Picture for Shijian Deng

Shijian Deng

AV-DiT: Efficient Audio-Visual Diffusion Transformer for Joint Audio and Video Generation

Add code
Jun 11, 2024
Viaarxiv icon

Separating Invisible Sounds Toward Universal Audiovisual Scene-Aware Sound Separation

Add code
Oct 18, 2023
Figure 1 for Separating Invisible Sounds Toward Universal Audiovisual Scene-Aware Sound Separation
Figure 2 for Separating Invisible Sounds Toward Universal Audiovisual Scene-Aware Sound Separation
Figure 3 for Separating Invisible Sounds Toward Universal Audiovisual Scene-Aware Sound Separation
Figure 4 for Separating Invisible Sounds Toward Universal Audiovisual Scene-Aware Sound Separation
Viaarxiv icon

Unveiling Cross Modality Bias in Visual Question Answering: A Causal View with Possible Worlds VQA

Add code
May 31, 2023
Figure 1 for Unveiling Cross Modality Bias in Visual Question Answering: A Causal View with Possible Worlds VQA
Figure 2 for Unveiling Cross Modality Bias in Visual Question Answering: A Causal View with Possible Worlds VQA
Figure 3 for Unveiling Cross Modality Bias in Visual Question Answering: A Causal View with Possible Worlds VQA
Figure 4 for Unveiling Cross Modality Bias in Visual Question Answering: A Causal View with Possible Worlds VQA
Viaarxiv icon