Search Results for author:
Found 7 papers, 4 papers with code
Target-Driven Structured Transformer Planner for Vision-Language Navigation
Vision-language navigation is the task of directing an embodied agent to navigate in 3D scenes with natural language instructions.
3D-SPS: Single-Stage 3D Visual Grounding via Referred Point Progressive Selection
3D visual grounding aims to locate the referred target object in 3D point cloud scenes according to a free-form language description.
Twins: Revisiting the Design of Spatial Attention in Vision Transformers
Very recently, a variety of vision transformer architectures for dense prediction tasks have been proposed and they show that the design of spatial attention is critical to their success in these tasks.
Ranked #46 on
Semantic Segmentation
on ADE20K val
End-to-End Video Instance Segmentation with Transformers
Here, we propose a new video instance segmentation framework built upon Transformers, termed VisTR, which views the VIS task as a direct end-to-end parallel sequence decoding/prediction problem.
Ranked #21 on
Video Instance Segmentation
on YouTube-VIS validation
Robust Trajectory Forecasting for Multiple Intelligent Agents in Dynamic Scene
Trajectory forecasting, or trajectory prediction, of multiple interacting agents in dynamic scenes, is an important problem for many applications, such as robotic systems and autonomous driving.
VisionNet: A Drivable-space-based Interactive Motion Prediction Network for Autonomous Driving
To further advance the performance, we propose an interactive loss to guide the generation of the drivable spaces.
StarNet: Pedestrian Trajectory Prediction using Deep Neural Network in Star Topology
The hub network takes observed trajectories of all pedestrians to produce a comprehensive description of the interpersonal interactions.
