
-
Betrayed by Motion: Camouflaged Object Discovery via Motion Segmentation
The objective of this paper is to design a computational architecture th...
read it
-
Self-supervised Co-training for Video Representation Learning
The objective of this paper is visual-only self-supervised video represe...
read it
-
Layered Neural Rendering for Retiming People in Video
We present a method for retiming people in an ordinary, natural video—ma...
read it
-
Inducing Predictive Uncertainty Estimation for Face Recognition
Knowing when an output can be trusted is critical for reliably using fac...
read it
-
Memory-augmented Dense Predictive Coding for Video Representation Learning
The objective of this paper is self-supervised learning from video, in p...
read it
-
Self-supervised Video Object Segmentation
The objective of this paper is self-supervised representation learning, ...
read it
-
VGGSound: A Large-scale Audio-Visual Dataset
Our goal is to collect a large-scale audio-visual dataset with low label...
read it
-
MAST: A Memory-Augmented Self-supervised Tracker
Recent interest in self-supervised dense tracking has yielded rapid prog...
read it
-
VoxSRC 2019: The first VoxCeleb Speaker Recognition Challenge
The VoxCeleb Speaker Recognition Challenge 2019 aimed to assess how well...
read it
-
Video Representation Learning by Dense Predictive Coding
The objective of this paper is self-supervised learning of spatio-tempor...
read it
-
Geometry-Aware Video Object Detection for Static Cameras
In this paper we propose a geometry-aware model for video object detecti...
read it
-
AutoCorrect: Deep Inductive Alignment of Noisy Geometric Annotations
We propose AutoCorrect, a method to automatically learn object-annotatio...
read it
-
Self-supervised Learning for Video Correspondence Flow
The objective of this paper is self-supervised learning of feature embed...
read it
-
Utterance-level Aggregation For Speaker Recognition In The Wild
The objective of this paper is speaker recognition "in the wild"-where u...
read it
-
Class-Agnostic Counting
Nearly all existing counting methods are designed for a specific object ...
read it
-
Comparator Networks
The objective of this work is set-based verification, e.g. to decide if ...
read it
-
Multicolumn Networks for Face Recognition
The objective of this work is set-based face recognition, i.e. to decide...
read it
-
Omega-Net: Fully Automatic, Multi-View Cardiac MR Detection, Orientation, and Segmentation with Deep Neural Networks
Pixelwise segmentation of the left ventricular (LV) myocardium and the f...
read it
-
VGGFace2: A dataset for recognising faces across pose and age
In this paper, we introduce a new large-scale face dataset named VGGFace...
read it
-
Freehand Ultrasound Image Simulation with Spatially-Conditioned Generative Adversarial Networks
Sonography synthesis has a wide range of applications, including medical...
read it