50 citations · 113 across the 13 of their papers we have counts for
14 papers
Compositional Clustering: Applications to Multi-Label Object Recognition and Speaker Identification
Zeqian Li, Xinlu He, Jacob Whitehill
We consider a novel clustering task in which clusters can have compositional relationships, e.g., one cluster contains images of rectangles, one contains images of circles, and a t…
Harnessing Geometric Constraints from Emotion Labels to improve Face Verification
Anand Ramakrishnan, Minh Pham, Jacob Whitehill
For the task of face verification, we explore the utility of harnessing auxiliary facial emotion labels to impose explicit geometric constraints on the embedding space when trainin…
Compositional embedding models for speaker identification and diarization with simultaneous speech from 2+ speakers
Zeqian Li, Jacob Whitehill
We propose a new method for speaker diarization that can handle overlapping speech with 2+ people. Our method is based on compositional embeddings [1]: Like standard speaker embedd…
Toward Automated Classroom Observation: Multimodal Machine Learning to Estimate CLASS Positive Climate and Negative Climate
Anand Ramakrishnan, Brian Zylich, Erin Ottmar +2
In this work we present a multi-modal machine learning-based system, which we call ACORN, to analyze videos of school classrooms for the Positive Climate (PC) and Negative Climate…
Leveraging Affect Transfer Learning for Behavior Prediction in an Intelligent Tutoring System
Nataniel Ruiz, Hao Yu, Danielle A. Allessio +10
In this work, we propose a video-based transfer learning approach for predicting problem outcomes of students working with an intelligent tutoring system (ITS). By analyzing a stud…
Compositional Embeddings for Multi-Label One-Shot Learning
Zeqian Li, Michael C. Mozer, Jacob Whitehill
We present a compositional embedding framework that infers not just a single class per input image, but a set of classes, in the setting of one-shot learning. Specifically, we prop…
Automatic Classifiers as Scientific Instruments: One Step Further Away from Ground-Truth
Jacob Whitehill, Anand Ramakrishnan
Automatic machine learning-based detectors of various psychological and social phenomena (e.g., emotion, stress, engagement) have great potential to advance basic science. However,…
How Does Knowledge of the AUC Constrain the Set of Possible Ground-truth Labelings?
Jacob Whitehill
Recent work on privacy-preserving machine learning has considered how data-mining competitions such as Kaggle could potentially be "hacked", either intentionally or inadvertently,…
Climbing the Kaggle Leaderboard by Exploiting the Log-Loss Oracle
Jacob Whitehill
In the context of data-mining competitions (e.g., Kaggle, KDDCup, ILSVRC Challenge), we show how access to an oracle that reports a contestant's log-loss score on the test set can…
Delving Deeper into MOOC Student Dropout Prediction
Jacob Whitehill, Kiran Mohan, Daniel Seaton +2
In order to obtain reliable accuracy estimates for automatic MOOC dropout predictors, it is important to train and test them in a manner consistent with how they will be used in pr…
A Crowdsourcing Approach To Collecting Tutorial Videos -- Toward Personalized Learning-at-Scale
Jacob Whitehill, Margo Seltzer
We investigated the feasibility of crowdsourcing full-fledged tutorial videos from ordinary people on the Web on how to solve math problems related to logarithms. This kind of appr…
Exploiting an Oracle that Reports AUC Scores in Machine Learning Contests
Jacob Whitehill
In machine learning contests such as the ImageNet Large Scale Visual Recognition Challenge and the KDD Cup, contestants can submit candidate solutions and receive from an oracle (t…
Understanding ACT-R - an Outsider's Perspective
Jacob Whitehill
The ACT-R theory of cognition developed by John Anderson and colleagues endeavors to explain how humans recall chunks of information and how they solve problems. ACT-R also serves…
Discriminately Decreasing Discriminability with Learned Image Filters
Jacob Whitehill, Javier Movellan
In machine learning and computer vision, input images are often filtered to increase data discriminability. In some situations, however, one may wish to purposely decrease discrimi…