Search Results for author:
Found 4 papers, 2 papers with code
Artwork Protection Against Neural Style Transfer Using Locally Adaptive Adversarial Color Attack
Neural style transfer (NST) generates new images by combining the style of one image with the content of another.
Semi-Supervised Crowd Counting with Contextual Modeling: Facilitating Holistic Understanding of Crowd Scenes
To alleviate the heavy annotation burden for training a reliable crowd counting model and thus make the model more practicable and accurate by being able to benefit from more data, this paper presents a new semi-supervised method based on the mean teacher framework.
Multimodal Latent Emotion Recognition from Micro-expression and Physiological Signals
Experimental results show that the proposed approach outperforms the benchmark method, with the weighted fusion method and guided attention modules both contributing to enhanced performance.
A White-Box False Positive Adversarial Attack Method on Contrastive Loss Based Offline Handwritten Signature Verification Models
The key contributions of this paper include a novel false positive attack method, two new loss functions, effective style transfer in handwriting styles, and superior performance in white-box false positive attacks compared to other white-box attack methods.
