Search Results for author:
Found 8 papers, 3 papers with code
Feature Representation Matters: End-to-End Learning for Reference-based Image Super-resolution
To this end, we engaged neural texture transfer to swap texture features between the low-resolution image and the high-resolution reference image.
Debiased Novel Category Discovering and Localization
In recent years, object detection in deep learning has experienced rapid development.
u-LLaVA: Unifying Multi-Modal Tasks via Large Language Model
Recent advancements in multi-modal large language models (MLLMs) have led to substantial improvements in visual understanding, primarily driven by sophisticated modality alignment strategies.
Open-Set Image Tagging with Multi-Grained Text Supervision
Specifically, for predefined commonly used tag categories, RAM++ showcases 10. 2 mAP and 15. 4 mAP enhancements over CLIP on OpenImages and ImageNet.
CLIP Brings Better Features to Visual Aesthetics Learners
Specifically, we first integrate and leverage a multi-source unlabeled dataset to align rich features between a given visual encoder and an off-the-shelf CLIP image encoder via feature alignment loss.
Recognize Anything: A Strong Image Tagging Model
We are releasing the RAM at \url{https://recognize-anything. github. io/} to foster the advancements of large models in computer vision.
Correlation Filter Selection for Visual Tracking Using Reinforcement Learning
In this paper, we propose a novel approach to address the correlation filter update problem.
IAN: The Individual Aggregation Network for Person Search
In addition, to relieve the negative effect caused by varying visual appearances of the same individual, IAN introduces a novel center loss that can increase the intra-class compactness of feature representations.
