![Loading...](https://link.springer.com/static/c4a417b97a76cc2980e3c25e2271af3129e08bbe/images/pdf-preview/spacer.gif)
-
Chapter and Conference Paper
Cross-Modulated Few-Shot Image Generation for Colorectal Tissue Classification
In this work, we propose a few-shot colorectal tissue image generation method for addressing the scarcity of histopathological training data for rare cancer tissues. Our few-shot generation method, named XM-GA...
-
Chapter and Conference Paper
EdgeNeXt: Efficiently Amalgamated CNN-Transformer Architecture for Mobile Vision Applications
In the pursuit of achieving ever-increasing accuracy, large and complex neural networks are usually developed. Such models demand high computational resources and therefore cannot be deployed on edge devices. ...
-
Chapter and Conference Paper
Anchor-ReID: A Test Time Adaptation for Person Re-identification
Person re-identification (ReID) is a challenging computer vision problem where the objective is to retrieve a person of interest from a gallery of images. Conventional person ReID methods struggle to generaliz...
-
Chapter and Conference Paper
RadarFormer: Lightweight and Accurate Real-Time Radar Object Detection Model
The performance of perception systems developed for autonomous driving vehicles has seen significant improvements over the last few years. This improvement was associated with the increasing use of LiDAR senso...
-
Chapter and Conference Paper
PS-ARM: An End-to-End Attention-Aware Relation Mixer Network for Person Search
Person search is a challenging problem with various real-world applications, that aims at joint person detection and re-identification of a query person from uncropped gallery images. Although, previous study ...
-
Chapter and Conference Paper
DoodleFormer: Creative Sketch Drawing with Transformers
Creative sketching or doodling is an expressive activity, where imaginative and previously unseen depictions of everyday visual objects are drawn. Creative sketch image generation is a challenging vision probl...
-
Chapter and Conference Paper
Video Instance Segmentation via Multi-Scale Spatio-Temporal Split Attention Transformer
State-of-the-art transformer-based video instance segmentation (VIS) approaches typically utilize either single-scale spatio-temporal features or per-frame multi-scale features during the attention computation...
-
Chapter and Conference Paper
Count- and Similarity-Aware R-CNN for Pedestrian Detection
Recent pedestrian detection methods generally rely on additional supervision, such as visible bounding-box annotations, to handle heavy occlusions. We propose an approach that leverages pedestrian count and pr...
-
Chapter and Conference Paper
SipMask: Spatial Information Preservation for Fast Image and Video Instance Segmentation
Single-stage instance segmentation approaches have recently gained popularity due to their speed and simplicity, but are still lagging behind in accuracy, compared to two-stage methods. We propose a fast singl...
-
Chapter and Conference Paper
Fixing Localization Errors to Improve Image Classification
Deep neural networks are generally considered black-box models that offer less interpretability for their decision process. To address this limitation, Class Activation Map (CAM) provides an attractive solutio...