68 datasets found

The PartNet dataset is a large-scale benchmark for 3D object recognition and retrieval. It consists of 527 objects composed of 2690 parts, which can be composited into a...

The dataset used in this paper for multi-sensor next-best-view planning as matroid-constrained submodular maximization.

The Small-NORB dataset is a dataset of 4,000 images of 6 classes, each class containing 60 images of size 16x16.

The dataset used in the paper is CIFAR10-DVS, a dataset of 10,000 event streams of 128x128 images.

The MiniImagenet dataset is a benchmark for few-shot learning, consisting of 60,000 images from 21 classes, each with 300 images.

The authors propose a novel coordinate transform that normalizes the image coordinates of the events by the timestamp of each event.

The event-based camera is a bio-inspired camera that captures the change of logarithmic light intensity of an image. The authors propose a novel coordinate transform that...

Sketchy is a large collection of sketch-photo pairs. The dataset consists of images from 125 different classes, with 100 photos each.

The PoseCNN dataset is a dataset for 6D object pose estimation in cluttered scenes.

The authors created a custom dataset for their experiment, consisting of 33,000 images of 320 possible object-image combinations, with 10 possible shapes, 8 possible colors, 2...

The Caltech-256 object category dataset is used for the feature extraction step, and the Omniglot dataset is used for the evaluation.

Shapenet is a large-scale synthesis 3D object dataset, where we follow [9] to use the official test splits of chair, car, and motorbike categories for evaluation since they...

Zero-shot learning (ZSL) aims to classify objects that are not observed or seen during training. It relies on class semantic description to transfer knowledge from the seen...

3D shape datasets for active object recognition

The Pix3D dataset is a collection of 3D models with RGB images, used for training and testing 3D object recognition and generation tasks.

Food-101 dataset is a large-scale dataset for food image classification, with 101 classes and over 30,000 images.

The N-Caltech 101 dataset is an event-based object recognition dataset generated from the Caltech 101 object recognition dataset.

N-Caltech101 is a widely used event-based object recognition dataset.

N-ImageNet is a large-scale dataset containing 1,781,167 event stream data of 1,000 object classes.

Recognizing objects from sparse and noisy events becomes extremely difficult when paired images and category labels do not exist. This paper proposes a joint formulation of...