Thesis Chapters by Lingfei Luan
The analysis method and paradigm of a film have become a controversial topic in the data-driven e... more The analysis method and paradigm of a film have become a controversial topic in the data-driven era. The film, is not only an attractive industry that can achieve filmmakers’ imagination but has become a perfect stimulus to understand human being’s mental activity. The core research in this study is to examine the impact of filmmaking experience and the role of narrative denoters from filmmakers’ construction to audiences’ interpretation. Based on previous studies and integrating cognitive approaches, the thesis re-explores the nature and essence of the film and proposes an alternative term - narrative denoter - which can be used as the indication of message exchanging between filmmakers and audiences. Using a released film that has a complete story to do the experiment, this study investigates the relationship between major, film interpretations, event segmentation, and audience’s preference. The result showed that filmmaking experience does not impact the interpretation of film; however the identification of the narrative denoter played an important role in film perception and cognition; apart from these, the audience’s preference did not correlate with film interpretation. With respect to this result, the narrative denoter can be an indicator to demonstrate the message transitions from filmmaker to audiences. Suggestions were made for future cognitive film studies on using the narrative denoters as a new analysis unit.
Papers by Lingfei Luan
arXiv (Cornell University), Nov 19, 2023
Automated human action recognition, a burgeoning field within computer vision, boasts diverse app... more Automated human action recognition, a burgeoning field within computer vision, boasts diverse applications spanning surveillance, security, human-computer interaction, tele-health, and sports analysis. Precise action recognition in infants serves a multitude of pivotal purposes, encompassing safety monitoring, developmental milestone tracking, early intervention for developmental delays, fostering parent-infant bonds, advancing computer-aided diagnostics, and contributing to the scientific comprehension of child development. This paper delves into the intricacies of infant action recognition, a domain that has remained relatively uncharted despite the accomplishments in adult action recognition. In this study, we introduce a groundbreaking dataset called "InfActPrimitive", encompassing five significant infant milestone action categories, and we incorporate specialized preprocessing for infant data. We conducted an extensive comparative analysis employing cutting-edge skeleton-based action recognition models using this dataset. Our findings reveal that, although the PoseC3D model achieves the highest accuracy at approximately 71%, the remaining models struggle to accurately capture the dynamics of infant actions. This highlights a substantial knowledge gap between infant and adult action recognition domains and the urgent need for data-efficient pipeline models † .
Rethinking Hybrid and Remote Work in Higher Education
International Journal of Chinese Education
STEM learning aims to prepare students with hands-on and problem-based learning. However, teacher... more STEM learning aims to prepare students with hands-on and problem-based learning. However, teacher-centered instruction has been the predominant course delivery technique in STEM education regardless face-to-face or online learning context. Using both quantitative and qualitative research methods, this study explores the expectations of effective online courses based on Moore’s three types of interactions among Chinese STEM college students taking synchronous teacher-centered lecture-based online courses. A total of 175 undergraduate STEM students were recruited at one Chinese university. Results indicate that these students expect their instructors to integrate activities to motivate interactions with their instructor, peers, and the learning content. Students’ perceptions of the advantages and challenges of taking synchronous lecture-based courses are also discussed. It is expected that the findings would enlighten professionals of higher education in China to adjust teacher-center...
2023 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW)
arXiv (Cornell University), Feb 3, 2023
The emergence of artificial intelligence has incited a paradigm shift across the spectrum of huma... more The emergence of artificial intelligence has incited a paradigm shift across the spectrum of human endeavors, with ChatGPT serving as a catalyst for the transformation of various established domains, including but not limited to education, journalism, security, and ethics. In the post-pandemic era, the widespread adoption of remote work has prompted the educational sector to reassess conventional pedagogical methods. This paper is to scrutinize the underlying psychological principles of ChatGPT, delve into the factors that captivate user attention, and implicate its ramifications on the future of learning. The ultimate objective of this study is to instigate a scholarly discourse on the interplay between technological advancements in education and the evolution of human learning patterns, raising the question of whether technology is driving human evolution or vice versa. Keywords： Artificial intelligence (AI), Human-machine communication, COVID-19, Chat GPT, Learning 3.0, Critical Thinking 1.Introduction of ChatGPT ChatGPT, a chatbot developed by OpenAI, can interpret and respond to natural language input using the GPT-3 language model which has 175 billion parameters (Floridi & Chiriatti, 2020). The utilization of a word-driven dialogue system offers assistance in cross-domain problem resolution and the generation of content to answer users' inquiries. (old: Word-driven dialogue provides support with cross-domain problem-solving and generative content to address users' questions). Within one week of its introduction to the public, one million consumers had signed up for the platform (Haque et al., 2022). This has spurred a discussion over the implications of ChatGPT in a variety of fields, including education. Some educators claim that the emergence of such technology renders conventional online exams outmoded and raises worries over the eventual automation of the teaching profession (Kung et al., 2022; Cotton, 2023; Pavlik, 2023; King &ChatGPT 2023). In contrast, some argue that ChatGPT has the potential to improve students' adaptability to changing educational needs and develop independent learning practices, which also assist instructors in providing customized training plans (Zhai, 2022; Qadir, 2022; FIRAT, 2022). The considerable interest received by this chatbot necessitates more research into the psychological underpinning its use and its possible influence on the evolution of educational paradigms. The discourse around AI's incorporation into the education sector and its role in molding the education of future generations include not just talks of technology developments, but also considerations of the human experience and the behavioral consequences of technological change.
2023 IEEE/CVF Winter Conference on Applications of Computer Vision (WACV), 2023
Bilateral postural symmetry plays a key role as a potential risk marker for autism spectrum disor... more Bilateral postural symmetry plays a key role as a potential risk marker for autism spectrum disorder (ASD) and as a symptom of congenital muscular torticollis (CMT) in infants, but current methods of assessing symmetry require laborious clinical expert assessments. In this paper, we develop a computer vision based infant symmetry assessment system, leveraging 3D human pose estimation for infants. Evaluation and calibration of our system against ground truth assessments is complicated by our findings from a survey of human ratings of angle and symmetry, that such ratings exhibit low inter-rater reliability. To rectify this, we develop a Bayesian estimator of the ground truth derived from a probabilistic graphical model of fallible human raters. We show that the 3D infant pose estimation model can achieve 68% area under the receiver operating characteristic curve performance in predicting the Bayesian aggregate labels, compared to only 61% from a 2D infant pose estimation model and 60% from a 3D adult pose estimation model, highlighting the importance of 3D poses and infant domain knowledge in assessing infant body symmetry. Our survey analysis also suggests that human ratings are susceptible to higher levels of bias and inconsistency, and hence our final 3D pose-based symmetry assessment system is calibrated but not directly supervised by Bayesian aggregate human ratings, yielding higher levels of consistency and lower levels of inter-limb assessment bias 1 .
International journal of education and humanities, May 9, 2022
This paper investigates how interdisciplinary research impacts the film industry in research and ... more This paper investigates how interdisciplinary research impacts the film industry in research and practice by introducing psychological concepts. Psychology, especially neural and cognitive science, provides a distinct advantage when examining humans' audiovisual processing mechanisms and esthetics questions regarding the film. By introducing psychology, film researchers and filmmakers could rethink and evaluate the current research paradigm from a broader point of view. This paper consists of three parts: (1) a discussion on the nature of film using an interdisciplinary approach; (2) a discussion on the characteristics and attributes of film; (3) an introduction of the psychological concept of "affordance" to film studies and practice. Although the film interdisciplinary research paradigm is still under development, we argue that introducing the other subjects is innovating the field of film research, providing us with a new angle to examine the intersections of ubiquitous but complex human esthetics activities.
The analysis method and paradigm of film have become a controversial topic in the data-driven era... more The analysis method and paradigm of film have become a controversial topic in the data-driven era. Film, is not only an attractive industry that can achieve filmmakers' imagination but has become a perfect stimulus to understand human being's mental activity. The core research in this study is to examine the impact of filmmaking experience and the role of narrative denoters from filmmakers' construction to audiences' interpretation. Based on previous studies and integrating cognitive approaches, the thesis re-explores the nature and essence of film and proposes an alternative term-narrative denoter-which can be used as the indication of message exchanging between filmmakers and audiences. Using a released film that has a complete story to do the experiment, this study investigates the relationship between major, film interpretations, event segmentation, and audience's preference. The result showed that filmmaking experience does not impact the interpretation of film; however the identification of the narrative denoter played an important role in film perception and cognition; apart from these, the audience's preference did not correlate with film interpretation. With respect to this result, the narrative denoter can be indicator to demonstrate the message transitions from filmmaker to audience. Suggestions were made for future cognitive film studies on using the narrative denoters as a new analysis unit.
This research considers the ranking and selection (R&S) problem of selecting the optimal subset f... more This research considers the ranking and selection (R&S) problem of selecting the optimal subset from a finite set of alternative designs. Given the total simulation budget constraint, we aim to maximize the probability of correctly selecting the top-m designs. In order to improve the selection efficiency, we incorporate the information from across the domain into regression metamodels. In this research, we assume that the mean performance of each design is approximately quadratic. To achieve a better fit of this model, we divide the solution space into adjacent partitions such that the quadratic assumption can be satisfied within each partition. Using the large deviation theory, we propose an approximately optimal simulation budget allocation rule in the presence of partitioned domains. Numerical experiments demonstrate that our approach can enhance the simulation efficiency significantly.
There is promising potential in the application of algorithmic facial landmark estimation to the ... more There is promising potential in the application of algorithmic facial landmark estimation to the early prediction, in infants, of pediatric developmental disorders and other conditions. However, the performance of these deep learning algorithms is severely hampered by the scarcity of infant data. To spur the development of facial landmarking systems for infants, we introduce InfAnFace, a diverse, richly-annotated dataset of infant faces. We use InfAnFace to benchmark the performance of existing facial landmark estimation algorithms that are trained on adult faces and demonstrate there is a significant domain gap between the representations learned by these algorithms when applied on infant vs. adult faces. Finally, we put forward the next potential steps to bridge that gap1.
Bilateral postural symmetry plays a key role as a potential risk marker for autism spectrum disor... more Bilateral postural symmetry plays a key role as a potential risk marker for autism spectrum disorder (ASD) and as a symptom of congenital muscular torticollis (CMT) in infants, but current methods of assessing symmetry require laborious clinical expert assessments. In this paper, we develop a computer vision based infant symmetry assessment system, leveraging 3D human pose estimation for infants. Evaluation and calibration of our system against ground truth assessments is complicated by our findings from a survey of human ratings of angle and symmetry, that such ratings exhibit low inter-rater reliability. To rectify this, we develop a Bayesian estimator of the ground truth derived from a probabilistic graphical model of fallible human raters. We show that the 3D infant pose estimation model can achieve 68% area under the receiver operating characteristic curve performance in predicting the Bayesian aggregate labels, compared to only 61% from a 2D infant pose estimation model and 60% from a 3D adult pose estimation model, highlighting the importance of 3D poses and infant domain knowledge in assessing infant body symmetry. Our survey analysis also suggests that human ratings are susceptible to higher levels of bias and inconsistency, and hence our final 3D pose-based symmetry assessment system is calibrated but not directly supervised by Bayesian aggregate human ratings, yielding higher levels of consistency and lower levels of inter-limb assessment bias 1 .
IBM Systems Journal, 2004
We propose a name service that enables construction of a uniform, global, hierarchical namespace,... more We propose a name service that enables construction of a uniform, global, hierarchical namespace, a key feature needed to create a file-system grid. Combined with other grid replication and location-lookup mechanisms, it supports independence of position for users and applications as well as transparency of data location in a scalable and secure fashion. This name service enables federation of individual files as well as file-system trees that are exported by a variety of distributed file systems and is extensible to include nonfile-system data such as databases or live data feeds. Such a federated namespace for files can be rendered by network file servers, such as NFS (Network File System) or CIFS (Common Internet File System) servers, proxies supporting the NAS (networkattached storage) protocol, or grid data service interfaces. File access proxies, which handle protocol translation, can also include caching and replication support to enhance data access performance. A uniform namespace with global scope and hierarchical ownership allows sharing file data between and within organizations without compromising security or autonomy.
Uploads
Thesis Chapters by Lingfei Luan
Papers by Lingfei Luan