Search Results for author:
Found 25 papers, 3 papers with code
Efficient Learning and Decoding of the Continuous-Time Hidden Markov Model for Disease Progression Modeling
We solve the first challenge by reformulating the estimation problem as an equivalent discrete time-inhomogeneous hidden Markov model.
Unsupervised Few-Shot Action Recognition via Action-Appearance Aligned Meta-Adaptation
We present MetaUVFS as the first Unsupervised Meta-learning algorithm for Video Few-Shot action recognition.
Space Time Recurrent Memory Network
We propose a novel visual memory network architecture for the learning and inference problem in the spatial-temporal domain.
Counterfactual State Explanations for Reinforcement Learning Agents via Generative Deep Learning
Our second user study investigates if counterfactual state explanations can help non-expert participants identify a flawed agent; we compare against a baseline approach based on a nearest neighbor explanation which uses images from the actual game.
iGOS++: Integrated Gradient Optimized Saliency by Bilateral Perturbations
In this paper, we present iGOS++, a framework to generate saliency maps that are optimized for altering the output of the black-box system by either removing or preserving only a small fraction of the input.
Counterfactual States for Atari Agents via Generative Deep Learning
In this work, we introduce the concept of a counterfactual state to help humans gain a better understanding of what would need to change (minimally) in an Atari game image for the agent to choose a different action.
Interactive Naming for Explaining Deep Neural Networks: A Formative Study
For this purpose, we developed a user interface for "interactive naming," which allows a human annotator to manually cluster significant activation maps in a test set into meaningful groups called "visual concepts".
Open Set Learning with Counterfactual Images
In open set recognition, a classifier must label instances of known classes while detecting instances of unknown classes not encountered during training.
Multi-object Tracking with Neural Gating Using Bilinear LSTM
We also propose novel data augmentation approaches to efficiently train recurrent models that score object tracks on both appearance and motion.
Purely Geometric Scene Association and Retrieval - A Case for Macro Scale 3D Geometry
We show how it can be employed to select a diverse set of data frames which have structurally similar content, and how to validate whether views with similar geometric content are from the same scene.
The morphodynamics of 3D migrating cancer cells
As a result, cell morphodynamics is mapped into temporal evolution of morphological phenotypes.
Embedding Deep Networks into Visual Explanations
The XNN works by learning a nonlinear embedding of a high-dimensional activation vector of a deep network layer into a low-dimensional explanation space while retaining faithfulness i. e., the original deep learning predictions can be constructed from the few concepts extracted by our explanation network.
Boundary Flow: A Siamese Network that Predicts Boundary Motion without Training on Motion
Using deep learning, this paper addresses the problem of joint object boundary detection and boundary motion estimation in videos, which we named boundary flow estimation.
Adversarial Examples Detection in Deep Networks with Convolutional Filter Statistics
A cascade classifier was designed to efficiently detect adversarials.
A Continuous Optimization Approach for Efficient and Accurate Scene Flow
We propose a continuous optimization method for solving dense 3D scene flow problems from stereo imagery.
Multiple Hypothesis Tracking Revisited
This paper revisits the classical multiple hypotheses tracking (MHT) algorithm in a tracking-by-detection framework.
Efficient Learning of Continuous-Time Hidden Markov Models for Disease Progression
The Continuous-Time Hidden Markov Model (CT-HMM) is an attractive approach to modeling disease progression due to its ability to describe noisy observations arriving irregularly in time.
The Middle Child Problem: Revisiting Parametric Min-Cut and Seeds for Object Proposals
We propose a new energy minimization framework incorporating geodesic distances between segments which solves this problem.
Robust Video Segment Proposals With Painless Occlusion Handling
We propose a robust algorithm to generate video segment proposals.
GASP : Geometric Association with Surface Patches
A fundamental challenge to sensory processing tasks in perception and robotics is the problem of obtaining data associations across views.
RIGOR: Reusing Inference in Graph Cuts for Generating Object Regions
By precomputing a graph which can be used for parametric min-cuts over different seeds, we speed up the generation of the segment pool.
Composite Statistical Inference for Semantic Segmentation
In this paper we present an inference procedure for the semantic segmentation of images.
A Linear Approximation to the chi^2 Kernel with Geometric Convergence
We propose a new analytical approximation to the $\chi^2$ kernel that converges geometrically.
Beyond Sentiment: The Manifold of Human Emotions
Sentiment analysis predicts the presence of positive or negative emotions in a text document.
Convex Multiple-Instance Learning by Estimating Likelihood Ratio
In this work, we propose an approach that recasts it as a convex likelihood ratio estimation problem.
