Artificial Intelligence Generated Content (AIGC) has shown remarkable
pr...
3D shape modeling is labor-intensive and time-consuming and requires yea...
Recently, text-guided 3D generative methods have made remarkable advance...
This paper, for the very first time, introduces human sketches to the
la...
Generative modelling over continuous-time geometric constructs, a.k.a su...
Sketches are highly expressive, inherently capturing subjective and
fine...
We propose a new formulation of temporal action detection (TAD) with
den...
This paper studies the problem of zero-short sketch-based image retrieva...
This paper advances the fine-grained sketch-based image retrieval (FG-SB...
In this paper, we leverage CLIP for zero-shot sketch based image retriev...
Human sketch has already proved its worth in various visual understandin...
Given an abstract, deformed, ordinary sketch from untrained amateurs lik...
Rising concerns about privacy and anonymity preservation of deep learnin...
Target domain pseudo-labelling has shown effectiveness in unsupervised d...
In the fashion domain, there exists a variety of vision-and-language (V+...
Existing unsupervised hashing methods typically adopt a feature similari...
The main challenge for fine-grained few-shot image classification is to ...
Existing Temporal Action Detection (TAD) methods typically take a
pre-pr...
Few-shot (FS) and zero-shot (ZS) learning are two different approaches f...
Multi-pose virtual try-on (MPVTON) aims to fit a target garment onto a p...
Machine learning models are intrinsically vulnerable to domain shift bet...
Generalized Few-shot Semantic Segmentation (GFSS) aims to segment each i...
Given multiple labeled source domains and a single target domain, most
e...
Growing free online 3D shapes collections dictated research on 3D retrie...
We present the first fine-grained dataset of 1,497 3D VR sketch and 3D s...
We study the practical task of fine-grained 3D-VR-sketch-based 3D shape
...
Multiple sketch datasets have been proposed to understand how people dra...
Reconstructing a 3D shape based on a single sketch image is challenging ...
Existing temporal action detection (TAD) methods rely on large training ...
Large-scale Vision-and-Language (V+L) pre-training for representation
le...
Existing temporal action detection (TAD) methods rely on a large number ...
Existing temporal action detection (TAD) methods rely on generating an
o...
The recent focus on Fine-Grained Sketch-Based Image Retrieval (FG-SBIR) ...
We for the first time extend multi-modal scene understanding to include ...
Interactive garment retrieval (IGR) aims to retrieve a target garment im...
Image-based virtual try-on aims to fit an in-shop garment into a clothed...
The human visual system is remarkable in learning new visual concepts fr...
Sketching enables many exciting applications, notably, image retrieval. ...
We scrutinise an important observation plaguing scene-level sketch resea...
Zero-shot sketch-based image retrieval typically asks for a trained mode...
Most existing studies on unsupervised domain adaptation (UDA) assume tha...
We advance sketch research to scenes with the first dataset of freehand ...
We present the first one-shot personalized sketch segmentation method. W...
Graph neural networks (GNNs) have been used to tackle the few-shot learn...
Despite great strides made on fine-grained visual classification (FGVC),...
As powerful as fine-grained visual classification (FGVC) is, responding ...
Fine-grained image analysis (FGIA) is a longstanding and fundamental pro...
A deep hashing model typically has two main learning objectives: to make...
The key challenge in designing a sketch representation lies with handlin...
A few-shot semantic segmentation model is typically composed of a CNN
en...