Michael Maynord

University of Maryland, College Park | UMD, UMCP, University of Maryland College Park · Department of Computer Science

In this paper we introduce a rule-based, compositional, and hierarchical modeling of action using Therbligs as our atoms. Introducing these atoms provides us with a consistent, expressive, contact-centered representation of action. Over the atoms we introduce a differentiable method of rule-based reasoning to regularize for logical consistency. Our...

Purpose: Machine learning algorithms are best trained with large quantities of accurately annotated samples. While natural scene images can often be labeled relatively cheaply and at large scale, obtaining accurate annotations for medical images is both time consuming and expensive. In this study, we propose a cooperative labeling method that allo...

Action plays a central role in our lives and environments, yet most Computer Vision methods do not explicitly model action. In this chapter we outline an action-centric framework which spans multiple time scales and levels of abstraction, producing both action and scene interpretations constrained towards action consistency. At the lower level of t...

Human actions involving hand manipulations are structured according to the making and breaking of hand-object contact, and human visual understanding of action is reliant on anticipation of contact as is demonstrated by pioneering work in cognitive science. Taking inspiration from this, we introduce representations and models centered on contact, w...

Human visual understanding of action is reliant on anticipation of contact as is demonstrated by pioneering work in cognitive science. Taking inspiration from this, we introduce representations and models centered on contact, which we then use in action prediction and anticipation. We annotate a subset of the EPIC Kitchens dataset to include time-t...

We introduce Egocentric Object Manipulation Graphs (Ego-OMG) - a novel representation for activity modeling and anticipation of near future actions integrating three components: 1) semantic temporal structure of activities, 2) short-term dynamics, and 3) representations for appearance. Semantic temporal structure is modeled through a graph, embedde...

In this paper we demonstrate that state-of-the-art convolutional neural networks can be constructed using a cascade algorithm for deep networks, inspired by the cascade algorithm in wavelet analysis. For each network layer the cascade algorithm creates two streams of features from the previous layer: one stream modulates the existing features produ...

We describe our Meta-cognitive, Integrated, Dual-Cycle Architecture (MIDCA), whose purpose is to provide agents with a greater capacity for acting in an open world and dealing with unexpected events. We present MIDCA-1.0, a partial implementation which explores a novel machine-learning approach to goal generation using the Tilde and FOIL algorithms...

We describe an iPad app which assists in language acquisition and development. Such an application can be used by clinicians for human developmental disabilities. A user drags images around on the screen. The app generates and speaks random (but sensible) phrases that matches the image interact. For example, if a user drags an image of a squirrel o...