no code implementations • ECCV 2020 • Tong Wang, Yousong Zhu, Chaoyang Zhao, Wei Zeng, Yao-Wei Wang, Jinqiao Wang, Ming Tang
Most of existing object detectors usually adopt a small training batch size ( ~16), which severely hinders the whole community from exploring large-scale datasets due to the extremely long training procedure.
no code implementations • ECCV 2020 • Jibin Gao, Wei-Shi Zheng, Jia-Hui Pan, Chengying Gao, Yao-Wei Wang, Wei Zeng, Jian-Huang Lai
However, existing methods for action assessment are mostly limited to individual actions, especially lacking modeling of the asymmetric relations among agents (e. g., between persons and objects); and this limitation undermines their ability to assess actions containing asymmetrically interactive motion patterns, since there always exists subordination between agents in many interactive actions.
2 code implementations • 13 Aug 2020 • Ling-An Zeng, Fa-Ting Hong, Wei-Shi Zheng, Qi-Zhi Yu, Wei Zeng, Yao-Wei Wang, Jian-Huang Lai
However, most existing works focus only on video dynamic information (i. e., motion information) but ignore the specific postures that an athlete is performing in a video, which is important for action assessment in long videos.
Ranked #2 on Action Quality Assessment on Rhythmic Gymnastic
no code implementations • 12 May 2020 • Yixiong Zou, Shanghang Zhang, Ke Chen, Yonghong Tian, Yao-Wei Wang, José M. F. Moura
Inspired by such capability of humans, to imitate humans' ability of learning visual primitives and composing primitives to recognize novel classes, we propose an approach to FSL to learn a feature representation composed of important primitives, which is jointly trained with two parts, i. e. primitive discovery and primitive enhancing.
no code implementations • ICCV 2019 • Limeng Qiao, Yemin Shi, Jia Li, Yao-Wei Wang, Tiejun Huang, Yonghong Tian
By solving the problem with its closed-form solution on the fly with the setup of transduction, our approach efficiently tailors an episodic-wise metric for each task to adapt all features from a shared task-agnostic embedding space into a more discriminative task-specific metric space.
no code implementations • 6 May 2019 • Yu Shu, Yemin Shi, Yao-Wei Wang, Tiejun Huang, Yonghong Tian
Predictors for new categories are added to the classification layer to "open" the deep neural networks to incorporate new categories dynamically.
no code implementations • 23 Jan 2019 • Yu Shu, Yemin Shi, Yao-Wei Wang, Yixiong Zou, Qingsheng Yuan, Yonghong Tian
Most of the existing action recognition works hold the \textit{closed-set} assumption that all action categories are known beforehand while deep networks can be well trained for these categories.
no code implementations • ICCV 2017 • Ke Yan, Yonghong Tian, Yao-Wei Wang, Wei Zeng, Tiejun Huang
In this paper, we model the relationship of vehicle images as multiple grains.
no code implementations • ACL 2017 • Xueying Zhan, Yao-Wei Wang, Yanghui Rao, Haoran Xie, Qing Li, Fu Lee Wang, Tak-Lam Wong
This paper focuses on the task of noisy label aggregation in social media, where users with different social or culture backgrounds may annotate invalid or malicious tags for documents.
Cultural Vocal Bursts Intensity Prediction Image Classification +2
1 code implementation • ICCV 2017 • Yemin Shi, Yonghong Tian, Yao-Wei Wang, Tiejun Huang
Despite a lot of research efforts devoted in recent years, how to efficiently learn long-term dependencies from sequences still remains a pretty challenging task.
1 code implementation • 16 Nov 2016 • Mengyue Geng, Yao-Wei Wang, Tao Xiang, Yonghong Tian
Second, a two-stepped fine-tuning strategy is developed to transfer knowledge from auxiliary datasets.
no code implementations • 16 Nov 2016 • Yemin Shi, Yonghong Tian, Yao-Wei Wang, Tiejun Huang
We also introduce an attention mechanism on the temporal domain to capture the long-term dependence meanwhile finding the salient portions.
no code implementations • 10 Sep 2016 • Yemin Shi, Yonghong Tian, Yao-Wei Wang, Tiejun Huang
Nevertheless, most of the existing features or descriptors cannot capture motion information effectively, especially for long-term motion.
no code implementations • CVPR 2016 • Peixi Peng, Tao Xiang, Yao-Wei Wang, Massimiliano Pontil, Shaogang Gong, Tiejun Huang, Yonghong Tian
Most existing person re-identification (Re-ID) approaches follow a supervised learning framework, in which a large number of labelled matching pairs are required for training.