19 datasets found

The PAVIS dataset contains RGB images of 79 people walking in an indoor scenario.

A person re-identification dataset using depth sensors.

A person re-identification dataset using RGB-D sensors.

MARS is an extension of the Market-1501 dataset [51]. It has been collected from six near-synchronized cameras. It consists of 1,261 different pedestrians, who are captured by...

Person re-identification using kernel-based metric learning methods

Video-based person re-identification (re-id) is a cen-

Person re-identification is challenging due to the large variations of pose, illumination, occlusion and camera view. Owing to these variations, the pedestrian data is...

Person re-identification (re-ID) under various occlusions has been a long-standing challenge as person images with different types of occlusions often suffer from misalign-ment...

Face recognition and person re-identification using paired image-attribute data, where the attributes (i.e., soft biometrics) are only available during the training phase.

The dataset used for experiments on generic image retrieval, person re-identification, and low-shot semantic segmentation.

The dataset used for tracking multiple people across multiple cameras is a large-scale multi-camera tracking dataset, DukeMTMC.

Person re-identification (ReID) aims to retrieve images of a specific person from different surveillance cameras.

The P-DukeMTMC-reID benchmark contains 12927 images of 665 person identities for training, including 2647 images with occlusion and 10280 images without occlusion.

Re-identification (Re-ID) problems aim to determine corresponding targets across multiple cameras or different locations in the same camera from the gallery set with a given probe.

The proposed method employs a divide-and-conquer strategy for the ReID task. Concretely, two self-supervision operations are used to generate new images with the characteristics...

The video-based person re-identification (ReID) aims to identify the given pedestrian video sequence across multiple non-overlapping cameras.

The video-based person re-identification (ReID) aims to identify the given pedestrian video sequence across multiple non-overlapping cameras.

The video-based person re-identification (ReID) aims to identify the given pedestrian video sequence across multiple non-overlapping cameras.

Face recognition and person re-identification using paired image-attribute data, where the attributes (i.e., soft biometrics) are only available during the training phase.