Boosting transferability in vision-language attacks via diversification along the intersection region of adversarial trajectory
Vision-language pre-training (VLP) models exhibit remarkable capabilities in
comprehending both images and text, yet they remain susceptible to multimodal adversarial …
comprehending both images and text, yet they remain susceptible to multimodal adversarial …
Pedestrian attribute recognition via clip based prompt vision-language fusion
Existing pedestrian attribute recognition (PAR) algorithms adopt pre-trained CNN (eg,
ResNet) as their backbone network for visual feature learning, which might obtain sub …
ResNet) as their backbone network for visual feature learning, which might obtain sub …
Triplane-Smoothed Video Dehazing with CLIP-Enhanced Generalization
Video dehazing is a critical research area in computer vision that aims to enhance the
quality of hazy frames, which benefits many downstream tasks, eg semantic segmentation …
quality of hazy frames, which benefits many downstream tasks, eg semantic segmentation …
Evaluating fairness in large vision-language models across diverse demographic attributes and prompts
Large vision-language models (LVLMs) have recently achieved significant progress,
demonstrating strong capabilities in open-world visual understanding. However, it is not yet …
demonstrating strong capabilities in open-world visual understanding. However, it is not yet …
CLIP-Gaze: Towards General Gaze Estimation via Visual-Linguistic Model
Gaze estimation methods often experience significant performance degradation when
evaluated across different domains, due to the domain gap between the testing and training …
evaluated across different domains, due to the domain gap between the testing and training …
Light the Night: A Multi-Condition Diffusion Framework for Unpaired Low-Light Enhancement in Autonomous Driving
Vision-centric perception systems for autonomous driving have gained considerable
attention recently due to their cost-effectiveness and scalability especially compared to …
attention recently due to their cost-effectiveness and scalability especially compared to …
Plgan: Generative adversarial networks for power-line segmentation in aerial images
Accurate segmentation of power lines in various aerial images is very important for UAV
flight safety. The complex background and very thin structures of power lines, however …
flight safety. The complex background and very thin structures of power lines, however …
Task2Box: Box Embeddings for Modeling Asymmetric Task Relationships
Modeling and visualizing relationships between tasks or datasets is an important step
towards solving various meta-tasks such as dataset discovery multi-tasking and transfer …
towards solving various meta-tasks such as dataset discovery multi-tasking and transfer …
Adaptive mixed-scale feature fusion network for blind AI-generated image quality assessment
With the increasing maturity of the text-to-image and image-to-image generative models, AI-
generated images (AGIs) have shown great application potential in advertisement …
generated images (AGIs) have shown great application potential in advertisement …
Multi-label cluster discrimination for visual representation learning
Abstract Contrastive Language Image Pre-training (CLIP) has recently demonstrated
success across various tasks due to superior feature representation empowered by image …
success across various tasks due to superior feature representation empowered by image …