esk
Datasets
All datasets matching “esk”ESK_action_segmentationPaper | GitHub
🍳 EPFL-Smart-Kitchen: Action segmentation benchmark
📚 Introduction
Given an untrimmed video, action segmentation requires the model to predict one or multiple action classes for every frame.Given the absence of popular (and comprehensive) action segmentation benchmarks from 3D pose we built an action segmentation benchmark that compares the impact of different input data (body,hand,eyes, videofeatures).One might expect that actions such as moving through… See the full description on the dataset page: https://huggingface.co/datasets/amathislab/ESK_action_segmentation.ESK_action_recognitionPaper | GitHub
🍳 EPFL-Smart-Kitchen: Action recognition benchmark
📚 Introduction
Given a video or temporal clip, action recognition requires the model to predict a single action label for that clip (or for a specified window within an untrimmed video). Building on the same EPFL-Smart-Kitchen-30 data and modalities as our segmentation benchmark, we provide a recognition-oriented setup to compare inputs from 3D body pose, hand pose, and eye gaze, as well as deep visual… See the full description on the dataset page: https://huggingface.co/datasets/amathislab/ESK_action_recognition.ESK_motion_generationPaper | GitHub
🍳 EPFL‑Smart‑Kitchen: Motion Generation Assets
📚 Introduction
This folder accompanies motion generation experiments on EPFL‑Smart‑Kitchen‑30 (ESK‑30). The goal is to generate realistic human motion sequences (e.g., body and hands in 3D) optionally conditioned on text, activity context, or past motion. The assets here focus on kinematic inputs/outputs (body, hands, gaze) from ESK‑30 to enable training, fine‑tuning, and evaluation of motion generators.… See the full description on the dataset page: https://huggingface.co/datasets/amathislab/ESK_motion_generation.eskulap_validation_datasetstfm_final_dataset_120_eps_depthtfm_final_dataset_120_eps