Alexander Martin

Hey, I am Alex. I am an incoming  Ph.D. student at Johns Hopkins University. I am supported by an NSF Graduate Research Fellowship.

My current research is in the intersection of vision and language. I am interested in understanding videos and documents, especially in large contexts, and distilling knowledge from these large unstructured sources into concise representations. My NSF GRF proposal is on understanding events in videos and multimodal (video+language).

I currently am working on projects in:

  1. 1. Automatic report generation and summarization for language (EKS) and videos (VideoXum)
  2. 2. Information Extraction across multiple documents (FAMuS) and multiple modalities (preprint coming soon).
  3. 3. Methods for strong video understanding (work in progress). With a specific interest in long videos and videos with multiple events.

Previously in my undergraduate at the University of Rochester, I worked on projects in image generation, video summarization, and event extraction advised by  Jiebo Luo and Aaron White. I also had the opportunity to do some research in mathematics (and still do) with  Clyde Martin.