Arrow Research search

Author name cluster

Dan Feng

Possible papers associated with this exact author name in Arrow. This page groups case-insensitive exact name matches and is not a full identity disambiguation profile.

4 papers
1 author row

Possible papers

4

AAMAS Conference 2019 Conference Paper

Exploring Improvisational Approaches to Social Knowledge Acquisition

  • Dan Feng
  • Elin Carstensdottir
  • Magy Seif El-Nasr
  • Stacy Marsella

To build agents that can engage user in more open-ended social contexts, more and more attention has been focused on data-driven approaches to reduce the requirement of extensive, hand-authored behavioral content creation. However, one fundamental challenge of data-driven approaches, is acquiring human social interaction data with sufficient variety to capture more open-ended social interactions, as well as their coherency. Previous work has attempted to extract such social knowledge using crowdsourced narratives. This paper proposes an approach to acquire the knowledge of social interaction by integrating an improvisational theatre training technique into a crowdsourcing task aimed at collecting social narratives. The approach emphasizes theory of mind concepts, through an iterative prompting process about the mental states of characters in the narrative and paired writing, in order to encourage the authoring of diverse social interactions. To assess the effectiveness of integrating prompting and two-worker improvisation to the knowledge acquisition process, we systematically compare alternative ways to design the crowdsourcing task, including a) single worker vs. two workers authoring interaction between different characters in a given social context, and b) with or without prompts. Findings from 175 participants across two different social contexts show that the prompts and two-workers collaboration could significantly improve the diversity and the objective coherency of the narratives. The results presented in this paper can provide a rich set of diverse and coherent action sequences to inform the design of socially intelligent agents.

PDF

AAAI Conference 2018 Conference Paper

End-to-End United Video Dehazing and Detection

  • Boyi Li
  • Xiulian Peng
  • Zhangyang Wang
  • Jizheng Xu
  • Dan Feng

The recent development of CNN-based image dehazing has revealed the effectiveness of end-to-end modeling. However, extending the idea to end-to-end video dehazing has not been explored yet. In this paper, we propose an End-to-End Video Dehazing Network (EVD-Net), to exploit the temporal consistency between consecutive video frames. A thorough study has been conducted over a number of structure options, to identify the best temporal fusion strategy. Furthermore, we build an End-to-End United Video Dehazing and Detection Network (EVDD-Net), which concatenates and jointly trains EVD-Net with a video object detection model. The resulting augmented end-to-end pipeline has demonstrated much more stable and accurate detection results in hazy video.

PDF Details

AAMAS Conference 2017 Conference Paper

"Is It Just Me? ": Evaluating Attribution of Negative Feedback as a Function of Virtual Instructor's Gender and Proxemics

  • Dan Feng
  • David C. Jeong
  • Nicole C. Krä mer
  • Lynn C. Miller
  • Stacy Marsella

Virtual agents are used in a number of different outcomebased contexts such as physical and mental health, skillbased training, as well as classroom learning and pedagogy. Virtual agents in such applications are largely designed so that they project positive attitude and feedback towards the human participant. Human-human interactions, however, are certainly not exclusively positive in valence. For example, teachers and educators engage in both positive and negative feedback strategies for pedagogical outcomes. While the distinct effects of positive and negative feedback on learning are well established, few studies have attempted to examine the effects of negative feedback across different combinations of instructor’s gender and proxemics-based physical behavior. This study explores this very question with a 2 (instructor gender)*2 (proxemic behavior) between subject design. In this experiment, participants (N=63) actively engage in a learning task with a male/female virtual instructor that provides negative feedback while either standing stationary or while physically approaching the participant. Based on the different deliveries of the negative feedback, the study aimed to identify the sources of variations in participant reactions to the negative feedback, namely patterns of attribution and both behavioral and physiological measurements of emotions. The results indicate that participants attribute greater self-blame (internal attribution) for their purported poor performance when interacting with the female virtual instructor than when interacting with the male virtual instructor. Participants also generally exhibited greater positive affect in response to female virtual professors than male virtual professors. These results are highly relevant both to the design of virtual agents as well as to adding to our understanding of the role of gender and behavior in human-human, non-peer interaction. Appears in: Proceedings of the 16th International Conference on Autonomous Agents and Multiagent Systems (AA- MAS 2017), S. Das, E. Durfee, K. Larson, M. Winikoff (eds.), May 8–12, 2017, São Paulo, Brazil. Copyright c 2017, International Foundation for Autonomous Agents and Multiagent Systems (www. ifaamas. org). All rights reserved.

PDF
v2026.09.13