Computer vision publications
-
Generative Memory for Lifelong Reinforcement Learning
Our research is focused on understanding and applying biological memory transfers to new AI systems that can fundamentally improve their performance, throughout their fielded lifetime experience.
-
Aesop: A Visual Storytelling Platform for Conversational AI and Commonsense Grounding
We believe that the future of Artificial Intelligence (AI) will be a mixed-initiative collaboration between humans and AI as equals.
-
Learn, Generate, Rank, Explain: A Case Study of Explanation by Generation
We propose a case study of a novel machine learning approach for generative searching and ranking of motion capture activities with visual explanation.
-
Generalized Ternary Connect: End-to-End Learning and Compression of Multiplication-Free Deep Neural Networks
The use of deep neural networks in edge computing devices hinges on the balance between accuracy and complexity of computations. Ternary Connect (TC) \cite{lin2015neural} addresses this issue by restricting the…
-
Human Motion Modeling using DVGANs
We present a novel generative model for human motion modeling using Generative Adversarial Networks (GANs).
-
Zero-Shot Object Detection
We introduce and tackle the problem of zero-shot object detection, which aims to detect object classes which are not observed during training.
-
Power-grid controller anomaly detection with enhanced temporal deep learning
Controllers of security-critical cyber-physical systems, like the power grid, are a very important class of computer systems. Attacks against the control code of a power-grid system, especially zero-day attacks, can…
-
Evaluating Visual-Semantic Explanations using a Collaborative Image Guessing Game
Abstract While there have been many proposals on making AI algorithms explainable, few have attempted to evaluate the impact of AI-generated explanations on human performance in conducting human-AI collaborative tasks.…
-
Augmented Reality Driving Using Semantic Geo-Registration
We propose a new approach that utilizes semantic information to register 2D monocular video frames to the world using 3D georeferenced data, for augmented reality driving applications.
-
Efficient Fine-Grained Classification and Part Localization Using One Compact Network
We propose a novel multi-task deep network architecture that jointly optimizes both localization of parts and fine-grained class labels by learning from training data.
-
Utilizing Semantic Visual Landmarks for Precise Vehicle Navigation
This paper presents a new approach for integrating semantic information for vision-based vehicle navigation.
-
Automated Image Analysis and Classification Tool Based on Computer Vision Deep Learning Technologies
We present a rapid underwater video and automated image analysis tool using computer vision deep learning technologies.