More Like this

1. Deep Multi-Task Learning with Adversarial-and-Cooperative Nets

   https://doi.org/10.24963/ijcai.2019/566  

   Yang, Pei; Tan, Qi; Ye, Jieping; Tong, Hanghang; He, Jingrui (August 2019, IJCAI)

   In this paper, we propose a deep multi-Task learning model based on Adversarial-and-COoperative nets (TACO). The goal is to use an adversarial-and-cooperative strategy to decouple the task-common and task-specific knowledge, facilitating the fine-grained knowledge sharing among tasks. TACO accommodates multiple game players, i.e., feature extractors, domain discriminator, and tri-classifiers. They play the MinMax games adversarially and cooperatively to distill the task-common and task-specific features, while respecting their discriminative structures. Moreover, it adopts a divide-and-combine strategy to leverage the decoupled multi-view information to further improve the generalization performance of the model. The experimental results show that our proposed method significantly outperforms the state-of-the-art algorithms on the benchmark datasets in both multi-task learning and semi-supervised domain adaptation scenarios. 

   more » « less
2. Evaluating the Consistency of Cooperative Video Games in Inducing Teamwork Behaviors

   https://doi.org/10.1177/21695067231196239  

   Farah, Yvonne A.; Banuelos-Moriel, Antonio; Dorneich, Michael C. (September 2023, Proceedings of the Human Factors and Ergonomics Society Annual Meeting)

   Teamwork assessment requires research environments that replicate the task complexity and induce challenges and uncertainty. Gamified environments are gaining attention as suitable environments for teamwork assessment, where teaming behaviors can be quantified. However, further research is needed to establish the relationship between gaming mechanics and teaming competencies. This work aims to assess the consistency of video games in inducing teaming behaviors. Five video games were analyzed through coding behaviors and cooperative features from gameplay streams. Results show that the selected games induce similar behavioral profiles of percentages of teaming competencies. These games have similar design characteristics, including performance environments and game loops. Design suggestions reflect potential associations between the analyzed game mechanics and the resulting behavioral profiles. The resulting teamwork profiles can be targeted through the simulation cooperative genre, therefore providing a design tool for teamwork testbed designers to induce teamwork distributions of interest. 

   more » « less
3. Looking for a Deal?: Visual Social Attention during Negotiations via Mixed Media Videoconferencing

   https://doi.org/10.1145/3434169  

   Vrzakova, Hana; Amon, Mary Jean; Rees, McKenzie; Faber, Myrthe; D'Mello, Sidney (January 2021, Proceedings of the ACM on Human-Computer Interaction)

   null (Ed.)

   Whereas social visual attention has been examined in computer-mediated (e.g., shared screen) or video-mediated (e.g., FaceTime) interaction, it has yet to be studied in mixed-media interfaces that combine video of the conversant along with other UI elements. We analyzed eye gaze of 37 dyads (74 participants) who were tasked with negotiating the price of a new car (as a buyer and seller) using mixed-media video conferencing under competitive or cooperative negotiation instructions (experimental manipulation). We used multidimensional recurrence quantification analysis to extract spatio-temporal patterns corresponding to mutual gaze (individuals look at each other), joint attention (individuals focus on the same elements of the interface), and gaze aversion (an individual looks at their partner, who is looking elsewhere). Our results indicated that joint attention predicted the sum of points attained by the buyer and seller (i.e., the joint score). In contrast, gaze aversion was associated with faster time to complete the negotiation, but with a lower joint score. Unexpectedly, mutual gaze was highly infrequent and unrelated to the negotiation outcomes and none of the gaze patterns predicted subjective perceptions of the negotiation. There were also no effects of gender composition or negotiation condition on the gaze patterns or negotiation outcomes. Our results suggest that social visual attention may operate differently in mixed-media collaborative interfaces than in face-to-face interaction. As mixed-media collaborative interfaces gain prominence, our work can be leveraged to inform the design of gaze-sensitive user interfaces that support remote negotiations among other tasks. 

   more » « less
4. Cognitive Engagement for STEM+C Education: Investigating Serious Game Impact on Graph Structure Learning with fNIRS

   https://doi.org/10.1109/AIxVR59861.2024.00032  

   Sharmin, Shayla; Koiler, Reza; Sadik, Rifat; Bhattacharjee, Arpan; Patre, Priyanka Raju; Kullu, Pinar; Hohensee, Charles; Getchell, Nancy; Barmaki, Roghayeh Leila (January 2024, IEEE International Conference on Artificial Intelligence and Virtual Reality)

   For serious games on education, understanding the effectiveness of different learning methods in influencing cognitive processes remains a significant challenge. In particular, limited research addresses the comparative effectiveness of serious games and videos in analyzing brain behavior for graph structure learning, which is an important part of the Science, Technology, Engineering, Math, and Computing (STEM+C) disciplinary education. This study investigates the impact of serious games on graph structure learning. For this, we compared our in-house game-based learning (GBL) and video-based learning (VBL) methodologies by evaluating their effectiveness on cognitive processes by oxygenated hemoglobin levels using functional near-infrared spectroscopy (fNIRS). We conducted a 2×1 between-subjects preliminary study with twelve participants, involving two conditions: game and video. Both groups received equivalent content related to the basic structure of a graph, with comparable session lengths. The game group interacted with a quiz-based game, while the video group watched a pre-recorded video. The fNIRS was employed to capture cerebral signals from the prefrontal cortex, and participants completed pre- and post-questionnaires capturing user experience and knowledge gain. In our study, we noted that the mean levels of oxygenated hemoglobin (delta HbO) were higher in the GBL group, suggesting the potential enhanced cognitive involvement. Our results show that the lateral prefrontal cortex (LPFC) has greater hemodynamic activity during the learning period. Moreover, knowledge gain analysis showed an increase in mean score in the GBL group compared to the VBL group. Although we did not observe statistically significant changes due to participant variability and sample size, this preliminary work contributes to understanding how GBL and VBL impact cognitive processes, providing insights for enhanced instructional design and educational game development. Additionally, it emphasizes the necessity for further investigation into the impact of GBL on cognitive engagement and learning outcomes. 

   more » « less
5. Using Physiological Linkage for Patient State Assessment In a Competitive Rehabilitation Game

   https://doi.org/10.1109/ICORR.2019.8779361  

   Darzi, Ali; Novak, Domen (June 2019, Proceedings of the 2019 IEEE International Conference on Rehabilitation Robotics)

   null (Ed.)

   Competitive rehabilitation games can enhance motivation and exercise intensity compared to solo exercise; however, since such games may be played by two people with different abilities, game difficulty must be dynamically adapted to suit both players. State-of-the-art adaptation algorithms are based on players' performance (e.g., score), which may not be representative of the patient's physical and psychological state. Instead, we propose a method that estimates players' states in a competitive game based on the covariation of players' physiological responses. The method was evaluated in 10 unimpaired pairs, who played a competitive game in 6 conditions while 5 physiological responses were measured: respiration, skin conductance, heart rate, and 2 facial electromyograms. Two physiological linkage methods were used to assess the similarity of the players' physiological measurements: coherence of raw measurements and correlation of heart and respiration rates. These linkage features were compared to traditional individual physiological features in classification of players' affects (enjoyment, valence, arousal, perceived difficulty) into 'low' and 'high' classes. Classifiers based on physiological linkage resulted in higher accuracies than those based on individual physiological features, and combining both feature types yielded the highest classification accuracies (75% to 91%). These classifiers will next be used to dynamically adapt game difficulty during rehabilitation. 

   more » « less