira, G AlRegib (*equal contribution)
Signal Processing: Image Communication, 2017
1612017
Self-Monitoring Navigation Agent via Auxiliary Progress Estimation
CY Ma, J Lu, Z Wu, G AlRegib, Z Kira, R Socher, C Xiong
International Conference on Learning Representations (ICLR), 2019
1072019
Attend and Interact: Higher-Order Object Interactions for Video Understanding
CY Ma, A Kadav, I Melvin, Z Kira, G AlRegib, HP Graf
IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2018
1022018
The Regretful Agent: Heuristic-Aided Navigation through Progress Estimation
CY Ma, Z Wu, G AlRegib, C Xiong, Z Kira
IEEE Conference on Computer Vision and Pattern Recognition (CVPR) (Oral), 2019
822019
AdaFrame: Adaptive Frame Selection for Fast Video Recognition
Z Wu, C Xiong, CY Ma, R Socher, LS Davis
IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2019
642019
Learning-based saliency model with depth information
CY Ma, HM Hang
Journal of vision 15 (6), 19-19, 2015
272015
10.2: Crosstalk Suppression by Image Processing in 3D Display
YC Chang, CY Ma, YP Huang
SID Symposium Digest of Technical Papers 41 (1), 124-127, 2010
232010
Frustratingly Simple Domain Generalization via Image Stylization
N Somavarapu, CY Ma, Z Kira
arXiv preprint arXiv:2006.11207, 2020
142020
FeatMatch: Feature-Based Augmentation for Semi-Supervised Learning
CW Kuo, CY Ma, JB Huang, Z Kira
European Conference on Computer Vision (ECCV), 2020
112020
Unbiased Teacher for Semi-Supervised Object Detection
YC Liu, CY Ma, Z He, CW Kuo, K Chen, P Zhang, B Wu, Z Kira, P Vajda
International Conference on Learning Representations (ICLR), 2021
102021
Who2com: Collaborative Perception Via Learnable Handshake Communication
YC Liu, J Tian, CY Ma, N Glaser, CW Kuo, Z Kira
IEEE International Conference on Robotics and Automation (ICRA), 2020
82020
Learning to Generate Grounded Visual Captions without Localization Supervision
CY Ma, Y Kalantidis, G AlRegib, P Vajda, M Rohrbach, Z Kira
European Conference on Computer Vision (ECCV), 2020
72020
Multi-zone digital crosstalk reduction by image processing in 3D display
CY Ma, YC Chang, YP Huang
Journal of Display Technology 10 (6), 488-493, 2014
52014
55.2: A Simulation Platform and Crosstalk Analysis for Patterned Retarder 3D Display
CY Ma, YC Chang, YP Huang, CH Tsao
SID Symposium Digest of Technical Papers 42 (1), 808-811, 2011
52011
Grounded Objects and Interactions for Video Captioning
CY Ma, A Kadav, I Melvin, Z Kira, G AlRegib, HP Graf
Neural Information Processing Systems (NeurIPS) Workshop on Visually …, 2017
42017
Hierarchical Cross-Modal Agent for Robotics Vision-and-Language Navigation
MZ Irshad, CY Ma, Z Kira
International Conference on Robotics and Automation (ICRA), 2021
22021
Manifold Graph with Learned Prototypes for Semi-Supervised Image Classification
CW Kuo, CY Ma, JB Huang, Z Kira
arXiv preprint arXiv:1906.05202, 2019
22019
Self-aware visual-textual co-grounded navigation agent
CY Ma, C Xiong
US Patent 11,029,694, 2021
12021
Spatio-temporal interaction network for learning object interactions
A Kadav, CY Ma, I Melvin, HP Graf
US Patent 10,503,978, 2019
2019
3D display panel and pixel brightness control method thereof
CY Ma, YC Chang, YP Huang, CH Tsao, CY Chen
US Patent 8,872,866, 2014
2014
Het systeem kan de bewerking nu niet uitvoeren. Probeer het later opnieuw.
Artikelen 1–20