Fuxiao Liu


Fuxiao Liu
Hi! I'm a 2nd-year CS Ph.D at University of Maryland, College Park, working with Abhinav Shrivastava and Yaser Yacoob. Before that, I worked in the Vision, Language, and Learning Lab in UVa, supervised by Vicente Ordonez-Roman. In the 2022 summer, I interned in Adobe Research, advised by Chris Tensmeyer, Hao Tan and Ani Nenkova.
I have broad interests in vision and language tasks, including image/video captioning, multimodal semantic alignment, fact-checking, document and infographic understanding.
My resume is here (2022.09). Email: fl3es@umd.edu
Experience
Publications
  1. Linking Figures and Main Body Text in Documents and Related UX feature in Reflowed Documents
    Fuxiao Liu*, Chris Tensmeyer, Hao Tan, Ani Nenkova
    Under Review
    Descriptions: In this project, we apply the contrastive learning algorithm to determine the document-internal connections between specific figures and body Text. Our model can be applied to Adobe Liquid mode to improve the reading experience on the smartphone.

  2. COVID-VTS: Fact Extraction and Verification on Short Video Platforms
    Fuxiao Liu*, Yaser Yacoob, Abhinav Shrivastava
    Descriptions: We introduce COVID-VTS, a fact-checking dataset for short video platforms. We propose an effective approach to automatically generate large-scale verifiable, trustworthy as well as misleading claims rather than employing human annotators. We propose TwtrDetective, a new explainable fact-checking framework for the short video platform.

  3. Visual News: Benchmark and Challenges in News Image Captioning
    Fuxiao Liu*, Yinghan Wang, Tianlu Wang, Vicente Ordonez
    EMNLP 2021 (~Oral presentation) [paper] [code] [bibtex]
    Descriptions: Introduced VisualNews, the largest and most diverse news image captioning dataset. Proposed VisualNews-Captioner, increasing CIDEr by 10+ points with fewer parameters than competing methods.

  4. A Novel Lightweight Semantic Segmentation Network in Remote Sensing
    Fuxiao Liu*, Ming Wu
    Bachelor Thesis, 2019 [paper]
    Descriptions: Developed a novel lightweight Fully Convolutional Network, which achieved better accuracy with much smaller model size(20.2M) than baseline models(117.8 M) on two Remote Sensing Datasets.
Projects
  1. Deep Learning Network Embedding with Regular Equivalence
    Keywords: Deep Learning, Graph Embedding
    Descriptions: Designed an Auto-Encoder based on the attention mechanism and LSTM to learn role information from the multi-hop neighborhoods. Experimented on American Air Traffic Network dataset, increased the accuracy by 0.03 compared to the baseline algorithms.
More About Myself
    I'm crazy about basketball since I was a little boy. I love it for its ultimate technical and mentality requirements. No one in the world can become a master without great talent and extensive training. My favorite basketball player is Kobe Bryant, who is noted for his rapid playing style, strong will, and his ambivalent relationship with the sport. I am always immersed in his phenomenal performance in the game.