Search Results for author:
Found 12 papers, 6 papers with code
New Threats against Object Detector with Non-local Block
The experiments show that the universal patches are able to mislead the detector with greater probabilities.
MACE: Mass Concept Erasure in Diffusion Models
In this paper, we introduce MACE, a finetuning framework for the task of mass concept erasure.
TF-ICON: Diffusion-Based Training-Free Cross-Domain Image Composition
In this paper, we propose TF-ICON, a novel Training-Free Image COmpositioN framework that harnesses the power of text-driven diffusion models for cross-domain image-guided composition.
Audio-Visual Deception Detection: DOLOS Dataset and Parameter-Efficient Crossmodal Learning
Despite this, deception detection research is hindered by the lack of high-quality deception datasets, as well as the difficulties of learning multimodal features effectively.
A Practical Upper Bound for the Worst-Case Attribution Deviations
Model attribution is a critical component of deep neural networks (DNNs) for its interpretability to complex models.
Flexible-modal Deception Detection with Audio-Visual Adapter
Detecting deception by human behaviors is vital in many fields such as custom security and multimedia anti-fraud.
Portmanteauing Features for Scene Text Recognition
To generate the portmanteau feature, a non-linear input pipeline with a block matrix initialization is presented.
Pure Transformer with Integrated Experts for Scene Text Recognition
PTIE is a transformer model that can process multiple patch resolutions and decode in both the original and reverse character orders.
A fully differentiable ligand pose optimization framework guided by deep learning and traditional scoring functions
In this work, we propose a fully differentiable framework for ligand pose optimization based on a hybrid scoring function (SF) combined with a multi-layer perceptron (DeepRMSD) and the traditional AutoDock Vina SF.
Transferable Adversarial Attack based on Integrated Gradients
The vulnerability of deep neural networks to adversarial examples has drawn tremendous attention from the community.
Exploiting the Relationship Between Kendall's Rank Correlation and Cosine Similarity for Attribution Protection
In this paper, we first show that the expected Kendall's rank correlation is positively correlated to cosine similarity and then indicate that the direction of attribution is the key to attribution robustness.
The Nipple-Areola Complex for Criminal Identification
In digital and multimedia forensics, identification of child sexual offenders based on digital evidence images is highly challenging due to the fact that the offender's face or other obvious characteristics such as tattoos are occluded, covered, or not visible at all.
