42 datasets found

The dataset used in the paper to simulate human behavior in various experiments, including the Ultimatum Game, Garden Path Sentences, Milgram Shock Experiment, and Wisdom of...

The dataset used in the paper for human-art dataset

The dataset used in the Wizard of Oz study to explore novice mental models in voice-based 3D modeling.

FashionEngine is an interactive 3D human generation and editing system that enables easy and efficient production of 3D digital humans with multimodal control.

The dataset used in this paper is a collection of data points from a lunar lander, which is used to test the proposed APG algorithm for task switching.

A text-driven animated human mesh synthesis system that leverages multi-modal aware and semantic textual matching.

RICH is an in-the-wild and indoor multi-view dataset for 3D human body reconstruction, containing 2D keypoints and 3D body mesh annotations.

The dataset used in this paper is a multiclass classification task where the goal is to correctly predict which of the 7 activities is being performed by the user. The...

RF-Capture: Capturing the Human Figure Through a Wall

The EGTEA Gaze+ dataset offers approximately 10,000 samples of 106 non-scripted daily activities that occur in a kitchen.

Motion synthesis in real-world 3D scenes has recently attracted much attention. However, the static environment assumption made by most current methods usually cannot be...

Human Activity Recognition (HAR) datasets used in the paper for Federated Learning and Federated Unlearning.

VideoAttentionTarget is a video-based gaze target dataset comprising 71,666 frames from 1,331 clips.

GazeFollow is a large-scale dataset consisting of 122,143 images with 130,339 annotations on head-target instances.

Gaze target detection aims to directly associate individuals and their gaze targets within a single image or across multiple video frames.

Dataset for tracking faces, hands, and bodies in videos.

Real-world dataset for reconstructing 3D people models from monocular video.

Real-world datasets for reconstructing human avatars from monocular video, including ZJU-MoCap and People-Snapshot.

The authors propose a novel approach that incorporates parameter-efficient tuning to better optimize control tokens, thus benefitting controllable generation.

A 4D instance segmentation dataset of close human interaction.