
Invertible Attention
Attention has been proved to be an efficient mechanism to capture longr...
read it

One Ring to Rule Them All: a simple solution to multiview 3DReconstruction of shapes with unknown BRDF via a small Recurrent ResNet
This paper proposes a simple method which solves an open problem of mult...
read it

Learning to Estimate Hidden Motions with Global Motion Aggregation
Occlusions pose a significant challenge to optical flow algorithms that ...
read it

Learning Optical Flow from a Few Matches
Stateoftheart neural network models for optical flow estimation requi...
read it

Fewshot WeaklySupervised Object Detection via Directional Statistics
Detecting novel objects from few examples has become an emerging topic i...
read it

UncertaintyAware Deep Calibrated Salient Object Detection
Existing deep neural network based salient object detection (SOD) method...
read it

Dual Pixel Exploration: Simultaneous Depth Estimation and Image Restoration
The dualpixel (DP) hardware works by splitting each pixel in half and c...
read it

Deep Learning Superpixel Semantic Segmentation with Transparent Initialization and Sparse Encoder
Even though deep learning greatly improves the performance of semantic s...
read it

RANP: Resource Aware Neuron Pruning at Initialization for 3D CNNs
Although 3D Convolutional Neural Networks (CNNs) are essential for most ...
read it

Posthoc Calibration of Neural Networks
Calibration of neural networks is a critical aspect to consider when inc...
read it

Calibration of Neural Networks using Splines
Calibrating neural networks is of utmost importance when employing them ...
read it

Single Image Optical Flow Estimation with an Event Camera
Event cameras are bioinspired sensors that asynchronously report intens...
read it

In Defense of Graph Inference Algorithms for Weakly Supervised Object Localization
Weakly Supervised Object Localization (WSOL) methods have become increas...
read it

Intra Orderpreserving Functions for Calibration of MultiClass Neural Networks
Predicting calibrated confidence scores for multiclass deep networks is...
read it

Joint Unsupervised Learning of Optical Flow and Egomotion with BiLevel Optimization
We address the problem of joint optical flow and camera motion estimatio...
read it

Action Anticipation with RBF Kernelized Feature Mapping RNN
We introduce a novel Recurrent Neural Networkbased algorithm for future...
read it

Action Anticipation with RBF KernelizedFeature Mapping RNN
We introduce a novel Recurrent Neural Networkbased algorithm for future...
read it

Fast and Differentiable Message Passing for Stereo Vision
Despite the availability of many Markov Random Field (MRF) optimization ...
read it

Mirror Descent View for Neural Network Quantization
Quantizing large Neural Networks (NN) while maintaining the performance ...
read it

CullNet: Calibrated and Pose Aware Confidence Scores for Object Pose Estimation
We present a new approach for a single view, imagebased object pose est...
read it

Exploiting Geometric Constraints on Dense Trajectories for Motion Saliency
The existing approaches for salient motion segmentation are unable to ex...
read it

Deep Declarative Networks: A New Hope
We introduce a new class of endtoend learnable models wherein data pro...
read it

Learning to Find Common Objects Across Image Collections
We address the problem of finding a set of images containing a common, b...
read it

Recovering Faces from Portraits with Auxiliary Facial Attributes
Recovering a photorealistic face from an artistic portrait is a challeng...
read it

Identitypreserving Face Recovery from Stylized Portraits
Given an artistic portrait, recovering the latent photorealistic face th...
read it

Bringing Blurry Alive at High FrameRate with an Event Camera
Eventbased cameras can measure intensity changes (called ` events') wit...
read it

SuperTrajectories: A Compact Yet Rich Video Representation
We propose a new video representation in terms of an oversegmentation o...
read it

Proximal Meanfield for Neural Network Quantization
Compressing large neural networks by quantizing the parameters, while ma...
read it

Phaseonly Image Based Kernel Estimation for Singleimage Blind Deblurring
The image blurring process is generally modelled as the convolution of a...
read it

Bringing a Blurry Frame Alive at High FrameRate with an Event Camera
Eventbased cameras can measure intensity changes (called ` events') wit...
read it

Generalized Range Moves
We consider movemaking algorithms for energy minimization of multilabe...
read it

Scalable Deep kSubspace Clustering
Subspace clustering algorithms are notorious for their scalability issue...
read it

Block Mean Approximation for Efficient Second Order Optimization
Advanced optimization algorithms such as Newton method and AdaGrad benef...
read it

Deep Unsupervised Saliency Detection: A Multiple Noisy Labeling Perspective
The success of current deep saliency detection methods heavily depends o...
read it

NonLinear Temporal Subspace Representations for Activity Recognition
Representations that can compactly and effectively capture the temporal ...
read it

Identitypreserving Face Recovery from Portraits
Recovering the latent photorealistic faces from their artistic portraits...
read it

Sequence Summarization Using Orderconstrained Kernelized Feature Subspaces
Representations that can compactly and effectively capture temporal evol...
read it

Dimensionality Reduction on SPD Manifolds: The Emergence of GeometryAware Methods
Representing images and videos with Symmetric Positive Definite (SPD) ma...
read it

MultiTarget Tracking with TimeVarying Clutter Rate and Detection Profile: Application to Timelapse Cell Microscopy Sequences
Quantitative analysis of the dynamics of tiny cellular and subcellular ...
read it

Optimizing Over Radial Kernels on Compact Manifolds
We tackle the problem of optimizing over all possible positive definite ...
read it

Kernel Methods on the Riemannian Manifold of Symmetric Positive Definite Matrices
Symmetric Positive Definite (SPD) matrices have become popular to encode...
read it

Kernel Methods on Riemannian Manifolds with Gaussian RBF Kernels
In this paper, we develop an approach to exploiting kernel methods with ...
read it

Iteratively Reweighted Graph Cut for Multilabel MRFs with Nonconvex Priors
While widely acknowledged as highly effective in computer vision, multi...
read it

Sparse Coding on Symmetric Positive Definite Manifolds using Bregman Divergences
This paper introduces sparse coding and dictionary learning for Symmetri...
read it

Expanding the Family of Grassmannian Kernels: An Embedding Perspective
Modeling videos and imagesets as linear subspaces has proven beneficial...
read it

From Manifold to Manifold: GeometryAware Dimensionality Reduction for SPD Matrices
Representing images and videos with Symmetric Positive Definite (SPD) ma...
read it

Extrinsic Methods for Coding and Dictionary Learning on Grassmann Manifolds
Sparsitybased representations have recently led to notable results in v...
read it

Sparse Coding and Dictionary Learning for Symmetric Positive Definite Matrices: A Kernel Approach
Recent advances suggest that a wide range of computer vision problems ca...
read it

Effective Pedestrian Detection Using Centersymmetric Local Binary/Trinary Patterns
Accurately detecting pedestrians in images plays a critically important ...
read it
Richard Hartley
verfied profile
Professor at Australian National University