Top AI Repos — open-source AI, indexed and scored
Top AI Repos tracks AI repositories on GitHub and answers two different questions about each one: is it moving right now, and would you bet a product on it.
Top AI Repos tracks AI repositories on GitHub and answers two different questions about each one: is it moving right now, and would you bet a product on it.
Dataset and code for the paper "First-Person Hand Action Benchmark with RGB-D Videos and 3D Hand Pose Annotations", CVPR 2018.
| Date | Stars |
|---|---|
| 2026-07-24 | 271 |
| 2026-07-25 | 271 |
| 2026-07-28 | 271 |
| 2026-07-30 | 271 |
| 2026-08-06 | 271 |
Today
— stars today
This week
— stars this week
This month
— stars this month
Momentum
0.0
growth rate 0.00%/day
## First-Person Hand Action Benchmark with RGB-D Videos and 3D Hand Pose Annotations This repository contains instructions on getting the data and code of the work `First-Person Hand Action Benchmark with RGB-D Videos and 3D Hand Pose Annotations` presented at CVPR 2018. For more information on the benchmark please check out [[1]](#refs). ### Downloading the data Please fill this [form](https://goo.gl/forms/FIsXpYVIUov0j7Wv2) to download the dataset after reading the [terms and conditions](#terms). ### Dataset structure: The dataset is organized as the following example: - File `Video_files/Subject_1/put_salt/1/color/color_0015.jpeg` Consists of frame number 15 of the color stream of the 1st repetition of action class "put salt" by subject number 1. - File `Video_files/Subject_1/put_salt/1/depth/depth_0015.png` CConsists of frame number 15 of the depth stream of the 1st repetition of action class "put salt" by subject number 1. - File `Hand_pose_annotation_v1_1/Subject_1/put_salt/1/skeleton.txt` Contains the hand pose (in world coordinates) for the sequence: repetition 1 of action class "put salt" by subject number 1. - File `Object_6D_pose_annotation_v1/Subject_1/put_salt/1/object_pose.txt` Contains the 6D object pose for the sequence: repetition 1 of action class "put salt" by subject number 1. Comment: Check Figure 3 and 4 of the paper to learn about action categories. We used a slightly different nomenclature for some actions compared to the paper. These are: "dish soap -> liquid soap"; "read paper -> read letter"; "use spray -> use flash". Note: Check `Subjects_info` folder for details on number of sequences, frames, etc. for each subject. The following sequences can be ignored (they were not used in the paper): 'Subject_2/close_milk/4', 'Subject_2/put_tea_bag/2' and 'Subject_4/flip_sponge/2'. ### Image data details * Camera: Intel RealSense SR300. * Color data: 1920x1080 32bit, jpeg format. * Depth data: 640x480 16bit, png format. ### Hand pose data: Format of each line of skeleton.txt: `t x_1 y_1 z_1 x_2 y_2 z_2 ... x_21 y_21 z_21` where `t` is the frame number and `x_i y_i z_i` are the world coordinates (in mm) of joint `i` at frame `t`. Hand joints are organised as follows: `[Wrist, TMCP, IMCP, MMCP, RMCP, PMCP, TPIP, TDIP, TTIP, IPIP, IDIP, ITIP, MPIP, MDIP, MTIP, RPIP, RDIP, RTIP, PPIP, PDIP, PTIP]`, where ’T’, ’I’, ’M’, ’R’, ’P’ denote ’Thumb’, ’Index’, ’Middle’, ’Ring’, ’Pinky’ fingers. <img src="hand_model.png" alt="hand_model" width="400" class="center"/> Check out the scripts `load_example.x` (.py for Python and .m for Matlab) for examples on how to visualise the hand pose on both color and depth images. **Updated 20/02/2019**: We also provide action sequences with normalized hand poses. Normalization of hand poses is essential to replicate the action recognition results on the paper. It's briefly mentioned on the paper, but if you want to normalize the hand poses you will need to: compute average distance among subjects between joints, normalize the distance between joints to have the same distance on every frame and subject, make the wrist the origin of coordinates for each frame and (optional but helps) align the wrist with one of the axis by rotating the 3D skeleton. ### Object pose data: Available objects: 'juice carton', 'milk bottle', 'salt' and 'liquid soap'. Format of each line of object_pose.txt: `t M11 M21 M31 M41 M12 ... Mij... M44` where `Mij` is the element of the transformation matrix `M` at row `i` and column `j`. Check the Python code `load_example.py` to see an example on how to visualise the object model for a given pose on top of the image. ### Object models Available objects: 'juice carton', 'milk bottle', 'salt' and 'liquid soap'. Format [.PLY](https://en.wikipedia.org/wiki/PLY_(file_format)). Each object comes with a texture file `texture.jpg`. Coordinates are in meters (in contrast to mm for hand poses). Juice carton and milk bottle objects also appear
Excerpt of 7,225 characters
Read on GitHubWould you bet a product on this? Bounded 0–100 and slow moving.
matched fp:62b3ffc6a5df5bcd, topic:dataset, desc:dataset, readme:dataset
matched fp:62b3ffc6a5df5bcd, topic:computer-vision
matched fp:62b3ffc6a5df5bcd, topic:benchmark