activity
20152026
most citedThe iWildCam 2018 Challenge Dataset

27 citations · 98 across the 38 of their papers we have counts for

collaborators
Showing 2018Show all

5 papers · 1 filter

cs.CV2018

Digging Into Self-Supervised Monocular Depth Estimation

Clément Godard, Oisin Mac Aodha, Michael Firman +1

Per-pixel ground-truth depth data is challenging to acquire at scale. To overcome this limitation, self-supervised learning has emerged as a promising alternative for training mode…

cs.AI2018

Teaching Multiple Concepts to a Forgetful Learner

Anette Hunziker, Yuxin Chen, Oisin Mac Aodha +5

How can we help a forgetful learner learn multiple concepts within a limited time frame? While there have been extensive studies in designing optimal schedules for teaching a singl…

cs.CV2018

It's all Relative: Monocular 3D Human Pose Estimation from Weakly Supervised Data

Matteo Ruggero Ronchi, Oisin Mac Aodha, Robert Eng +1

We address the problem of 3D human pose estimation from 2D input images using only weakly supervised training data. Despite showing considerable success for 2D pose estimation, the…

cs.CV2018

Teaching Categories to Human Learners with Visual Explanations

Oisin Mac Aodha, Shihan Su, Yuxin Chen +2

We study the problem of computer-assisted teaching with explanations. Conventional approaches for machine teaching typically only provide feedback at the instance level e.g., the c…

cs.LG2018

Understanding the Role of Adaptivity in Machine Teaching: The Case of Version Space Learners

Yuxin Chen, Adish Singla, Oisin Mac Aodha +2

In real-world applications of education, an effective teacher adaptively chooses the next example to teach based on the learner's current state. However, most existing work in algo…