81 citations · 642 across the 37 of their papers we have counts for
8 papers · 1 filter
Toward Multimodal Model-Agnostic Meta-Learning
Risto Vuorio, Shao-Hua Sun, Hexiang Hu +1
Gradient-based meta-learners such as MAML are able to learn a meta-prior from similar tasks to adapt to novel tasks from the same distribution with few gradient updates. One import…
Few-Shot Learning via Embedding Adaptation with Set-to-Set Functions
Han-Jia Ye, Hexiang Hu, De-Chuan Zhan +1
Learning with limited data is a key challenge for visual recognition. Many few-shot learning methods address this challenge by learning an instance embedding function from seen cla…
Cross-Modal and Hierarchical Modeling of Video and Text
Bowen Zhang, Hexiang Hu, Fei Sha
Visual data and text data are composed of information at multiple granularities. A video can describe a complex scene that is composed of multiple clips or shots, where each depict…
Engaging Image Captioning Via Personality
Kurt Shuster, Samuel Humeau, Hexiang Hu +2
Standard image captioning tasks such as COCO and Flickr30k are factual, neutral in tone and (to a human) state the obvious (e.g., "a man playing a guitar"). While such tasks are us…
Multi-Task Learning for Sequence Tagging: An Empirical Study
Soravit Changpinyo, Hexiang Hu, Fei Sha
We study three general multi-task learning (MTL) approaches on 11 sequence tagging tasks. Our extensive empirical results show that in about 50% of the cases, jointly learning all…
Cross-Dataset Adaptation for Visual Question Answering
Wei-Lun Chao, Hexiang Hu, Fei Sha
We investigate the problem of cross-dataset adaptation for visual question answering (Visual QA). Our goal is to train a Visual QA model on a source dataset but apply it to another…