As a promising field, Multi-Query Image Retrieval (MQIR) aims at searchi...
As a fundamental and challenging task in bridging language and vision
do...
Few-shot Class-Incremental Learning (FSCIL) aims at learning new concept...
Video-text retrieval (VTR) is an attractive yet challenging task for
mul...
General Continual Learning (GCL) aims at learning from non independent a...
The domain shift between the source and target domain is the main challe...
Semantic information provides intra-class consistency and inter-class
di...
Image-text matching plays a central role in bridging the semantic gap be...
Image-text matching plays a central role in bridging vision and language...
We propose a Generative Transfer Network (GTNet) for zero shot object
de...
Zero-Shot Classification (ZSC) equips the learned model with the ability...
This paper studies the task of matching image and sentence, where learni...
Existing generative Zero-Shot Learning (ZSL) methods only consider the
u...
Zero-Shot Learning (ZSL) is achieved via aligning the semantic relations...
Zero-Shot Hashing aims at learning a hashing model that is trained only ...
Zero-Shot Learning (ZSL) is typically achieved by resorting to a class
s...
Given the explosive growth of online videos, it is becoming increasingly...
A typical pipeline for Zero-Shot Learning (ZSL) is to integrate the visu...
Zero-shot learning (ZSL) endows the computer vision system with the
infe...
As an important and challenging problem in computer vision, zero-shot
le...
Zero-shot learning (ZSL) extends the conventional image classification
t...