The NUS-WIDE dataset is a large-scale multi-label image dataset that can be widely used for image classification and multi-label learning tasks. It contains 269,648 images collected from Flickr, annotated with 81 concept labels .

TAT-QA (Tabular And Textual dataset for Question Answering) contains 16,552 questions associated with 2,757 hybrid contexts from real-world financial reports.

TAT-DQA: Towards Complex Document Understanding By Discrete Reasoning

TAT-HQA

NeuRec is a comprehensive and flexible Python library for recommendation models that includes a large range of state-of-the-art neural recommender models.

PACIFIC: Towards Proactive Conversational Question Answering over Tabular and Textual Data in Finance

The baseline method for CCIR 22https://www.datafountain.cn/competitions/573

Official repository for "MMConv: An Environment for Multimodal Conversational Search across Multiple Domains"

Video Relation Understanding (VRU) grand challenge toolbox