Search Results for author:
Found 11 papers, 2 papers with code
SGC-Net: Stratified Granular Comparison Network for Open-Vocabulary HOI Detection
Despite their effectiveness, these methods face two challenges: (1) feature granularity deficiency, due to reliance on last layer visual features for text alignment, leading to the neglect of crucial object-level details from intermediate layers; (2) semantic similarity confusion, resulting from CLIP's inherent biases toward certain classes, while LLM-generated descriptions based solely on labels fail to adequately capture inter-class similarities.
Refining Positive and Toxic Samples for Dual Safety Self-Alignment of LLMs with Minimal Human Interventions
The MLE loss encourages an LLM to maximize the generation of harmless content based on positive samples.
Efficient Streaming Voice Steganalysis in Challenging Detection Scenarios
Ultimately, this method effectively address the detection difficulty in VoIP.
Beyond Statistical Estimation: Differentially Private Individual Computation via Shuffling
PIC enables personalized outputs while preserving privacy, and enjoys privacy amplification through shuffling.
ContextBLIP: Doubly Contextual Alignment for Contrastive Image Retrieval from Linguistically Complex Descriptions
The main challenges lie in aligning key contextual cues in two modalities, where these subtle cues are concealed in tiny areas of multiple contrastive images and within the complex linguistics of textual descriptions.
GanFinger: GAN-Based Fingerprint Generation for Deep Neural Network Ownership Verification
To address these issues, we propose a network fingerprinting approach, named as GanFinger, to construct the network fingerprints based on the network behavior, which is characterized by network outputs of pairs of original examples and conferrable adversarial examples.
Auto-Focus Contrastive Learning for Image Manipulation Detection
However, we argue that those models achieve sub-optimal detection performance as it tends to: 1) distinguish the manipulation traces from a lot of noisy information within the entire image, and 2) ignore the trace relations among the pixels of each manipulated region and its surroundings.
Traceable and Authenticable Image Tagging for Fake News Detection
Extensive experiments, on diverse datasets and unseen manipulations, demonstrate that the proposed tagging approach achieves excellent performance in the aspects of both authenticity verification and source tracing for reliable fake news detection and outperforms the prior works.
Real-World Image Super Resolution via Unsupervised Bi-directional Cycle Domain Transfer Learning based Generative Adversarial Network
First, the UBCDTN is able to produce an approximated real-like LR image through transferring the LR image from an artificially degraded domain to the real-world LR image domain.
Continual Learning for Steganalysis
To detect the existing steganographic algorithms, recent steganalysis methods usually train a Convolutional Neural Network (CNN) model on the dataset consisting of corresponding paired cover/stego-images.
Learning Hierarchical Graph Representation for Image Manipulation Detection
The objective of image manipulation detection is to identify and locate the manipulated regions in the images.
