Search Results for author:
Found 17 papers, 5 papers with code
An Analysis of Dialogue Act Sequence Similarity Across Multiple Domains
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.
The Potential of Vision-Language Models for Content Moderation of Children's Videos
However, generating informative prompts can be challenging for more subtle tasks, such as video content moderation.
LAMP: Leveraging Language Prompts for Multi-person Pose Estimation
Human-centric visual understanding is an important desideratum for effective human-robot interaction.
Malicious or Benign? Towards Effective Content Moderation for Children's Videos
Online video platforms receive hundreds of hours of uploads every minute, making manual content moderation impossible.
Ranked #1 on
Video Classification
on MoB
Improving the Generalizability of Collaborative Dialogue Analysis with Multi-Feature Embeddings
To alleviate this problem, this paper introduces a multi-feature embedding (MFeEmb) that improves the generalizability of conflict prediction models trained on dialogue sequences.
Through a fair looking-glass: mitigating bias in image datasets
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.
Transformer-based Value Function Decomposition for Cooperative Multi-agent Reinforcement Learning in StarCraft
The StarCraft II Multi-Agent Challenge (SMAC) was created to be a challenging benchmark problem for cooperative multi-agent reinforcement learning (MARL).
Predicting Team Performance with Spatial Temporal Graph Convolutional Networks
This paper presents a new approach for predicting team performance from the behavioral traces of a set of agents.
Leveraging Transformers for StarCraft Macromanagement Prediction
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.
Analyzing Team Performance with Embeddings from Multiparty Dialogues
Good communication is indubitably the foundation of effective teamwork.
Leveraging the Variance of Return Sequences for Exploration Policy
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.
A Transfer Learning Approach for Dialogue Act Classification of GitHub Issue Comments
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.
Explaining Differences in Classes of Discrete Sequences
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.
Selfie Drone Stick: A Natural Interface for Quadcopter Photography
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.
Network Semantic Segmentation with Application to GitHub
In this paper we introduce the concept of network semantic segmentation for social network analysis.
Social and Information Networks 91D30
Leveraging Network Dynamics for Improved Link Prediction
We compare the use of this network dynamics model to directly creating time series of network similarity measures.
An Active Learning Approach for Jointly Estimating Worker Performance and Annotation Reliability with Crowdsourced Data
Crowdsourcing platforms offer a practical solution to the problem of affordably annotating large datasets for training supervised classifiers.
