Person Identification

A large dataset of human hand images (dorsal and palmar sides) with detailed ground-truth information for gender recognition and biometric identification. Source: 11K Hands: Gender recognition and biometric identification using a large dataset of hand images

iQIYI-VID dataset, which comprises video clips from iQIYI variety shows, films, and television dramas. The whole dataset contains 500,000 videos clips of 5,000 celebrities. The length of each video is 1~30 seconds. Source: iQIYI-VID

WiGesture dataset contains data related to gesture recognition and people id identification in a meeting room scenario. The dataset provides synchronised CSI, RSSI, and timestamp for each sample. It can be used for research on WiFi-based human gesture recognition and people id identification.

This data set consists of over 1500 one- and two-minute EEG recordings, obtained from 109 volunteers.

NVSA is a large-scale NBA dataset for Sports Video Analysis (NSVA) with a focus on sports video captioning. This dataset consists of more than 32K video clips and it is also designed to address two additional tasks, namely fine-grained sports action recognition and salient player identification.

WiFall dataset contains data related to fall detection, action recognition and people id identification in a meeting room scenario. The dataset provides synchronised CSI, RSSI, and timestamp for each sample.

Dataset (part 1/3) for Motion Patterns Identification part of MotionID: Human Authentication Approach. Data type: bin (should be converted by attached notebook). Six users each with a Samsung Galaxy S10e smartphone collected IMU data every day for 2 weeks. At the end of two weeks, the users switched smartphones with each other and restarted the process. Each user spent 2 weeks per smartphone during the whole data collection process, which took 12 weeks in total. Throughout the experiment, the Galaxy S10e was the main and only device of each user. The smartphones were used habitually and ordinarily, with the only difference from real-life scenarios being that the data collection app was always on. Each measurement has a corresponding timestamp. Screen.txt file consists of timestamps with current status of device: 1) SCREEN_OFF - a phone turned off 2) SCREEN_ON - a phone is on 3) USER_PRESENT - a phone has just been unlocked

Dataset (part 2/3) for Motion Patterns Identification part of MotionID: Human Authentication Approach. Data type: bin (should be converted by attached notebook). Six users each with a Samsung Galaxy S10e smartphone collected IMU data every day for 2 weeks. At the end of two weeks, the users switched smartphones with each other and restarted the process. Each user spent 2 weeks per smartphone during the whole data collection process, which took 12 weeks in total. Throughout the experiment, the Galaxy S10e was the main and only device of each user. The smartphones were used habitually and ordinarily, with the only difference from real-life scenarios being that the data collection app was always on. Each measurement has a corresponding timestamp. Screen.txt file consists of timestamps with current status of device: 1) SCREEN_OFF - a phone turned off 2) SCREEN_ON - a phone is on 3) USER_PRESENT - a phone has just been unlocked

Dataset (part 3/3) for Motion Patterns Identification part of MotionID: Human Authentication Approach. Data type: bin (should be converted by attached notebook). Six users each with a Samsung Galaxy S10e smartphone collected IMU data every day for 2 weeks. At the end of two weeks, the users switched smartphones with each other and restarted the process. Each user spent 2 weeks per smartphone during the whole data collection process, which took 12 weeks in total. Throughout the experiment, the Galaxy S10e was the main and only device of each user. The smartphones were used habitually and ordinarily, with the only difference from real-life scenarios being that the data collection app was always on. Each measurement has a corresponding timestamp. Screen.txt file consists of timestamps with current status of device: 1) SCREEN_OFF - a phone turned off 2) SCREEN_ON - a phone is on 3) USER_PRESENT - a phone has just been unlocked

Dataset for User Verification part of MotionID: Human Authentication Approach. Data type: bin (should be converted by attached notebook). ~50 hours of IMU (Inertial Measurement Units) data for one specific motion pattern, provided by 101 users. For data collection only one smartphone (Samsung Galaxy S20) was used. The data was collected by 101 users, each of whom lifted the smartphone from the table 300 times, 50 times for each of the 6 locations of the device (see picture below). The data collection procedure for user verification was as follows: 1) The user lifts the locked smartphone from the table surface to a comfortable level 2) The user unlocks the smartphone via an in-display ultrasonic fingerprint sensor 3) The user locks the smartphone via Home button and puts the device 4) The cycle is repeated for 50 times at each location, for a total of 300 times per person Each measurement has a corresponding timestamp. Screen.txt file consists of timestamps with current status of device: 1) SCREEN_OFF - a phone turned off 2) SCREEN_ON - a phone is on 3) USER_PRESENT - a phone has just been unlocked