Profiles2021-2023
Paul Hongsuck Seo
Google Research
5Papers
0Last author
7Unique co-authors
3First author
0Solo
First and last author come from byline position, which some venues assign alphabetically.
Recent papers5
- AVFormer: Injecting Vision into Frozen Speech Models for Zero-Shot AV-ASRAuthor 1 of 3CVPR 2023
- IFSeg: Image-free Semantic Segmentation via Vision-Language ModelAuthor 3 of 4CVPR 2023
- Zero-shot Referring Image Segmentation with Global-Local Context FeaturesAuthor 2 of 3CVPR 2023
- End-to-end Generative Pretraining for Multimodal Video CaptioningAuthor 1 of 4CVPR 2022 · 152 citations
- Look Before You Speak: Visually Contextualized UtterancesAuthor 1 of 3CVPR 2021
