Dataset Hub

We created a wild multimodal plant disease recognition dataset PlantWild, which has the most disease categories. Our dataset introduces descriptive prompts to provide rich information in the text modality.

CogBeacon is a multimodal dataset designed to study cognitive fatigue effects in human performance. It contains 76 sessions collected from 19 male and female users performing various versions of the Wisconsin Card Sorting Test (WCST). In each session, EEG signals, facial keypoints, real‑time self‑reported cognitive fatigue, and performance metrics (accuracy, response time, error count, etc.) were recorded and fully annotated. Additionally, a baseline machine‑learning analysis for predicting cognitive fatigue is provided, along with a multimodal WCST implementation to allow other researchers to extend or modify the data‑collection framework. To our knowledge, this is the first multimodal dataset specifically designed to assess cognitive fatigue.