71 citations · 280 across the 25 of their papers we have counts for
26 papers
Focus on Background: Exploring SAM's Potential in Few-shot Medical Image Segmentation with Background-centric Prompting
Yuntian Bo, Yazhou Zhu, Piotr Koniusz +1
Conventional few-shot medical image segmentation (FSMIS) approaches face performance bottlenecks that hinder broader clinical applicability. Although the Segment Anything Model (SA…
Event-guided Multi-patch Network with Self-supervision for Non-uniform Motion Deblurring
Hongguang Zhang, Limeng Zhang, Yuchao Dai +2
Contemporary deep learning multi-scale deblurring models suffer from many issues: 1) They perform poorly on non-uniformly blurred images/videos; 2) Simply increasing the model dept…
Accurate 3-DoF Camera Geo-Localization via Ground-to-Satellite Image Matching
Yujiao Shi, Xin Yu, Liu Liu +3
We address the problem of ground-to-satellite image geo-localization, that is, estimating the camera latitude, longitude and orientation (azimuth angle) by matching a query image c…
Simple Dialogue System with AUDITED
Yusuf Tas, Piotr Koniusz
We devise a multimodal conversation system for dialogue utterances composed of text, image or both modalities. We leverage Auxiliary UnsuperviseD vIsual and TExtual Data (AUDITED).…
Power Normalizations in Fine-grained Image, Few-shot Image and Graph Classification
Piotr Koniusz, Hongguang Zhang
Power Normalizations (PN) are useful non-linear operators which tackle feature imbalances in classification problems. We study PNs in the deep learning setup via a novel PN layer p…
6DoF Object Pose Estimation via Differentiable Proxy Voting Loss
Xin Yu, Zheyu Zhuang, Piotr Koniusz +1
Estimating a 6DOF object pose from a single image is very challenging due to occlusions or textureless appearances. Vector-field based keypoint voting has demonstrated its effectiv…
Rethinking Class Relations: Absolute-relative Supervised and Unsupervised Few-shot Learning
Hongguang Zhang, Piotr Koniusz, Songlei Jian +2
The majority of existing few-shot learning methods describe image relations with binary labels. However, such binary relations are insufficient to teach the network complicated rea…
Few-shot Action Recognition with Permutation-invariant Attention
Hongguang Zhang, Li Zhang, Xiaojuan Qi +3
Many few-shot learning models focus on recognising images. In contrast, we tackle a challenging task of few-shot action recognition from videos. We build on a C3D encoder for spati…
Improving Few-shot Learning by Spatially-aware Matching and CrossTransformer
Hongguang Zhang, Philip H. S. Torr, Piotr Koniusz
Current few-shot learning models capture visual object relations in the so-called meta-learning setting under a fixed-resolution input. However, such models have a limited generali…
Identity-preserving Face Recovery from Stylized Portraits
Fatemeh Shiri, Xin Yu, Fatih Porikli +2
Given an artistic portrait, recovering the latent photorealistic face that preserves the subject's identity is challenging because the facial details are often distorted or fully l…
Recovering Faces from Portraits with Auxiliary Facial Attributes
Fatemeh Shiri, Xin Yu, Fatih Porikli +2
Recovering a photorealistic face from an artistic portrait is a challenging task since crucial facial details are often distorted or completely lost in artistic compositions. To ha…
Few-Shot Learning via Saliency-guided Hallucination of Samples
Hongguang Zhang, Jing Zhang, Piotr Koniusz
Learning new concepts from a few of samples is a standard challenge in computer vision. The main directions to improve the learning ability of few-shot training models include (i)…
Deep Stacked Hierarchical Multi-patch Network for Image Deblurring
Hongguang Zhang, Yuchao Dai, Hongdong Li +1
Despite deep end-to-end learning methods have shown their superiority in removing non-uniform motion blur, there still exist major challenges with the current multi-scale and scale…
Power Normalizing Second-order Similarity Network for Few-shot Learning
Hongguang Zhang, Piotr Koniusz
Second- and higher-order statistics of data points have played an important role in advancing the state of the art on several computer vision problems such as the fine-grained imag…
Model Selection for Generalized Zero-shot Learning
Hongguang Zhang, Piotr Koniusz
In the problem of generalized zero-shot learning, the datapoints from unknown classes are not available during training. The main challenge for generalized zero-shot learning is th…
A Deeper Look at Power Normalizations
Piotr Koniusz, Hongguang Zhang, Fatih Porikli
Power Normalizations (PN) are very useful non-linear operators in the context of Bag-of-Words data representations as they tackle problems such as feature imbalance. In this paper,…
Artwork Identification from Wearable Camera Images for Enhancing Experience of Museum Audiences
Rui Zhang, Yusuf Tas, Piotr Koniusz
Recommendation systems based on image recognition could prove a vital tool in enhancing the experience of museum audiences. However, for practical systems utilizing wearable camera…
CNN-based Action Recognition and Supervised Domain Adaptation on 3D Body Skeletons via Kernel Feature Maps
Yusuf Tas, Piotr Koniusz
Deep learning is ubiquitous across many areas areas of computer vision. It often requires large scale datasets for training before being fine-tuned on small-to-medium scale problem…
Face Destylization
Fatemeh Shiri, Xin Yu, Fatih Porikli +1
Numerous style transfer methods which produce artistic styles of portraits have been proposed to date. However, the inverse problem of converting the stylized portraits back into r…
Identity-preserving Face Recovery from Portraits
Fatemeh Shiri, Xin Yu, Fatih Porikli +2
Recovering the latent photorealistic faces from their artistic portraits aids human perception and facial analysis. However, a recovery process that can preserve identity is challe…
Museum Exhibit Identification Challenge for Domain Adaptation and Beyond
Piotr Koniusz, Yusuf Tas, Hongguang Zhang +3
In this paper, we approach an open problem of artwork identification and propose a new dataset dubbed Open Museum Identification Challenge (Open MIC). It contains photos of exhibit…
Zero-Shot Kernel Learning
Hongguang Zhang, Piotr Koniusz
In this paper, we address an open problem of zero-shot learning. Its principle is based on learning a mapping that associates feature vectors extracted from i.e. images and attribu…
Higher-order Pooling of CNN Features via Kernel Linearization for Action Recognition
Anoop Cherian, Piotr Koniusz, Stephen Gould
Most successful deep learning algorithms for action recognition extend models designed for image-based tasks such as object recognition to video. Such extensions are typically trai…
Domain Adaptation by Mixture of Alignments of Second- or Higher-Order Scatter Tensors
Piotr Koniusz, Yusuf Tas, Fatih Porikli
In this paper, we propose an approach to the domain adaptation, dubbed Second- or Higher-order Transfer of Knowledge (So-HoT), based on the mixture of alignments of second- or high…