Textdiffuser: Diffusion models as text painters
Diffusion models have gained increasing attention for their impressive generation abilities
but currently struggle with rendering accurate and coherent text. To address this issue, we …
but currently struggle with rendering accurate and coherent text. To address this issue, we …
Vehicle-damage-detection segmentation algorithm based on improved mask RCNN
Q Zhang, X Chang, SB Bian - IEEE Access, 2020 - ieeexplore.ieee.org
Traffic congestion due to vehicular accidents seriously affects normal travel, and accurate
and effective mitigating measures and methods must be studied. To resolve traffic accident …
and effective mitigating measures and methods must be studied. To resolve traffic accident …
BRPPNet: Balanced privacy protection network for referring personal image privacy protection
Traditional personal image privacy protection usually suffers from the overprotection
problem, where one or more undesired persons in an image may be inevitably shielded …
problem, where one or more undesired persons in an image may be inevitably shielded …
Tpsnet: Reverse thinking of thin plate splines for arbitrary shape scene text representation
W Wang, Y Zhou, J Lv, D Wu, G Zhao, N Jiang… - Proceedings of the 30th …, 2022 - dl.acm.org
The research focus of scene text detection and recognition has shifted to arbitrary shape text
in recent years, where the text shape representation is a fundamental problem. An ideal …
in recent years, where the text shape representation is a fundamental problem. An ideal …
A new DCT-PCM method for license plate number detection in drone images
H Mokayed, P Shivakumara, HH Woon… - Pattern Recognition …, 2021 - Elsevier
License plate number detection in drone images is a complex problem because the images
are generally captured at oblique angles and pose several challenges like perspective …
are generally captured at oblique angles and pose several challenges like perspective …
Piglet: Pixel-level grounding of language expressions with transformers
This paper proposes Panoptic Narrative Grounding, a spatially fine and general formulation
of the natural language visual grounding problem. We establish an experimental framework …
of the natural language visual grounding problem. We establish an experimental framework …
Panoptic narrative grounding
Abstract This paper proposes Panoptic Narrative Grounding, a spatially fine and general
formulation of the natural language visual grounding problem. We establish an experimental …
formulation of the natural language visual grounding problem. We establish an experimental …
Geometry sensitive cross-modal reasoning for composed query based image retrieval
Composed Query Based Image Retrieval (CQBIR) aims at retrieving images relevant to a
composed query containing a reference image with a requested modification expressed via …
composed query containing a reference image with a requested modification expressed via …
License plate number detection in drone images
H Mokayed, P Shivakumara… - Artificial Intelligence …, 2025 - ojs.bonviewpress.com
This work aims to figure out a way to accurately identify license plate numbers in photos
taken by drones. This technology is used in practical applications like managing parking and …
taken by drones. This technology is used in practical applications like managing parking and …
ScanFormer: Referring Expression Comprehension by Iteratively Scanning
Abstract Referring Expression Comprehension (REC) aims to localize the target objects
specified by free-form natural language descriptions in images. While state-of-the-art …
specified by free-form natural language descriptions in images. While state-of-the-art …