research
∙
08/08/2022
Two-Stream Networks for Object Segmentation in Videos
Existing matching-based approaches perform video object segmentation (VO...
share
research
∙
07/19/2022
Target-Driven Structured Transformer Planner for Vision-Language Navigation
Vision-language navigation is the task of directing an embodied agent to...
research
∙
04/29/2022
SideRT: A Real-time Pure Transformer Architecture for Single Image Depth Estimation
Since context modeling is critical for estimating depth from a single im...
research
∙
04/13/2022
3D-SPS: Single-Stage 3D Visual Grounding via Referred Point Progressive Selection
3D visual grounding aims to locate the referred target object in 3D poin...
research
∙
04/28/2021
Twins: Revisiting Spatial Attention Design in Vision Transformers
Very recently, a variety of vision transformer architectures for dense p...
research
∙
02/09/2021