Picture for Xiwen Liang

Xiwen Liang

MO-VLN: A Multi-Task Benchmark for Open-set Zero-Shot Vision-and-Language Navigation

Add code
Jun 17, 2023
Figure 1 for MO-VLN: A Multi-Task Benchmark for Open-set Zero-Shot Vision-and-Language Navigation
Figure 2 for MO-VLN: A Multi-Task Benchmark for Open-set Zero-Shot Vision-and-Language Navigation
Figure 3 for MO-VLN: A Multi-Task Benchmark for Open-set Zero-Shot Vision-and-Language Navigation
Figure 4 for MO-VLN: A Multi-Task Benchmark for Open-set Zero-Shot Vision-and-Language Navigation
Viaarxiv icon

Visual Exemplar Driven Task-Prompting for Unified Perception in Autonomous Driving

Mar 03, 2023
Figure 1 for Visual Exemplar Driven Task-Prompting for Unified Perception in Autonomous Driving
Figure 2 for Visual Exemplar Driven Task-Prompting for Unified Perception in Autonomous Driving
Figure 3 for Visual Exemplar Driven Task-Prompting for Unified Perception in Autonomous Driving
Figure 4 for Visual Exemplar Driven Task-Prompting for Unified Perception in Autonomous Driving
Viaarxiv icon

NLIP: Noise-robust Language-Image Pre-training

Jan 04, 2023
Figure 1 for NLIP: Noise-robust Language-Image Pre-training
Figure 2 for NLIP: Noise-robust Language-Image Pre-training
Figure 3 for NLIP: Noise-robust Language-Image Pre-training
Figure 4 for NLIP: Noise-robust Language-Image Pre-training
Viaarxiv icon

Effective Adaptation in Multi-Task Co-Training for Unified Autonomous Driving

Add code
Sep 19, 2022
Figure 1 for Effective Adaptation in Multi-Task Co-Training for Unified Autonomous Driving
Figure 2 for Effective Adaptation in Multi-Task Co-Training for Unified Autonomous Driving
Figure 3 for Effective Adaptation in Multi-Task Co-Training for Unified Autonomous Driving
Figure 4 for Effective Adaptation in Multi-Task Co-Training for Unified Autonomous Driving
Viaarxiv icon

ADAPT: Vision-Language Navigation with Modality-Aligned Action Prompts

Add code
May 31, 2022
Figure 1 for ADAPT: Vision-Language Navigation with Modality-Aligned Action Prompts
Figure 2 for ADAPT: Vision-Language Navigation with Modality-Aligned Action Prompts
Figure 3 for ADAPT: Vision-Language Navigation with Modality-Aligned Action Prompts
Figure 4 for ADAPT: Vision-Language Navigation with Modality-Aligned Action Prompts
Viaarxiv icon

Visual-Language Navigation Pretraining via Prompt-based Environmental Self-exploration

Add code
Mar 08, 2022
Figure 1 for Visual-Language Navigation Pretraining via Prompt-based Environmental Self-exploration
Figure 2 for Visual-Language Navigation Pretraining via Prompt-based Environmental Self-exploration
Figure 3 for Visual-Language Navigation Pretraining via Prompt-based Environmental Self-exploration
Figure 4 for Visual-Language Navigation Pretraining via Prompt-based Environmental Self-exploration
Viaarxiv icon

Contrastive Instruction-Trajectory Learning for Vision-Language Navigation

Dec 09, 2021
Figure 1 for Contrastive Instruction-Trajectory Learning for Vision-Language Navigation
Figure 2 for Contrastive Instruction-Trajectory Learning for Vision-Language Navigation
Figure 3 for Contrastive Instruction-Trajectory Learning for Vision-Language Navigation
Figure 4 for Contrastive Instruction-Trajectory Learning for Vision-Language Navigation
Viaarxiv icon

SODA10M: Towards Large-Scale Object Detection Benchmark for Autonomous Driving

Add code
Jun 22, 2021
Figure 1 for SODA10M: Towards Large-Scale Object Detection Benchmark for Autonomous Driving
Figure 2 for SODA10M: Towards Large-Scale Object Detection Benchmark for Autonomous Driving
Figure 3 for SODA10M: Towards Large-Scale Object Detection Benchmark for Autonomous Driving
Figure 4 for SODA10M: Towards Large-Scale Object Detection Benchmark for Autonomous Driving
Viaarxiv icon

SOON: Scenario Oriented Object Navigation with Graph-based Exploration

Mar 31, 2021
Figure 1 for SOON: Scenario Oriented Object Navigation with Graph-based Exploration
Figure 2 for SOON: Scenario Oriented Object Navigation with Graph-based Exploration
Figure 3 for SOON: Scenario Oriented Object Navigation with Graph-based Exploration
Figure 4 for SOON: Scenario Oriented Object Navigation with Graph-based Exploration
Viaarxiv icon