Posts by Collection

Fine-Grained Sketch-Based Image Retrieval: The Role of Part-Aware Attributes

Published in IEEE Winter Conference on Applications of Computer Vision(WACV), 2016

In this paper, we propose to detect visual attributes at part-level, in order to build a new representation that not only captures fine-grained characteristics but also traverses across visual domains.

Recommended citation: Fine-Grained Sketch-Based Image Retrieval: The Role of Part-Aware Attributes." WACV2016. http://keli-sketchx.github.io/files/WACV2016.pdf

Synergistic Instance-Level Subspace Alignment for Fine-Grained Sketch-Based Image Retrieval

Published in TIP, 2017

In this work,we propose to bridge the image-sketch gap both at the high-level via parts and attributes, as well as at the low-level, via introducing a new domain alignment method.

Recommended citation: Synergistic Instance-Level Subspace Alignment for Fine-Grained Sketch-Based Image Retrieval." TIP. http://keli-sketchx.github.io/files/TIP2017.pdf

Universal Sketch Perceptual Grouping

Published in ECCV, 2018

In this work we aim to develop a universal sketch grouper. That is, a grouper that can be applied to sketches of any category in any domain to group constituent strokes/segments into semantically meaningful object parts. Meanwhile, we contribute the largest sketch perceptual grouping (SPG) dataset to date, consisting of 20, 000 unique sketches evenly distributed over 25 object categories.

Recommended citation: Universal Sketch Perceptual Grouping." ECCV2018. http://keli-sketchx.github.io/files/ECCV2018.pdf

Generalising Fine-Grained Sketch-Based Image Retrieval

Published in CVPR2019, 2019

In this paper, we identify cross-category generalisation for FG-SBIR as a domain generalisation problem, and propose the first solution. Our key contribution is a novel unsupervised learning approach to model a universal manifold of prototypical visual sketch traits.

Recommended citation: Generalising Fine-Grained Sketch-Based Image Retrieval." CVPR2019. http://keli-sketchx.github.io/files/CVPR2019.pdf

Variational Attention: Propagating Domain-Specific Knowledge for Multi-Domain Learning in Crowd Counting

Published in ICCV, 2021

In this paper, we resort to the multi-domain joint learning and propose a simple but effective Domain-specific Knowledge Propagating Network (DKPNet) for unbiasedly learning the knowledge from multiple diverse data domains at the same time.

Recommended citation: Variational Attention: Propagating Domain-Specific Knowledge for Multi-Domain Learning in Crowd Counting." ICCV. https://arxiv.org/abs/2108.08023

Teaching experience 1

Undergraduate course, University 1, Department, 2014

This is a description of a teaching experience. You can use markdown like any other post.

Teaching experience 2

Workshop, University 1, Department, 2015

This is a description of a teaching experience. You can use markdown like any other post.