Search Results for author: Shangzhe Di

Found 2 papers, 1 papers with code

Grounded Question-Answering in Long Egocentric Videos

1 code implementation • 11 Dec 2023 • Shangzhe Di, Weidi Xie

Existing approaches to video understanding, mainly designed for short videos from a third-person perspective, are limited in their applicability in certain fields, such as robotics.

Open-Ended Question Answering Video Question Answering +1

Paper
Code

Sparse Dense Fusion for 3D Object Detection

no code implementations • 9 Apr 2023 • Yulu Gao, Chonghao Sima, Shaoshuai Shi, Shangzhe Di, Si Liu, Hongyang Li

With the prevalence of multimodal learning, camera-LiDAR fusion has gained popularity in 3D object detection.

3D Object Detection Object +1

Paper
Add Code

Cannot find the paper you are looking for? You can Submit a new open access paper.