Picture for Jimin Pi

Jimin Pi

Semantic Diffusion Network for Semantic Segmentation

Add code
Feb 04, 2023
Viaarxiv icon

Augmentation Matters: A Simple-yet-Effective Approach to Semi-supervised Semantic Segmentation

Add code
Dec 09, 2022
Figure 1 for Augmentation Matters: A Simple-yet-Effective Approach to Semi-supervised Semantic Segmentation
Figure 2 for Augmentation Matters: A Simple-yet-Effective Approach to Semi-supervised Semantic Segmentation
Figure 3 for Augmentation Matters: A Simple-yet-Effective Approach to Semi-supervised Semantic Segmentation
Figure 4 for Augmentation Matters: A Simple-yet-Effective Approach to Semi-supervised Semantic Segmentation
Viaarxiv icon

Instance-specific and Model-adaptive Supervision for Semi-supervised Semantic Segmentation

Add code
Nov 21, 2022
Viaarxiv icon

Beyond Attentive Tokens: Incorporating Token Importance and Diversity for Efficient Vision Transformers

Add code
Nov 21, 2022
Viaarxiv icon

CAE v2: Context Autoencoder with CLIP Target

Add code
Nov 17, 2022
Figure 1 for CAE v2: Context Autoencoder with CLIP Target
Figure 2 for CAE v2: Context Autoencoder with CLIP Target
Figure 3 for CAE v2: Context Autoencoder with CLIP Target
Figure 4 for CAE v2: Context Autoencoder with CLIP Target
Viaarxiv icon

Multimodal Utterance-level Affect Analysis using Visual, Audio and Text Features

Add code
May 04, 2018
Figure 1 for Multimodal Utterance-level Affect Analysis using Visual, Audio and Text Features
Figure 2 for Multimodal Utterance-level Affect Analysis using Visual, Audio and Text Features
Figure 3 for Multimodal Utterance-level Affect Analysis using Visual, Audio and Text Features
Figure 4 for Multimodal Utterance-level Affect Analysis using Visual, Audio and Text Features
Viaarxiv icon