Picture for Yiqi Gao

Yiqi Gao

Enhancing Prompt Following with Visual Control Through Training-Free Mask-Guided Diffusion

Add code
Apr 23, 2024
Viaarxiv icon

Human-centric Behavior Description in Videos: New Benchmark and Model

Add code
Oct 04, 2023
Viaarxiv icon

S3C: Semi-Supervised VQA Natural Language Explanation via Self-Critical Learning

Add code
Sep 05, 2023
Viaarxiv icon

Dual-Level Decoupled Transformer for Video Captioning

Add code
May 06, 2022
Figure 1 for Dual-Level Decoupled Transformer for Video Captioning
Figure 2 for Dual-Level Decoupled Transformer for Video Captioning
Figure 3 for Dual-Level Decoupled Transformer for Video Captioning
Figure 4 for Dual-Level Decoupled Transformer for Video Captioning
Viaarxiv icon

CapOnImage: Context-driven Dense-Captioning on Image

Add code
Apr 27, 2022
Figure 1 for CapOnImage: Context-driven Dense-Captioning on Image
Figure 2 for CapOnImage: Context-driven Dense-Captioning on Image
Figure 3 for CapOnImage: Context-driven Dense-Captioning on Image
Figure 4 for CapOnImage: Context-driven Dense-Captioning on Image
Viaarxiv icon