Picture for Yuankai Qi

Yuankai Qi

Structural Attention: Rethinking Transformer for Unpaired Medical Image Synthesis

Add code
Jun 27, 2024
Viaarxiv icon

Augmented Commonsense Knowledge for Remote Object Grounding

Add code
Jun 03, 2024
Viaarxiv icon

Retrieval Enhanced Zero-Shot Video Captioning

Add code
May 11, 2024
Viaarxiv icon

Generating Content for HDR Deghosting from Frequency View

Add code
Apr 01, 2024
Figure 1 for Generating Content for HDR Deghosting from Frequency View
Figure 2 for Generating Content for HDR Deghosting from Frequency View
Figure 3 for Generating Content for HDR Deghosting from Frequency View
Figure 4 for Generating Content for HDR Deghosting from Frequency View
Viaarxiv icon

Decomposing Disease Descriptions for Enhanced Pathology Detection: A Multi-Aspect Vision-Language Matching Framework

Add code
Mar 12, 2024
Figure 1 for Decomposing Disease Descriptions for Enhanced Pathology Detection: A Multi-Aspect Vision-Language Matching Framework
Figure 2 for Decomposing Disease Descriptions for Enhanced Pathology Detection: A Multi-Aspect Vision-Language Matching Framework
Figure 3 for Decomposing Disease Descriptions for Enhanced Pathology Detection: A Multi-Aspect Vision-Language Matching Framework
Figure 4 for Decomposing Disease Descriptions for Enhanced Pathology Detection: A Multi-Aspect Vision-Language Matching Framework
Viaarxiv icon

StyleDubber: Towards Multi-Scale Style Learning for Movie Dubbing

Add code
Feb 21, 2024
Viaarxiv icon

Subject-Oriented Video Captioning

Add code
Dec 20, 2023
Viaarxiv icon

Weakly Supervised Video Individual CountingWeakly Supervised Video Individual Counting

Add code
Dec 10, 2023
Figure 1 for Weakly Supervised Video Individual CountingWeakly Supervised Video Individual Counting
Figure 2 for Weakly Supervised Video Individual CountingWeakly Supervised Video Individual Counting
Figure 3 for Weakly Supervised Video Individual CountingWeakly Supervised Video Individual Counting
Figure 4 for Weakly Supervised Video Individual CountingWeakly Supervised Video Individual Counting
Viaarxiv icon

Dynamic Erasing Network Based on Multi-Scale Temporal Features for Weakly Supervised Video Anomaly Detection

Add code
Dec 04, 2023
Figure 1 for Dynamic Erasing Network Based on Multi-Scale Temporal Features for Weakly Supervised Video Anomaly Detection
Figure 2 for Dynamic Erasing Network Based on Multi-Scale Temporal Features for Weakly Supervised Video Anomaly Detection
Figure 3 for Dynamic Erasing Network Based on Multi-Scale Temporal Features for Weakly Supervised Video Anomaly Detection
Figure 4 for Dynamic Erasing Network Based on Multi-Scale Temporal Features for Weakly Supervised Video Anomaly Detection
Viaarxiv icon

March in Chat: Interactive Prompting for Remote Embodied Referring Expression

Add code
Aug 20, 2023
Figure 1 for March in Chat: Interactive Prompting for Remote Embodied Referring Expression
Figure 2 for March in Chat: Interactive Prompting for Remote Embodied Referring Expression
Figure 3 for March in Chat: Interactive Prompting for Remote Embodied Referring Expression
Figure 4 for March in Chat: Interactive Prompting for Remote Embodied Referring Expression
Viaarxiv icon