Yan Shen
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Previous Organizations / Institutes
The organizations / institutes from the scholar's other articles in the past ten years
Yan Shen has a total of 30 co-authors. Here are the top co-authors by number of shared publications:
- Akira Matsui
Yokohama National University
1 shared publication - Anuja Majmundar
Department of Preventive Medicine, Keck School of Medicine, University of Southern California, Los Angeles, USA
1 shared publication - Anurag Arnab
Google research
1 shared publication - Arsha Nagrani
University of Oxford
1 shared publication - Ashok Deb
University of Southern California, USA
1 shared publication Austin Myers
Google
1 shared publication
Latest Publications
- Open Access
- 28 March 2025
- Published by Springer Nature in Educational Technology Research and Development
- p. 1-37
Integrating cognition, self-regulation, motivation, and metacognition: a framework of post-pandemic flipped classroom design
The adoption of blended and hybrid Flipped Classroom (FC) models increased dramatically during COVID-19 and is still highly valued and recommended for enhancing the quality, flexibility, and effectiveness of teaching and learning post-pandemic. While meta-analyses indicate a small yet meaningful effect size of the FC approach, examined studies often lack theoretical groundings and/or explicit design frameworks. As a result, there is an ever-increasing need for instructional design guidance for effectively integrating and facilitating online and in-person learning in the FC context. The current paper outlines a framework intended to guide educators, designers, and researchers to maximize the synergy of online and in-person learning as they design and implement FC. Grounded in (Merrill, First principles of instruction: Identifying and designing effective, efficient and engaging instruction, Pfeiffer, 2013) First Principles of Instruction, (Zimmerman and Schunk, Zimmerman and Schunk (eds), Handbook of self-regulation of learning and performance, Routledge, 2011) Self-Regulated Learning process, (Jones, Motivating students by design: Practical strategies for professors, CreateSpace, 2018) MUSIC Model of Academic Motivation, and (Flavell, American Psychologist 34:906, 1979) Metacognition theory, we first present a conceptual framework with flipped learning cycle, self-regulated learning cycle, and metacognitive FC orientation. Informed by these theories and our FC design experience across disciplines, we convert the conceptual framework into a procedural framework by organizing the design aspects and components into a generic FC learning process. Finally, we propose theoretically and empirically grounded design strategies for individual components of the FC process, which can be further validated and refined through iterative educational design research.
- 28 March 2025
- Published by Springer Nature in Educational Technology Research and Development
- p. 1-37
Open AccessIntegrating cognition, self-regulation, motivation, and metacognition: a framework of post-pandemic flipped classroom design
The adoption of blended and hybrid Flipped Classroom (FC) models increased dramatically during COVID-19 and is still highly valued and recommended for enhancing the quality, flexibility, and effectiveness of teaching and learning post-pandemic. While meta-analyses indicate a small yet meaningful effect size of the FC approach, examined studies often lack theoretical groundings and/or explicit design frameworks. As a result, there is an ever-increasing need for instructional design guidance for effectively integrating and facilitating online and in-person learning in the FC context. The current paper outlines a framework intended to guide educators, designers, and researchers to maximize the synergy of online and in-person learning as they design and implement FC. Grounded in (Merrill, First principles of instruction: Identifying and designing effective, efficient and engaging instruction, Pfeiffer, 2013) First Principles of Instruction, (Zimmerman and Schunk, Zimmerman and Schunk (eds), Handbook of self-regulation of learning and performance, Routledge, 2011) Self-Regulated Learning process, (Jones, Motivating students by design: Practical strategies for professors, CreateSpace, 2018) MUSIC Model of Academic Motivation, and (Flavell, American Psychologist 34:906, 1979) Metacognition theory, we first present a conceptual framework with flipped learning cycle, self-regulated learning cycle, and metacognitive FC orientation. Informed by these theories and our FC design experience across disciplines, we convert the conceptual framework into a procedural framework by organizing the design aspects and components into a generic FC learning process. Finally, we propose theoretically and empirically grounded design strategies for individual components of the FC process, which can be further validated and refined through iterative educational design research.
- 16 June 2024
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 18243-18252
Streaming Dense Video Captioning
An ideal model for dense video captioning - predicting captions localized temporally in a video - should be able to handle long input videos, predict rich, detailed textual descriptions, and be able to produce outputs before processing the entire video. Current state-of-the-art models, however, process a fixed number of downsampled frames, and make a single full prediction after seeing the whole video. We propose a streaming dense video captioning model that consists of two novel components: First, we propose a new memory module, based on clustering incoming tokens, which can handle arbitrarily long videos as the memory is of a fixed size. Second, we develop a streaming decoding algorithm that enables our model to make predictions before the entire video has been processed. Our model achieves this streaming ability, and significantly improves the state-of-the-art on three dense video captioning benchmarks: ActivityNet, YouCook2 and ViTT. Our code is released at https://github.com/google-research/scenic.
- 16 June 2024
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 18243-18252
Streaming Dense Video Captioning
An ideal model for dense video captioning - predicting captions localized temporally in a video - should be able to handle long input videos, predict rich, detailed textual descriptions, and be able to produce outputs before processing the entire video. Current state-of-the-art models, however, process a fixed number of downsampled frames, and make a single full prediction after seeing the whole video. We propose a streaming dense video captioning model that consists of two novel components: First, we propose a new memory module, based on clustering incoming tokens, which can handle arbitrarily long videos as the memory is of a fixed size. Second, we develop a streaming decoding algorithm that enables our model to make predictions before the entire video has been processed. Our model achieves this streaming ability, and significantly improves the state-of-the-art on three dense video captioning benchmarks: ActivityNet, YouCook2 and ViTT. Our code is released at https://github.com/google-research/scenic.
- 6 April 2022
- Published by Springer Nature in Applied Intelligence
- Vol. 52 (15) , 17864-17880
Video summarization with u-shaped transformer
- 6 April 2022
- Published by Springer Nature in Applied Intelligence
- Vol. 52 (15) , 17864-17880
Video summarization with u-shaped transformer
- Open Access
- 1 November 2021
- Published by University of California Press in The American Biology Teacher
- Vol. 83 (9) , 600-602
A New Open-Source Web Application with Animations to Support Learning of Neuron-to-Neuron Signaling
Pesticides and their associated modes of action serve as real-world examples of chemical toxicity, stimulating student interest and supporting their understanding of nervous system function and cell signaling. An open-source web application called “Neuron-to-Neuron Normal and Toxic Actions” hosts narrated animations of pesticide toxic actions and exists as a resource for instructors of advanced secondary or undergraduate biology courses. This article describes the features of the web application, reports student feedback on the animations, and details a cooperative learning procedure for instructors to use the web application in online learning environments or in-person classroom settings with technology support.
- 1 November 2021
- Published by University of California Press in The American Biology Teacher
- Vol. 83 (9) , 600-602
Open AccessA New Open-Source Web Application with Animations to Support Learning of Neuron-to-Neuron Signaling
Pesticides and their associated modes of action serve as real-world examples of chemical toxicity, stimulating student interest and supporting their understanding of nervous system function and cell signaling. An open-source web application called “Neuron-to-Neuron Normal and Toxic Actions” hosts narrated animations of pesticide toxic actions and exists as a resource for instructors of advanced secondary or undergraduate biology courses. This article describes the features of the web application, reports student feedback on the animations, and details a cooperative learning procedure for instructors to use the web application in online learning environments or in-person classroom settings with technology support.
- 1 August 2019
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- Vol. 26, 929-934
A Brief Review on Loop Closure Detection with 3D Point Cloud
A robust loop closure detection (LCD) in simultaneous localization and mapping (SLAM) can lead to more consistent and accurate map, which is a key part of SLAM. Currently, there are two main kind of data sources used for loop closure detection, the 2D image or 3D points. The 2D image-based LCD method has been extensively studied and many literatures have been published. However, this kind of method is sensitive to the illumination, the change of weather conditions and season et al. With the rapid development of self-driving technique, LiDAR-based SLAM has attracted many researchers because of its advantages. In this paper, we make a summarization on the recent developments of LCD method with 3D data source, especially with 3D point cloud input, and classify these methods into three groups, point feature based, segmentation/object based, and learning-based methods. For each group, the typical references are introduced. For the feature based method, four kind of features for LCD are introduced. Based on these introduction, the readers can get an overview on these LCD methods and even their working principles. Some discussions and the future trend on LCD with 3D point are also presented.
- 1 August 2019
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- Vol. 26, 929-934
A Brief Review on Loop Closure Detection with 3D Point Cloud
A robust loop closure detection (LCD) in simultaneous localization and mapping (SLAM) can lead to more consistent and accurate map, which is a key part of SLAM. Currently, there are two main kind of data sources used for loop closure detection, the 2D image or 3D points. The 2D image-based LCD method has been extensively studied and many literatures have been published. However, this kind of method is sensitive to the illumination, the change of weather conditions and season et al. With the rapid development of self-driving technique, LiDAR-based SLAM has attracted many researchers because of its advantages. In this paper, we make a summarization on the recent developments of LCD method with 3D data source, especially with 3D point cloud input, and classify these methods into three groups, point feature based, segmentation/object based, and learning-based methods. For each group, the typical references are introduced. For the feature based method, four kind of features for LCD are introduced. Based on these introduction, the readers can get an overview on these LCD methods and even their working principles. Some discussions and the future trend on LCD with 3D point are also presented.
- Open Access
- 1 August 2018
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 1-4
Social Bots for Online Public Health Interventions
According to the Center for Disease Control and Prevention, hundreds of thousands initiate smoking each year, and millions live with smoking-related diseases in the United States. Many tobacco users discuss their opinions, habits and preferences on social media. This work conceptualizes a framework for targeted health interventions to inform tobacco users about the consequences of tobacco use. We designed a Twitter bot named Notobot (short for No-Tobacco Bot) that leverages machine learning to identify users posting pro-tobacco tweets and select individualized interventions to curb their tobacco use. We searched the Twitter feed for tobacco-related keywords and phrases, and trained a convolutional neural network using over 4,000 tweets manually labeled as either pro-tobacco or not pro-tobacco. This model achieved a 90% accuracy rate on the training set and 74% on test data. Users posting protobacco tweets were matched with former smokers with similar interests who posted anti-tobacco tweets. Algorithmic matching, leveraging the power of peer influence, allows for the systematic delivery of personalized interventions based on real anti-tobacco tweets from former smokers. Experimental evaluation suggested that our system would perform well if deployed.
- 1 August 2018
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 1-4
Open AccessSocial Bots for Online Public Health Interventions
According to the Center for Disease Control and Prevention, hundreds of thousands initiate smoking each year, and millions live with smoking-related diseases in the United States. Many tobacco users discuss their opinions, habits and preferences on social media. This work conceptualizes a framework for targeted health interventions to inform tobacco users about the consequences of tobacco use. We designed a Twitter bot named Notobot (short for No-Tobacco Bot) that leverages machine learning to identify users posting pro-tobacco tweets and select individualized interventions to curb their tobacco use. We searched the Twitter feed for tobacco-related keywords and phrases, and trained a convolutional neural network using over 4,000 tweets manually labeled as either pro-tobacco or not pro-tobacco. This model achieved a 90% accuracy rate on the training set and 74% on test data. Users posting protobacco tweets were matched with former smokers with similar interests who posted anti-tobacco tweets. Algorithmic matching, leveraging the power of peer influence, allows for the systematic delivery of personalized interventions based on real anti-tobacco tweets from former smokers. Experimental evaluation suggested that our system would perform well if deployed.