Picture for Tsung-Han Wu

Tsung-Han Wu

Visual Haystacks: Answering Harder Questions About Sets of Images

Add code
Jul 18, 2024
Viaarxiv icon

AED: Adaptable Error Detection for Few-shot Imitation Policy

Add code
Feb 06, 2024
Viaarxiv icon

See, Say, and Segment: Teaching LMMs to Overcome False Premises

Add code
Dec 13, 2023
Figure 1 for See, Say, and Segment: Teaching LMMs to Overcome False Premises
Figure 2 for See, Say, and Segment: Teaching LMMs to Overcome False Premises
Figure 3 for See, Say, and Segment: Teaching LMMs to Overcome False Premises
Figure 4 for See, Say, and Segment: Teaching LMMs to Overcome False Premises
Viaarxiv icon

Self-correcting LLM-controlled Diffusion Models

Add code
Nov 27, 2023
Figure 1 for Self-correcting LLM-controlled Diffusion Models
Figure 2 for Self-correcting LLM-controlled Diffusion Models
Figure 3 for Self-correcting LLM-controlled Diffusion Models
Figure 4 for Self-correcting LLM-controlled Diffusion Models
Viaarxiv icon

WLST: Weak Labels Guided Self-training for Weakly-supervised Domain Adaptation on 3D Object Detection

Add code
Oct 05, 2023
Figure 1 for WLST: Weak Labels Guided Self-training for Weakly-supervised Domain Adaptation on 3D Object Detection
Figure 2 for WLST: Weak Labels Guided Self-training for Weakly-supervised Domain Adaptation on 3D Object Detection
Figure 3 for WLST: Weak Labels Guided Self-training for Weakly-supervised Domain Adaptation on 3D Object Detection
Figure 4 for WLST: Weak Labels Guided Self-training for Weakly-supervised Domain Adaptation on 3D Object Detection
Viaarxiv icon

MuRAL: Multi-Scale Region-based Active Learning for Object Detection

Add code
Mar 29, 2023
Figure 1 for MuRAL: Multi-Scale Region-based Active Learning for Object Detection
Figure 2 for MuRAL: Multi-Scale Region-based Active Learning for Object Detection
Figure 3 for MuRAL: Multi-Scale Region-based Active Learning for Object Detection
Figure 4 for MuRAL: Multi-Scale Region-based Active Learning for Object Detection
Viaarxiv icon

Free-form 3D Scene Inpainting with Dual-stream GAN

Add code
Dec 16, 2022
Figure 1 for Free-form 3D Scene Inpainting with Dual-stream GAN
Figure 2 for Free-form 3D Scene Inpainting with Dual-stream GAN
Figure 3 for Free-form 3D Scene Inpainting with Dual-stream GAN
Figure 4 for Free-form 3D Scene Inpainting with Dual-stream GAN
Viaarxiv icon

CrossDTR: Cross-view and Depth-guided Transformers for 3D Object Detection

Add code
Oct 12, 2022
Figure 1 for CrossDTR: Cross-view and Depth-guided Transformers for 3D Object Detection
Figure 2 for CrossDTR: Cross-view and Depth-guided Transformers for 3D Object Detection
Figure 3 for CrossDTR: Cross-view and Depth-guided Transformers for 3D Object Detection
Figure 4 for CrossDTR: Cross-view and Depth-guided Transformers for 3D Object Detection
Viaarxiv icon

Learning Fine-Grained Visual Understanding for Video Question Answering via Decoupling Spatial-Temporal Modeling

Add code
Oct 08, 2022
Figure 1 for Learning Fine-Grained Visual Understanding for Video Question Answering via Decoupling Spatial-Temporal Modeling
Figure 2 for Learning Fine-Grained Visual Understanding for Video Question Answering via Decoupling Spatial-Temporal Modeling
Figure 3 for Learning Fine-Grained Visual Understanding for Video Question Answering via Decoupling Spatial-Temporal Modeling
Figure 4 for Learning Fine-Grained Visual Understanding for Video Question Answering via Decoupling Spatial-Temporal Modeling
Viaarxiv icon

Fair Robust Active Learning by Joint Inconsistency

Add code
Sep 22, 2022
Figure 1 for Fair Robust Active Learning by Joint Inconsistency
Figure 2 for Fair Robust Active Learning by Joint Inconsistency
Figure 3 for Fair Robust Active Learning by Joint Inconsistency
Figure 4 for Fair Robust Active Learning by Joint Inconsistency
Viaarxiv icon