62 datasets found

The FSC147 dataset is a large-scale dataset for evaluating class-agnostic counting (CAC) models. It contains 6,135 natural images of 147 object categories.

Multi-label image recognition is a practical and challenging task compared to single-label image classification.

The TrackingNet dataset is a benchmark for visual tracking, containing 511 video sequences with varying difficulties.

The NFS30 dataset contains 100 videos and a length of 380K frames in total.

The RefCOCOg dataset is a reconstructed dataset of the MS-COCO dataset, containing 85,474 referring expressions for 54,822 objects in 26,711 images.

The dataset used in the paper is a benchmark for referring expression grounding, containing 142,210 referring expressions for 50,000 referents in 19,994 images.

ILSVRC is a large-scale image dataset containing over 1.2 million images across 1,000 classes.

The Objects365 dataset is a large-scale object detection dataset containing 365,000 images with 365 categories.

ShanghaiTech Part A is a crowd counting dataset that contains 300 training images and 182 test images.

The dataset used in this paper is a ResNet50 model, which is a convolutional neural network. The model is used to evaluate the effects of quantization on the compute...

The LaSOT dataset is a large-scale benchmark for visual tracking, containing 1400 video sequences with varying difficulties.

The UAV123 dataset is a benchmark for visual tracking, containing 123 video sequences with varying difficulties.

Semantic segmentation is a crucial and challenging task for image understanding. It aims to predict a dense labeling map for the input image, which assigns each pixel a unique...

Large-scale vision-and-language models trained on curated and web-scrapped data have led to significant improvements over task-specific models when transferred to downstream...

Large scale datasets [18, 17, 27, 6] boosted text conditional image generation quality. However, in some domains it could be difficult to make such datasets and usually it could...

The dataset used for training and validation of the proposed approach to combine semantic segmentation and dense outlier detection.

The Cityscapes dataset is a large and famous city street scene semantic segmentation dataset. 19 classes of which 30 classes of this dataset are considered for training and...

The dataset used in the paper is the KITTI dataset, which is a benchmark for monocular depth estimation. The dataset consists of a large collection of images and corresponding...

The Microsoft COCO dataset was used for training and evaluating the CNNs because it has become a standard benchmark for testing algorithms aimed at scene understanding and...

A benchmark for low-shot recognition was proposed by Hariharan & Girshick (2017) and consists of a representation learning phase without access to the low-shot classes and a...