no code implementations • 10 May 2024 • Wenjin Zhang, Keyi Li, Sen yang, Chenyang Gao, Wanzhao Yang, Sifan Yuan, Ivan Marsic
To overcome this limitation and improve SSL performance, we introduce \algo, a novel algorithm that fully utilizes unlabeled data to boost semi-supervised learning.
no code implementations • 20 Nov 2023 • Chenyang Gao, Yue Gu, Ivan Marsic
Despite its success, previous studies showed that PIT is plagued by excessive label assignment switching in adjacent epochs, impeding the model to learn better label assignments.
no code implementations • 6 Jul 2022 • Keyi Li, Sen yang, Travis M. Sullivan, Randall S. Burd, Ivan Marsic
The best model achieved an average F1-score of 0. 67 for 61 activity types.
no code implementations • 15 Mar 2022 • Keyi Li, Sen yang, Travis M. Sullivan, Randall S. Burd, Ivan Marsic
We experimented with different models of representation learning and used the learned model to generate synthetic process data.
no code implementations • 20 Oct 2021 • Chenyang Gao, Yue Gu, Ivan Marsic
We investigate the use of the mapping-based method in the time domain and show that it can perform better on a large training set than the masking-based method.
no code implementations • ICCV 2021 • Yanyi Zhang, Xinyu Li, Chunhui Liu, Bing Shuai, Yi Zhu, Biagio Brattoli, Hao Chen, Ivan Marsic, Joseph Tighe
We first introduce the vanilla video transformer and show that transformer module is able to perform spatio-temporal modeling from raw pixels, but with heavy memory usage.
Ranked #15 on Action Classification on Charades
1 code implementation • CVPR 2022 • Jiaojiao Zhao, Yanyi Zhang, Xinyu Li, Hao Chen, Shuai Bing, Mingze Xu, Chunhui Liu, Kaustav Kundu, Yuanjun Xiong, Davide Modolo, Ivan Marsic, Cees G. M. Snoek, Joseph Tighe
We propose TubeR: a simple solution for spatio-temporal video action detection.
no code implementations • CVPR 2021 • Yanyi Zhang, Xinyu Li, Ivan Marsic
Multi-label activity recognition is designed for recognizing multiple activities that are performed simultaneously or sequentially in each video.
2 code implementations • 15 Apr 2019 • Jalal Abdulbaqi, Yue Gu, Ivan Marsic
Most current speech enhancement models use spectrogram features that require an expensive transformation and result in phase information loss.
no code implementations • 6 Dec 2018 • Yanyi Zhang, Xinyu Li, Kaixiang Huang, Yehan Wang, Shuhong Chen, Ivan Marsic
We present a system for concurrent activity recognition.
no code implementations • COLING 2018 • Yue Gu, Kangning Yang, Shiyu Fu, Shuhong Chen, Xinyu Li, Ivan Marsic
The proposed hybrid attention architecture helps the system focus on learning informative representations for both modality-specific feature extraction and model fusion.
no code implementations • ACL 2018 • Yue Gu, Kangning Yang, Shiyu Fu, Shuhong Chen, Xinyu Li, Ivan Marsic
Multimodal affective computing, learning to recognize and interpret human affects and subjective information from multiple data sources, is still challenging because: (i) it is hard to extract informative features to represent human affects from heterogeneous inputs; (ii) current fusion strategies only fuse different modalities at abstract level, ignoring time-dependent interactions between modalities.
no code implementations • 22 Feb 2018 • Yue Gu, Shuhong Chen, Ivan Marsic
In this paper, we present a novel deep multimodal framework to predict human emotions based on sentence-level spoken language.
no code implementations • 16 Sep 2017 • Shuhong Chen, Sen yang, Moliang Zhou, Randall S. Burd, Ivan Marsic
We applied PIMA to analyzing medical workflow data, showing how iterative alignment can better represent the data and facilitate the extraction of insights from data visualization.
no code implementations • 28 Feb 2017 • Xinyu Li, Yanyi Zhang, Jianyu Zhang, Yueyang Chen, Shuhong Chen, Yue Gu, Moliang Zhou, Richard A. Farneth, Ivan Marsic, Randall S. Burd
For the Olympic swimming dataset, our system achieved an accuracy of 88%, an F1-score of 0. 58, a completeness estimation error of 6. 3% and a remaining-time estimation error of 2. 9 minutes.
no code implementations • 10 Feb 2017 • Xinyu Li, Yanyi Zhang, Ivan Marsic, Randall S. Burd
We introduce a novel, accurate and practical system for real-time people tracking and identification.
no code implementations • 6 Feb 2017 • Xinyu Li, Yanyi Zhang, Jianyu Zhang, Shuhong Chen, Ivan Marsic, Richard A. Farneth, Randall S. Burd
Our system is the first to address the concurrent activity recognition with multisensory data using a single model, which is scalable, simple to train and easy to deploy.