482 datasets found

MS-COCO 2017 dataset is used for evaluating the performance of object detection models.

G-CAME is a method to explain object detection models using Gaussian Class Activation Mapping Explainer.

The T-Less dataset is used for testing the class-adaptive object detector. It contains 15 objects with a large number of occurrences.

The HomeBrew dataset is used for testing the class-adaptive object detector. It contains 30 objects with a large number of occurrences.

The YCB-V dataset is used for testing the class-adaptive object detector. It contains 33 objects with a large number of occurrences.

The FewSol dataset is used for training the class-adaptive object detector. It contains 666 objects with a large number of occurrences.

The DoPose and HOPE datasets are used for testing the class-adaptive object detector. The DoPose dataset contains 18 objects with distinctive shapes and colors, while the HOPE...

Selective search is a method for object detection.

Deeply Supervised Object Detector (DSOD) is a framework that can learn object detectors from scratch.

Person search unifies person detection and person re-identification (Re-ID) to locate query persons from the panoramic gallery images. One major challenge comes from the...

CUHK-SYSU is a large-scale dataset designed for person search, which contains 18,184 scene images captured from street nap and movie screenshot.

The ADL Dataset is a public dataset used for object detection in wearable videos. It contains 27000 frames extracted from 10 hours of video recorded with a chest-mounted GoPro...

Few-shot object detection aims at learning a detector that can fast adapt to previously unseen objects with scarce annotated examples, which is challenging and demanding.

Propose-and-attend single shot detector for object detection

The OpenImagesV4 dataset is a large benchmark dataset for object detection and image classification. It contains 1.7 million images with 1,000 object classes.

The dataset used in the paper is a video prediction dataset with occlusions, which is used to evaluate the proposed Fast Fourier Inception Networks (FFINet) for occluded video...

The dataset used for object detection on limited datasets

FoveaBox is a completely anchor-free framework for generic object detection. It directly predicts the object existing possibility and the corresponding boundary for each...

The dataset used in the paper is a synthetic dataset for blind super-resolution, consisting of low-resolution images and their corresponding blur kernels.

The internal dataset contains 6 million real-world driving scenarios from Las Vegas (LV), Seattle (SEA), San Francisco (SF), and the campus of the Stanford Linear Accelerator...