no code implementations • LREC 2022 • Ayesha Enayet, Gita Sukthankar
This paper presents an analysis of how dialogue act sequences vary across different datasets in order to anticipate the potential degradation in the performance of learned models during domain adaptation.
no code implementations • 9 May 2024 • Syed Hammad Ahmed, Muhammad Junaid Khan, Gita Sukthankar
Due to the rise in video content creation targeted towards children, there is a need for robust content moderation schemes for video hosting platforms.
no code implementations • 6 Dec 2023 • Syed Hammad Ahmed, Shengnan Hu, Gita Sukthankar
However, generating informative prompts can be challenging for more subtle tasks, such as video content moderation.
1 code implementation • 21 Jul 2023 • Shengnan Hu, Ce Zheng, Zixiang Zhou, Chen Chen, Gita Sukthankar
Human-centric visual understanding is an important desideratum for effective human-robot interaction.
1 code implementation • 24 May 2023 • Syed Hammad Ahmed, Muhammad Junaid Khan, H. M. Umer Qaisar, Gita Sukthankar
Online video platforms receive hundreds of hours of uploads every minute, making manual content moderation impossible.
Ranked #1 on Video Classification on MoB
1 code implementation • 9 Feb 2023 • Ayesha Enayet, Gita Sukthankar
To alleviate this problem, this paper introduces a multi-feature embedding (MFeEmb) that improves the generalizability of conflict prediction models trained on dialogue sequences.
no code implementations • 18 Sep 2022 • Amirarsalan Rajabi, Mehdi Yazdani-Jahromi, Ozlem Ozmen Garibay, Gita Sukthankar
In this study, we present a fast and effective model to de-bias an image dataset through reconstruction and minimizing the statistical dependence between intended variables.
1 code implementation • 15 Aug 2022 • Muhammad Junaid Khan, Syed Hammad Ahmed, Gita Sukthankar
The StarCraft II Multi-Agent Challenge (SMAC) was created to be a challenging benchmark problem for cooperative multi-agent reinforcement learning (MARL).
no code implementations • 21 Jun 2022 • Shengnan Hu, Gita Sukthankar
This paper presents a new approach for predicting team performance from the behavioral traces of a set of agents.
no code implementations • 11 Oct 2021 • Muhammad Junaid Khan, Shah Hassan, Gita Sukthankar
Inspired by the recent success of transformers in natural language processing and computer vision applications, we introduce a transformer-based neural architecture for two key StarCraft II (SC2) macromanagement tasks: global state and build order prediction.
no code implementations • 23 Jan 2021 • Ayesha Enayet, Gita Sukthankar
Good communication is indubitably the foundation of effective teamwork.
no code implementations • 17 Nov 2020 • Zerong Xi, Gita Sukthankar
We demonstrate that the variance of the return sequence for a specific state-action pair is an important information source that can be leveraged to guide exploration in reinforcement learning.
2 code implementations • 10 Nov 2020 • Ayesha Enayet, Gita Sukthankar
Social coding platforms, such as GitHub, serve as laboratories for studying collaborative problem solving in open source software development; a key feature is their ability to support issue reporting which is used by teams to discuss tasks and ideas.
no code implementations • 6 Nov 2020 • Samaneh Saadat, Gita Sukthankar
For example, psychologists are less interested in having a model that predicts human behavior with high accuracy and more concerned with identifying differences between actions that lead to divergent human behavior.
no code implementations • 14 Sep 2019 • Saif Alabachi, Gita Sukthankar, Rahul Sukthankar
This paper describes two key innovations required to deploy deep reinforcement learning models on a real robot: 1) an abstract state representation for transferring learning from simulation to the hardware platform, and 2) reward shaping and staging paradigms for training the controller.
no code implementations • 14 Feb 2019 • Neda Hajiakhoond Bidoki, Gita Sukthankar
In this paper we introduce the concept of network semantic segmentation for social network analysis.
Social and Information Networks 91D30
no code implementations • 8 Apr 2016 • Alireza Hajibagheri, Gita Sukthankar, Kiran Lakkaraju
We compare the use of this network dynamics model to directly creating time series of network similarity measures.
no code implementations • 16 Jan 2014 • Liyue Zhao, Yu Zhang, Gita Sukthankar
Crowdsourcing platforms offer a practical solution to the problem of affordably annotating large datasets for training supervised classifiers.