Search Results for author:
Found 16 papers, 5 papers with code
A Benchmark Grocery Dataset of Realworld Point Clouds From Single View
Existing datasets on groceries are mainly 2D images.
Improving Normalization with the James-Stein Estimator
In this paper, first, we establish that normalization layers in deep learning use inadmissible estimators for mean and variance.
SODAWideNet -- Salient Object Detection with an Attention augmented Wide Encoder Decoder network without ImageNet pre-training
To achieve a shallower network, we increase the receptive field from the beginning of the network using a combination of dilated convolutions and self-attention.
Sentence Attention Blocks for Answer Grounding
We visually demonstrate how this block filters out irrelevant feature-maps channels based on sentence embedding.
Empowering Visually Impaired Individuals: A Novel Use of Apple Live Photos and Android Motion Photos
Our findings reveal that both Live Photos and Motion Photos outperform single-frame images in common visual assisting tasks, specifically in object classification and VideoQA.
Local Neighborhood Features for 3D Classification
We train and evaluate PointNeXt on ModelNet40 (synthetic), ScanObjectNN (real-world), and a recent large-scale, real-world grocery dataset, i. e., 3DGrocery100.
Ranked #21 on
3D Point Cloud Classification
on ScanObjectNN
Semantic Segmentation using Neural Ordinary Differential Equations
The idea of neural Ordinary Differential Equations (ODE) is to approximate the derivative of a function (data model) instead of the function itself.
SimpleView++: Neighborhood Views for Point Cloud Classification
Among these methods, the Simple View model demonstrates that features from six orthogonal perspective projections of a point cloud achieved comparable 3D classification.
Ranked #42 on
3D Point Cloud Classification
on ScanObjectNN
AIM: An Auto-Augmenter for Images and Meshes
Data augmentations are commonly used to increase the robustness of deep neural networks.
Dynamic Local Geometry Capture in 3D PointCloud Classification
We propose a novel technique of dynamically oriented and scaled ellipsoid based on unique local information to capture the local geometry better.
Ranked #53 on
3D Point Cloud Classification
on ScanObjectNN
PatchAugment: Local Neighborhood Augmentation in Point Cloud Classification
Methods using 3D datasets are among the most common to use data augmentation techniques such as random point drop, scaling, translation, rotations, and jittering.
Ranked #54 on
3D Point Cloud Classification
on ScanObjectNN
Learning Dense Stereo Matching for Digital Surface Models from Satellite Imagery
Digital Surface Model generation from satellite imagery is a difficult task that has been largely overlooked by the deep learning community.
CATS: A Color and Thermal Stereo Benchmark
We present the Color And Thermal Stereo (CATS) benchmark, a dataset consisting of stereo thermal, stereo color, and cross-modality image pairs with high accuracy ground truth (< 2mm) generated from a LiDAR.
Robust Shape Registration using Fuzzy Correspondences
We present a shape registration approach that solves for the transformation using fuzzy correspondences to maximize the overlap between the given shape and the target shape.
Localize Me Anywhere, Anytime: A Multi-Task Point-Retrieval Approach
The main contribution of our paper is that we use a 3D model reconstructed by a short video as the query to realize 3D-to-3D localization under a multi-task point retrieval framework.
Material Classification With Thermal Imagery
Typical algorithms use color and texture information for classification, but there are problems due to varying lighting conditions and diversity of colors in a single material class.
