Picture for Fanman Meng

Fanman Meng

On the Adversarial Robustness of Learning-based Image Compression Against Rate-Distortion Attacks

Add code
May 13, 2024
Viaarxiv icon

GRSDet: Learning to Generate Local Reverse Samples for Few-shot Object Detection

Dec 29, 2023
Viaarxiv icon

Learning with Noisy Low-Cost MOS for Image Quality Assessment via Dual-Bias Calibration

Nov 27, 2023
Viaarxiv icon

Cross-modal Cognitive Consensus guided Audio-Visual Segmentation

Oct 10, 2023
Viaarxiv icon

Towards Continual Egocentric Activity Recognition: A Multi-modal Egocentric Activity Dataset for Continual Learning

Jan 26, 2023
Figure 1 for Towards Continual Egocentric Activity Recognition: A Multi-modal Egocentric Activity Dataset for Continual Learning
Figure 2 for Towards Continual Egocentric Activity Recognition: A Multi-modal Egocentric Activity Dataset for Continual Learning
Figure 3 for Towards Continual Egocentric Activity Recognition: A Multi-modal Egocentric Activity Dataset for Continual Learning
Figure 4 for Towards Continual Egocentric Activity Recognition: A Multi-modal Egocentric Activity Dataset for Continual Learning
Viaarxiv icon

Forgetting to Remember: A Scalable Incremental Learning Framework for Cross-Task Blind Image Quality Assessment

Add code
Sep 15, 2022
Figure 1 for Forgetting to Remember: A Scalable Incremental Learning Framework for Cross-Task Blind Image Quality Assessment
Figure 2 for Forgetting to Remember: A Scalable Incremental Learning Framework for Cross-Task Blind Image Quality Assessment
Figure 3 for Forgetting to Remember: A Scalable Incremental Learning Framework for Cross-Task Blind Image Quality Assessment
Figure 4 for Forgetting to Remember: A Scalable Incremental Learning Framework for Cross-Task Blind Image Quality Assessment
Viaarxiv icon

RefCrowd: Grounding the Target in Crowd with Referring Expressions

Add code
Jun 16, 2022
Figure 1 for RefCrowd: Grounding the Target in Crowd with Referring Expressions
Figure 2 for RefCrowd: Grounding the Target in Crowd with Referring Expressions
Figure 3 for RefCrowd: Grounding the Target in Crowd with Referring Expressions
Figure 4 for RefCrowd: Grounding the Target in Crowd with Referring Expressions
Viaarxiv icon

Non-Homogeneous Haze Removal via Artificial Scene Prior and Bidimensional Graph Reasoning

Add code
Apr 05, 2021
Figure 1 for Non-Homogeneous Haze Removal via Artificial Scene Prior and Bidimensional Graph Reasoning
Figure 2 for Non-Homogeneous Haze Removal via Artificial Scene Prior and Bidimensional Graph Reasoning
Figure 3 for Non-Homogeneous Haze Removal via Artificial Scene Prior and Bidimensional Graph Reasoning
Figure 4 for Non-Homogeneous Haze Removal via Artificial Scene Prior and Bidimensional Graph Reasoning
Viaarxiv icon

A New Local Transformation Module for Few-shot Segmentation

Nov 12, 2019
Figure 1 for A New Local Transformation Module for Few-shot Segmentation
Figure 2 for A New Local Transformation Module for Few-shot Segmentation
Figure 3 for A New Local Transformation Module for Few-shot Segmentation
Figure 4 for A New Local Transformation Module for Few-shot Segmentation
Viaarxiv icon

Subjective and Objective De-raining Quality Assessment Towards Authentic Rain Image

Add code
Oct 06, 2019
Figure 1 for Subjective and Objective De-raining Quality Assessment Towards Authentic Rain Image
Figure 2 for Subjective and Objective De-raining Quality Assessment Towards Authentic Rain Image
Figure 3 for Subjective and Objective De-raining Quality Assessment Towards Authentic Rain Image
Figure 4 for Subjective and Objective De-raining Quality Assessment Towards Authentic Rain Image
Viaarxiv icon