Lune

Profiles2019-2023

Cordelia Schmid

University of Illinois at Urbana-Champaign

12Papers
9Last author
23Unique co-authors
0First author
0Solo

First and last author come from byline position, which some venues assign alphabetically.

Recent papers12

  1. UnLoc: A Unified Framework for Video Localization TasksAuthor 8 of 8ICCV 2023 · 82 citations
  2. AVFormer: Injecting Vision into Frozen Speech Models for Zero-Shot AV-ASRAuthor 3 of 3CVPR 2023
  3. How can objects help action recognition?Author 4 of 4CVPR 2023
  4. Multiview Transformers for Video RecognitionAuthor 7 of 7CVPR 2022 · 279 citations
  5. End-to-end Generative Pretraining for Multimodal Video CaptioningAuthor 4 of 4CVPR 2022 · 152 citations
  6. ViViT: A Video Vision TransformerAuthor 6 of 6ICCV 2021 · 2,947 citations
  7. Attention Bottlenecks for Multimodal FusionAuthor 5 of 6NeurIPS 2021 · 884 citations
  8. Unified Graph Structured Models for Video UnderstandingAuthor 3 of 3ICCV 2021 · 57 citations
  9. Composable Augmentation Encoding for Video Representation LearningAuthor 4 of 5ICCV 2021 · 20 citations
  10. Look Before You Speak: Visually Contextualized UtterancesAuthor 3 of 3CVPR 2021
  11. VectorNet: Encoding HD Maps and Agent Dynamics From Vectorized RepresentationAuthor 7 of 7CVPR 2020
  12. Self-Supervised Learning With Geometric Constraints in Monocular Video: Connecting Flow, Depth, and CameraAuthor 2 of 3ICCV 2019 · 265 citations
Dusk over the sea between two cliffs drawn in fine vertical lines