Junnan Li
Junnan Li
Salesforce Research Asia
Verified email at salesforce.com - Homepage
Title
Cited by
Cited by
Year
Dividemix: Learning with noisy labels as semi-supervised learning
J Li, R Socher, SCH Hoi
arXiv preprint arXiv:2002.07394, 2020
1582020
Learning to Learn from Noisy Labeled Data
J Li, Y Wong, Q Zhao, MS Kankanhalli
The IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2019
1482019
Prototypical contrastive learning of unsupervised representations
J Li, P Zhou, C Xiong, SCH Hoi
arXiv preprint arXiv:2005.04966, 2020
1432020
Learning to detect human-object interactions with knowledge
B Xu, Y Wong, J Li, Q Zhao, MS Kankanhalli
Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern …, 2019
692019
Facial expression recognition using deep neural networks
J Li, EY Lam
2015 IEEE International Conference on Imaging Systems and Techniques (IST), 1-6, 2015
572015
Unsupervised Learning of View-invariant Action Representations
J Li, Y Wong, Q Zhao, M Kankanhalli
Conference on Neural Information Processing Systems (NeurIPS), 2018
562018
Interact as you intend: Intention-driven human-object interaction detection
B Xu, J Li, Y Wong, Q Zhao, MS Kankanhalli
IEEE Transactions on Multimedia 22 (6), 1423-1432, 2019
472019
Dual-Glance Model for Deciphering Social Relationships
J Li, Y Wong, Q Zhao, MS Kankanhalli
The IEEE International Conference on Computer Vision (ICCV), 2650-2659, 2017
422017
Attention transfer from web images for video recognition
J Li, Y Wong, Q Zhao, MS Kankanhalli
Proceedings of the 25th ACM international conference on multimedia, 1-9, 2017
352017
Hierarchical & multimodal video captioning: Discovering and transferring multimodal knowledge for vision to language
AA Liu, N Xu, Y Wong, J Li, YT Su, M Kankanhalli
Computer Vision and Image Understanding 163, 113-125, 2017
292017
The devil is in classification: A simple framework for long-tail instance segmentation
T Wang, Y Li, B Kang, J Li, J Liew, S Tang, S Hoi, J Feng
European Conference on computer vision, 728-744, 2020
242020
Mopro: Webly supervised learning with momentum prototypes
J Li, C Xiong, SCH Hoi
arXiv preprint arXiv:2009.07995, 2020
162020
Multi-stream deep learning framework for automated presentation assessment
J Li, Y Wong, MS Kankanhalli
2016 IEEE International Symposium on Multimedia (ISM), 222-225, 2016
142016
Deep reinforcement learning in soft viscoelastic actuator of dielectric elastomer
L Li, J Li, L Qin, J Cao, MS Kankanhalli, J Zhu
IEEE Robotics and Automation Letters 4 (2), 2094-2100, 2019
132019
LSTM-based multi-label video event detection
AA Liu, Z Shao, Y Wong, J Li, YT Su, M Kankanhalli
Multimedia Tools and Applications 78 (1), 677-695, 2019
122019
Improving out-of-distribution generalization via multi-task self-supervised pretraining
I Albuquerque, N Naik, J Li, N Keskar, R Socher
arXiv preprint arXiv:2003.13525, 2020
82020
A multi-sensor framework for personal presentation analytics
T Gan, J Li, Y Wong, MS Kankanhalli
ACM Transactions on Multimedia Computing, Communications, and Applications …, 2019
82019
Weakly-Supervised Multi-Person Action Recognition in 360 Videos
J Li, J Liu, W Yongkang, S Nishimura, M Kankanhalli
Proceedings of the IEEE/CVF Winter Conference on Applications of Computer …, 2020
72020
Comatch: Semi-supervised learning with contrastive graph regularization
J Li, C Xiong, SCH Hoi
Proceedings of the IEEE/CVF International Conference on Computer Vision …, 2021
62021
Video storytelling: Textual summaries for events
J Li, Y Wong, Q Zhao, MS Kankanhalli
IEEE Transactions on Multimedia 22 (2), 554-565, 2019
52019
The system can't perform the operation now. Try again later.
Articles 1–20