Search Results for author:
Found 31 papers, 8 papers with code
Improving Multi-label Recognition using Class Co-Occurrence Probabilities
Multi-label Recognition (MLR) involves the identification of multiple objects within an image.
Piecewise-Linear Manifolds for Deep Metric Learning
For this purpose, we propose to model the high-dimensional data manifold using a piecewise-linear approximation, with each low-dimensional linear piece approximating the data manifold in a small neighborhood of a point.
Learning Implicit Representation for Reconstructing Articulated Objects
Our method simultaneously estimates the visible (explicit) representation (3D shapes, colors, camera parameters) and the implicit skeletal representation, from motion cues in the object video without 3D supervision.
CSL: Class-Agnostic Structure-Constrained Learning for Segmentation Including the Unseen
Addressing Out-Of-Distribution (OOD) Segmentation and Zero-Shot Semantic Segmentation (ZS3) is challenging, necessitating segmenting unseen classes.
Open-NeRF: Towards Open Vocabulary NeRF Decomposition
Current techniques for NeRF decomposition involve a trade-off between the flexibility of processing open-vocabulary queries and the accuracy of 3D segmentation.
Long-Distance Gesture Recognition using Dynamic Neural Networks
We demonstrate the performance of our method on the LD-ConGR long-distance dataset where it outperforms previous state-of-the-art methods on recognition accuracy and compute efficiency.
Learning Audio-Visual Dynamics Using Scene Graphs for Audio Source Separation
In this paper, we propose to use this connection between audio and visual dynamics for solving two challenging tasks simultaneously, namely: (i) separating audio sources from a mixture using visual cues, and (ii) predicting the 3D visual motion of a sounding source using its separated audio.
Tracking Grow-Finish Pigs Across Large Pens Using Multiple Cameras
We identify the adjacent camera and the shared pig location on the floor at the handover time using inter-view homography.
A Hierarchical Variational Neural Uncertainty Model for Stochastic Video Prediction
Predicting the future frames of a video is a challenging task, in part due to the underlying stochastic real-world phenomena.
Visual Scene Graphs for Audio Source Separation
At its core, AVSGS uses a recursive neural network that emits mutually-orthogonal sub-graph embeddings of the visual graph using multi-head attention.
Unsupervised 3D Pose Estimation for Hierarchical Dance Video Recognition
Dance experts often view dance as a hierarchy of information, spanning low-level (raw images, image sequences), mid-levels (human poses and bodypart movements), and high-level (dance genre).
Learning to Generate Videos Using Neural Uncertainty Priors
Predicting the future frames of a video is a challenging task, in part due to the underlying stochastic real-world phenomena.
Sound2Sight: Generating Visual Dynamics from Sound and Context
To tackle this problem, we present Sound2Sight, a deep variational framework, that is trained to learn a per frame stochastic prior conditioned on a joint embedding of audio and past frames.
Coreset-Based Neural Network Compression
We propose a novel Convolutional Neural Network (CNN) compression algorithm based on coreset representations of filters.
DeepMVS: Learning Multi-view Stereopsis
We present DeepMVS, a deep convolutional neural network (ConvNet) for multi-view stereo reconstruction.
Joint Image Filtering with Deep Convolutional Networks
In contrast to existing methods that consider only the guidance image, the proposed algorithm can selectively transfer salient structures that are consistent with both guidance and target images.
Tracking Persons-of-Interest via Unsupervised Representation Adaptation
Multi-face tracking in unconstrained videos is a challenging problem as faces of one person often appear drastically different in multiple shots due to significant variations in scale, pose, expression, illumination, and make-up.
Fast and Accurate Image Super-Resolution with Deep Laplacian Pyramid Networks
However, existing methods often require a large number of network parameters and entail heavy computational loads at runtime for generating high-accuracy super-resolution results.
Robust Visual Tracking Using Oblique Random Forests
Unlike conventional orthogonal decision trees that use a single feature and heuristic measures to obtain a split at each node, we propose to use a more powerful proximal SVM to obtain oblique hyperplanes to capture the geometric structure of the data better.
Deep Laplacian Pyramid Networks for Fast and Accurate Super-Resolution
Convolutional neural networks have recently demonstrated high-quality reconstruction for single-image super-resolution.
Ranked #40 on
Image Super-Resolution
on BSD100 - 4x upscaling
Detecting Migrating Birds at Night
In this paper, we present a vision-based system for detecting migrating birds in flight at night.
A Comparative Study for Single Image Blind Deblurring
Using these datasets, we conduct a large-scale user study to quantify the performance of several representative state-of-the-art blind deblurring algorithms.
Superpixel Hierarchy
Quantitative and qualitative evaluation on a number of computer vision applications was conducted, demonstrating that the proposed method is the top performer.
Uncovering Interactions and Interactors: Joint Estimation of Head, Body Orientation and F-Formations From Surveillance Videos
We present a novel approach for jointly estimating tar- gets' head, body orientations and conversational groups called F-formations from a distant social scene (e. g., a cocktail party captured by surveillance cameras).
On the Equivalence of Moving Entrance Pupil and Radial Distortion for Camera Calibration
Using a thick-lens setting, we show that such a back-projection is more accurate than the two-step method of undistorting an image pixel and then back-projecting it.
Single Image Super-Resolution From Transformed Self-Exemplars
However, the internal dictionary obtained from the given image may not always be sufficiently expressive to cover the textural appearance variations in the scene.
Structural Sparse Tracking
Sparse representation has been applied to visual tracking by finding the best target candidate with minimal reconstruction error by use of target templates.
Super-Resolving Noisy Images
We then show that by taking a convex combination of orientation and frequency selective bands of the noisy and the denoised HR images, we can obtain a desired HR image where (i) some of the textural signal lost in the denoising step is effectively recovered in the HR domain, and (ii) additional textures can be easily synthesized by appropriately constraining the parameters of the convex combination.
Generalized Pupil-Centric Imaging and Analytical Calibration for a Non-frontal Camera
The second approach based on decentering distortion modeling is approximate as it can only handle small tilts and cannot explicitly estimate the sensor tilt.
Robust Orthonormal Subspace Learning: Efficient Recovery of Corrupted Low-rank Matrices
Low-rank matrix recovery from a corrupted observation has many applications in computer vision.
Partial Occlusion Handling for Visual Tracking via Robust Part Matching
The proposed part matching tracker (PMT) has a number of attractive properties.
