LIAM: Multimodal Transformer for Language Instructions, Images, Actions and Semantic Maps
- 2 September 2026
- book chapter
- Published by Springer Nature
- p. 120-131
Abstract
No abstract availableThis publication has 6 references indexed in Scilit:
- Detecting Twenty-Thousand Classes Using Image-Level Supervision2022
- CLIP4Clip: An empirical study of CLIP for end to end video clip retrieval and captioningNeurocomputing, 2022
- GroupViT: Semantic Segmentation Emerges from Text Supervision2022
- Image Segmentation Using Text and Image Prompts2022
- Episodic Transformer for Vision-and-Language Navigation2021
- ALFRED: A Benchmark for Interpreting Grounded Instructions for Everyday Tasks2020