-
A Deep Neural Network for Multiclass Bridge Element Parsing in Inspection Ima...
Aerial robots such as drones have been leveraged to perform bridge inspections. Inspection images with both recognizable structural elements and apparent surface defects can be... -
Object Tracking Benchmark
The OTB100 dataset is an extension of the OTB50 dataset, containing 100 videos with 1000 frames each. -
VIGOR dataset
The VIGOR dataset contains images of buildings and streets from different angles and lighting conditions. -
Stanford-Cars, Oxford-Flowers102, Oxford-IIIT Pets, FGVC Aircraft, CIFAR-10 d...
Stanford-Cars, Oxford-Flowers102, Oxford-IIIT Pets, FGVC Aircraft, CIFAR-10 datasets. -
Tied-Augment: Controlling Representation Similarity Improves Data Augmentation
Data augmentation methods have played an important role in the recent advance of deep learning models, and have become an indispensable component of state-of-the-art models in... -
MnasNet: Platform-Aware Neural Architecture Search for Mobile
Designing convolutional neural networks (CNN) for mobile devices is challenging because mobile models need to be small and fast, yet still accurate. Although significant efforts... -
ARS: Augmented Reality Semi-automatic-labeling
Two novel datasets are created using the ARS pipeline, one on electromechanical components (industrial scenario) and one on fruits (daily-living scenario). -
Transform Quantization for CNN Compression
The dataset used in this paper is a collection of convolutional neural network (CNN) weights, which are compressed using transform quantization. -
Engineering the Neural Collapse Geometry of Supervised-Contrastive Loss
Supervised-contrastive loss (SCL) is an alternative to cross-entropy (CE) for classification tasks that makes use of similarities in the embedding space to allow for richer... -
Automated Deep Photo Style Transfer
Photorealism is a complex concept that cannot easily be formulated mathematically. Deep Photo Style Transfer is an attempt to transfer the style of a reference image to a... -
HMDB51-DVS
A neuromorphic vision sensing (NVS) device represents visual information as sequences of asynchronous discrete events (a.k.a., “spikes”) in response to changes in scene... -
UCF101-DVS
A neuromorphic vision sensing (NVS) device represents visual information as sequences of asynchronous discrete events (a.k.a., “spikes”) in response to changes in scene... -
Graph-based Spatial-temporal Feature Learning for Neuromorphic Vision Sensing
A neuromorphic vision sensing (NVS) device represents visual information as sequences of asynchronous discrete events (a.k.a., “spikes”) in response to changes in scene... -
Cross-view image geolocalization
Cross-view image geolocalization. -
Localizing and orienting street views using overhead imagery
Localizing and orienting street views using overhead imagery. -
Cross-View Image Synthesis
Cross-view image synthesis aims to translate images between two distinct views, such as synthesizing ground images from aerial images, and vice versa. -
NYUv2 dataset
The NYUv2 dataset is a large-scale dataset for 3D object recognition and semantic segmentation. It contains 206 test set video sequences with 135 classes. -
Strike (with) a Pose: Neural Networks Are Easily Fooled by Strange Poses of F...
The dataset used in the paper Strike (with) a Pose: Neural Networks Are Easily Fooled by Strange Poses of Familiar Objects. The dataset consists of 30 unique 3D object models...
