Picture for Jingjing Wang

Jingjing Wang

Unified Directly Denoising for Both Variance Preserving and Variance Exploding Diffusion Models

May 31, 2024
Viaarxiv icon

Directly Denoising Diffusion Model

May 22, 2024
Viaarxiv icon

1st Place Solution for ICCV 2023 OmniObject3D Challenge: Sparse-View Reconstruction

Add code
Apr 16, 2024
Figure 1 for 1st Place Solution for ICCV 2023 OmniObject3D Challenge: Sparse-View Reconstruction
Figure 2 for 1st Place Solution for ICCV 2023 OmniObject3D Challenge: Sparse-View Reconstruction
Figure 3 for 1st Place Solution for ICCV 2023 OmniObject3D Challenge: Sparse-View Reconstruction
Figure 4 for 1st Place Solution for ICCV 2023 OmniObject3D Challenge: Sparse-View Reconstruction
Viaarxiv icon

ChatASU: Evoking LLM's Reflexion to Truly Understand Aspect Sentiment in Dialogues

Add code
Mar 12, 2024
Figure 1 for ChatASU: Evoking LLM's Reflexion to Truly Understand Aspect Sentiment in Dialogues
Figure 2 for ChatASU: Evoking LLM's Reflexion to Truly Understand Aspect Sentiment in Dialogues
Figure 3 for ChatASU: Evoking LLM's Reflexion to Truly Understand Aspect Sentiment in Dialogues
Figure 4 for ChatASU: Evoking LLM's Reflexion to Truly Understand Aspect Sentiment in Dialogues
Viaarxiv icon

TopicDiff: A Topic-enriched Diffusion Approach for Multimodal Conversational Emotion Detection

Add code
Mar 11, 2024
Figure 1 for TopicDiff: A Topic-enriched Diffusion Approach for Multimodal Conversational Emotion Detection
Figure 2 for TopicDiff: A Topic-enriched Diffusion Approach for Multimodal Conversational Emotion Detection
Figure 3 for TopicDiff: A Topic-enriched Diffusion Approach for Multimodal Conversational Emotion Detection
Figure 4 for TopicDiff: A Topic-enriched Diffusion Approach for Multimodal Conversational Emotion Detection
Viaarxiv icon

Arbitrary-Scale Point Cloud Upsampling by Voxel-Based Network with Latent Geometric-Consistent Learning

Add code
Mar 08, 2024
Figure 1 for Arbitrary-Scale Point Cloud Upsampling by Voxel-Based Network with Latent Geometric-Consistent Learning
Figure 2 for Arbitrary-Scale Point Cloud Upsampling by Voxel-Based Network with Latent Geometric-Consistent Learning
Figure 3 for Arbitrary-Scale Point Cloud Upsampling by Voxel-Based Network with Latent Geometric-Consistent Learning
Figure 4 for Arbitrary-Scale Point Cloud Upsampling by Voxel-Based Network with Latent Geometric-Consistent Learning
Viaarxiv icon

CLIP-Gaze: Towards General Gaze Estimation via Visual-Linguistic Model

Mar 08, 2024
Figure 1 for CLIP-Gaze: Towards General Gaze Estimation via Visual-Linguistic Model
Figure 2 for CLIP-Gaze: Towards General Gaze Estimation via Visual-Linguistic Model
Figure 3 for CLIP-Gaze: Towards General Gaze Estimation via Visual-Linguistic Model
Figure 4 for CLIP-Gaze: Towards General Gaze Estimation via Visual-Linguistic Model
Viaarxiv icon

Learning Expressive And Generalizable Motion Features For Face Forgery Detection

Mar 08, 2024
Figure 1 for Learning Expressive And Generalizable Motion Features For Face Forgery Detection
Figure 2 for Learning Expressive And Generalizable Motion Features For Face Forgery Detection
Figure 3 for Learning Expressive And Generalizable Motion Features For Face Forgery Detection
Figure 4 for Learning Expressive And Generalizable Motion Features For Face Forgery Detection
Viaarxiv icon

How to Understand "Support"? An Implicit-enhanced Causal Inference Approach for Weakly-supervised Phrase Grounding

Mar 04, 2024
Viaarxiv icon

Is GPT Powerful Enough to Analyze the Emotions of Memes?

Nov 01, 2023
Figure 1 for Is GPT Powerful Enough to Analyze the Emotions of Memes?
Figure 2 for Is GPT Powerful Enough to Analyze the Emotions of Memes?
Figure 3 for Is GPT Powerful Enough to Analyze the Emotions of Memes?
Figure 4 for Is GPT Powerful Enough to Analyze the Emotions of Memes?
Viaarxiv icon