Get our free extension to see links to code for papers anywhere online!

Add to Chrome

Add to Firefox

Picture for AJ Piergiovanni

AJ Piergiovanni

Compound Tokens: Channel Fusion for Vision-Language Representation Learning

Dec 02, 2022
Maxwell Mbabilla Aladago, AJ Piergiovanni

Figure 1 for Compound Tokens: Channel Fusion for Vision-Language Representation Learning

Figure 2 for Compound Tokens: Channel Fusion for Vision-Language Representation Learning

Figure 3 for Compound Tokens: Channel Fusion for Vision-Language Representation Learning

Figure 4 for Compound Tokens: Channel Fusion for Vision-Language Representation Learning

Access Paper or Ask Questions

F-VLM: Open-Vocabulary Object Detection upon Frozen Vision and Language Models

Sep 30, 2022
Weicheng Kuo, Yin Cui, Xiuye Gu, AJ Piergiovanni, Anelia Angelova

Figure 1 for F-VLM: Open-Vocabulary Object Detection upon Frozen Vision and Language Models

Figure 2 for F-VLM: Open-Vocabulary Object Detection upon Frozen Vision and Language Models

Figure 3 for F-VLM: Open-Vocabulary Object Detection upon Frozen Vision and Language Models

Figure 4 for F-VLM: Open-Vocabulary Object Detection upon Frozen Vision and Language Models

* 19 pages, 6 figures

Access Paper or Ask Questions

4D-Net for Learned Multi-Modal Alignment

Sep 02, 2021
AJ Piergiovanni, Vincent Casser, Michael S. Ryoo, Anelia Angelova

Figure 1 for 4D-Net for Learned Multi-Modal Alignment

Figure 2 for 4D-Net for Learned Multi-Modal Alignment

Figure 3 for 4D-Net for Learned Multi-Modal Alignment

Figure 4 for 4D-Net for Learned Multi-Modal Alignment

* ICCV 2021

Access Paper or Ask Questions