{"success":true,"data":{"author":"Botao He, Zhi Wang, Linna Kuang, Ishaan Ghosh, Jitendra Malik, Cornelia Fermuller et al.","bucketAccessType":"public","bucketName":"boootaooo/forceband-emg2force","bucketPrefix":"","category":"Physiology","cloudProvider":"huggingface","createdAt":"2026-11-22T01:09:18.670Z","description":"The pretraining data of the EMG2Force model from ForceBand: Learning Forceful Manipulation with sEMG (He, Wang, Kuang, Ghosh, Malik, Fermuller and colleagues, arXiv:2606.26093). A wrist band records 8-channel surface electromyography (sEMG) and a 10-channel inertial measurement unit (IMU: orientation quaternion, gyroscope and accelerometer) together with fingertip force for each of the five fingers, all at 1 kHz; RGB video from one or more cameras is synchronized by per-frame timestamps. The release has 53 recordings from October 2025 to April 2026, 8.61 hours of cleaned EMG, IMU and force (8.39 hours valid), 6.37 hours of it with video, about 7.7 GB. Each segment folder holds timeseries.hdf5 (timestamps, emg, imu, force, validity masks, trial and task indices) plus H.264 MP4 video and frame timestamps; manifest.csv, recording_log.csv and summary.json index the segments. Load with h5py and huggingface_hub. Uses: regressing grip and finger force from forearm muscle activity, EMG-based hand interfaces, and teaching robots forceful manipulation from human demonstrations. Video shows participants' faces. The authors state the dataset is released under Apache-2.0, the same as the ForceBand code (LICENSE file in the repository). Cite He et al., ForceBand, 2026.","displayTitle":"ForceBand EMG2Force: Wrist Surface EMG and IMU with Per-Finger Fingertip Force and RGB Video (He, Malik et al.)","huggingFaceUrl":"https://huggingface.co/datasets/boootaooo/forceband-emg2force","id":"d364f67f-6d74-5a96-8bd3-17efcdbcf7e8","license":"Apache-2.0","licenseEvidenceUrl":"https://huggingface.co/datasets/boootaooo/forceband-emg2force","objectCountEstimate":253,"probeStatus":"ok","referenceUrl":"https://arxiv.org/abs/2606.26093","region":"us","schemaCard":{"accessHints":[{"language":"python-datasets","snippet":"from datasets import load_dataset\nds = load_dataset(\"boootaooo/forceband-emg2force\")"},{"language":"python-hub","snippet":"from huggingface_hub import snapshot_download\nsnapshot_download(repo_id=\"boootaooo/forceband-emg2force\", repo_type=\"dataset\")"}],"caveats":["HuggingFace metadata: author=boootaooo, license:apache-2.0, size_categories:n<1K, format:csv, downloads=1300"],"format":"mixed","generatedAt":"2026-11-22T01:10:18.891Z","layout":{"example":"manifest.csv","pattern":"{repoId}/{filename}"},"mountPath":"/mnt/archive","sampleHeaders":[{"bytes":"segment,recording,date,start_utc,kind,collection,duration_s,trial_s,gap_real_s,gap_held_s,valid_s,invalid_s,invalid_emg_s,invalid_force_s,invalid_imu_s,n_tasks,n_trials,force_tared_fingers,video_cameras,video_frames,video_span_s,emg_source,source_bag,validation\r\n2025-10-12-17-53-25,2025-10-12-17-53-25,2025-10-12,2025-10-12 21:53:32,continuous (unlogged bag),unlogged_paired/1012,90.68,90.679,0.001,0.0,90.633,0.047,0.047,0.0,0.0,1,1,thumb,camera,2719,90.68,unlogged_paired/1012/2025-10-12-17-53-25/emg/OpenBCI-","encoding":"utf8","key":"manifest.csv","truncatedAt":512}],"sampleObjects":["manifest.csv","recording_log.csv","recording_log.txt","segments/2025-10-12-17-53-25/meta.json","segments/2025-10-12-17-53-25/rgb_camera.mp4"],"sidecars":[{"bytes":"\n                                 Apache License\n                           Version 2.0, January 2004\n                        http://www.apache.org/licenses/\n\n   TERMS AND CONDITIONS FOR USE, REPRODUCTION, AND DISTRIBUTION\n\n   1. Definitions.\n\n      \"License\" shall mean the terms and conditions for use, reproduction,\n      and distribution as defined by Sections 1 through 9 of this document.\n\n      \"Licensor\" shall mean the copyright owner or entity authorized by\n      the copyright owner that is granting the License.\n\n      \"Legal Entity\" shall mean the union of the acting entity and all\n      other entities that control, are controlled by, or are under common\n      control with that entity. For the purposes of this definition,\n      \"control\" means (i) the power, direct or indirect, to cause the\n      direction or management of such entity, whether by contract or\n      otherwise, or (ii) ownership of fifty percent (50%) or more of the\n      outstanding shares, or (iii) beneficial ownership of such entity.\n\n      \"You\" (or \"Your\") shall mean an individual or Legal Entity\n      exercising permissions granted by this License.\n\n      \"Source\" form shall mean the preferred form for making modifications,\n      including but not limited to software source code, documentation\n      source, and configuration files.\n\n      \"Object\" form shall mean any form resulting from mechanical\n      transformation or translation of a Source form, including but\n      not limited to compiled object code, generated documentation,\n      and conversions to other media types.\n\n      \"Work\" shall mean the work of authorship, whether in Source or\n      Object form, made available under the License, as indicated by a\n      copyright notice that is included in or attached to the work\n      (an example is provided in the Appendix below).\n\n      \"Derivative Works\" shall mean any work, whether in Source or Object\n      form, that is based on (or derived from) the Work and for which the\n      editorial revisions, annotations, elaborations, or other modifications\n      represent, as a whole, an original work of authorship. For the purposes\n      of this License, Derivative Works shall not include works that remain\n      separable from, or merely link (or bind by name) to the interfaces of,\n      the Work and Derivative Works thereof.\n\n      \"Contribution\" shall mean any work of authorship, including\n      the original version of the Work and any modifications or additions\n      to that Work or Derivative Works thereof, that is intentionally\n      submitted to Licensor for inclusion in the Work by the copyright owner\n      or by an individual or Legal Entity authorized to submit on behalf of\n      the copyright owner. For the purposes of this definition, \"submitted\"\n      means any form of electronic, verbal, or written communication sent\n      to the Licensor or its representatives, including but not limited to\n      communication on electronic mailing lists, source code control systems,\n      and issue tracking systems that are managed by, or on behalf of, the\n      Licensor for the purpose of discussing and improving the Work, but\n      excluding communication that is conspicuously marked or otherwise\n      designated in writing by the copyright owner as \"Not a Contribution.\"\n\n      \"Contributor\" shall mean Licensor and any individual or Legal Entity\n      on behalf of whom a Contribution has been received by Licensor and\n      subsequently incorporated within the Work.\n\n   2. Grant of Copyright License. Subject to the terms and conditions of\n      this License, each Contributor hereby grants to You a perpetual,\n      worldwide, non-exclusive, no-charge, royalty-free, irrevocable\n      copyright license to reproduce, prepare Derivative Works of,\n      publicly display, publicly perform, sublicense, and distribute the\n      Work and such Derivative Works in Source or Object form.\n\n   3. Grant of Patent License. Subject to the terms and conditions of\n      this License, each Contributor hereby grants to You a perpetual,\n      worldwide, non-exclusive, no-","encoding":"utf8","key":"LICENSE","name":"LICENSE","size":11352,"truncated":true},{"bytes":"---\nlicense: apache-2.0\npretty_name: ForceBand EMG2Force\ntags:\n- emg\n- semg\n- force\n- imu\n- wearable\n- robotics\n- manipulation\n- time-series\n- video\nsize_categories:\n- n<1K\nconfigs:\n- config_name: segments\n  data_files: manifest.csv\n  default: true\n---\n\n# ForceBand EMG2Force dataset\n\nWrist **sEMG + IMU** paired with **per-finger fingertip force** and synchronized **RGB video**,\nrecorded with the ForceBand wrist band — the pretraining data of the **EMG2Force** model in\n*\"ForceBand: Learning Forceful Manipulation with sEMG\"* ([arXiv:2606.26093](https://arxiv.org/abs/2606.26093) ·\n[project page](https://forceband-emg.github.io/) · [code](https://github.com/Bottle101/ForceBand)).\n\n- **8.61 h** of cleaned-up EMG + IMU + force at 1 kHz (8.39 h valid), 53 recordings, Oct 2025 – Apr 2026\n- **6.37 h** of it with RGB video (40 recordings; video only for recordings before March 2026)\n- ~7.7 GB (0.55 GB time series + 7.2 GB video)\n\n## Files\n\n```\nsegments/<segment_id>/timeseries.hdf5              EMG / IMU / force, masks, trial table (1 kHz)\nsegments/<segment_id>/rgb_<camera>.mp4              RGB video, one per camera (if any)\nsegments/<segment_id>/rgb_<camera>_timestamps.npy   capture time of each frame\nsegments/<segment_id>/meta.json                     durations, provenance, video info\nmanifest.csv · recording_log.csv · summary.json     per-segment index, recording times, totals\n```\n\nA segment is one continuous recording, including the rest periods between trials.\n`segment_id` is the local start time of the recording.\n\n## Format\n\n`timeseries.hdf5`, group `forceband/timeseries/`:\n\n| dataset | shape | meaning |\n|---|---|---|\n| `timestamps` | (N,) | seconds from segment start (1 kHz) |\n| `emg` | (N, 8) | 8-channel sEMG, filtered |\n| `imu` | (N, 10) | quaternion xyzw, gyro (rad/s), accel (m/s²) |\n| `force` | (N, 5) | thumb … pinky force, sensor units (÷ 18 ≈ N) |\n| `valid` / `imu_valid` | (N,) | real EMG + force / IMU data present |\n| `in_trial`, `task_index` | (N,) | trial mask and task id (−1 between trials) |\n\n`forceband/trials` (K, 4) lists `task_index, trial_in_task, start_s, end_s`.\n\n**Video:** H.264 MP4 at native resolution (848×480 `camera`; 640×480 `cam_ego` + `cam_gt` in Dec 2025).\nFrame `i` was captured at `rgb_<camera>_timestamps.npy[i]` on the same clock as `timestamps` — use these\ntimes to align, since the container's 30 fps is nominal.\n\n## Quick start\n\n```python\nfrom huggingface_hub import snapshot_download\nimport h5py, numpy as np\n\nroot = snapshot_download(\"boootaooo/forceband-emg2force\", repo_type=\"dataset\")\n# time series only: snapshot_download(..., allow_patterns=[\"*.hdf5\", \"*.json\", \"*.csv\", \"*.md\"])\nseg = f\"{root}/segments/2025-11-04-15-13-41\"\nwith h5py.File(f\"{seg}/timeseries.hdf5\") as f:\n    g = f[\"forceband/timeseries\"]\n    t, emg, imu, force = (g[k][()] for k in (\"timestamps\", \"emg\", \"imu\", \"force\"))\nframe_t = np.load(f\"{seg}/rgb_camera_timestamps.npy\")    # align frames with np.searchsorted(t, frame_t)\n```\n\n## Notes\n\n* EMG: OpenBCI timestamps evened out, then 58–62 Hz bandstop, 5–50 Hz bandpass and 50/60 Hz noise\n  removal — the preprocessing used for training. All streams are resampled to 1 kHz.\n* Some recordings had force-sensor drift; their force carries a baseline correction (`force_tared`).\n* The EMG contains occasional large spikes (filter edge transients, electrode artifacts) not flagged by `valid`.\n* Two recordings have no IMU (`imu` is NaN). Video shows the participants, including faces.\n\n## License\n\nApache-2.0, the same as the [ForceBand code](https://github.com/Bottle101/ForceBand) (see `LICENSE`).\n\n## Citation\n\n```bibtex\n@article{he2026forceband,\n  title   = {ForceBand: Learning Forceful Manipulation with sEMG},\n  author  = {He, Botao and Wang, Zhi and Kuang, Linna and Ghosh, Ishaan and Malik, Jitendra and Fermuller, Cornelia and Wu, Tingfan and Mao, Jiayuan and Liu, Ruoshi and Qi, Haozhi and Aloimonos, Yiannis},\n  journal = {arXiv preprint arXiv:2606.26093},\n  year    = {2026}\n}\n```\n","encoding":"utf8","key":"README.md","name":"README.md","size":4007,"truncated":false}],"sourceObjectKey":"manifest.csv","starterCell":"import pandas as pd\ndf = pd.read_csv(\"hf://datasets/boootaooo/forceband-emg2force/manifest.csv\")\ndf.head()","starterSamplePath":"manifest.csv","totalObjects":253},"summary":"The pretraining data of the EMG2Force model from ForceBand: Learning Forceful Manipulation with sEMG (He, Wang, Kuang, Ghosh, Malik, Fermuller and colleagues, arXiv:2606.26093).","title":"ForceBand EMG2Force: Wrist Surface EMG and IMU with Per-Finger Fingertip Force and RGB Video (He, Malik et al.)","updatedAt":"2026-11-22T04:01:16.753Z","visibility":"public","websiteUrl":"https://forceband-emg.github.io/"}}