David Harwath
9 papers · 342 citations
Most-cited papers
- Everything At Once -- Multi-modal Fusion Transformer For Video Retrieval2021 · 126 citations
- Jointly Discovering Visual Objects And Spoken Words From Raw Sensory Input2018 · 79 citations
- Multimodal Clustering Networks For Self-supervised Learning From Unlabeled Videos2021 · 58 citations
- Avlnet: Learning Audio-visual Language Representations From Instructional Videos2020 · 51 citations
- Why Is Winoground Hard? Investigating Failures In Visuolinguistic Compositionality2022 · 11 citations
Top co-authors
Topics