MOMA: Multi-Object Multi-Actor Activity Parsing

no code implementations • NeurIPS 2021 • Zelun Luo, Wanze Xie, Siddharth Kapoor, Yiyun Liang, Michael Cooper, Juan Carlos Niebles, Ehsan Adeli, Fei-Fei Li

This paper introduces Activity Parsing as the overarching task of temporal segmentation and classification of activities, sub-activities, atomic actions, along with an instance-level understanding of actors, objects, and their relationships in videos.

Object

CNNs for NLP in the Browser: Client-Side Deployment and Visualization Opportunities

no code implementations • NAACL 2018 • Yiyun Liang, Zhucheng Tu, Laetitia Huang, Jimmy Lin

We demonstrate a JavaScript implementation of a convolutional neural network that performs feedforward inference completely in the browser.

Interpretable Machine Learning Sentence Classification +1