We tackle the data scarcity challenge in few-shot point cloud recognitio...
Typical layout-to-image synthesis (LIS) models generate images for a clo...
Exemplar-based class-incremental learning (CIL) finetunes the model with...
Weakly Supervised Video Anomaly Detection (WSVAD) is challenging because...
Extracting class activation maps (CAM) from a classification model often...
Semantic Scene Completion (SSC) transforms an image of single-view depth...
Class-Incremental Learning (CIL) [40] trains classifiers under a strict
...
Class-incremental learning (CIL) aims to train a classification model wh...
Extracting class activation maps (CAM) is a key step for weakly-supervis...
Cross-modal video retrieval aims to retrieve the semantically relevant v...
Out-Of-Distribution generalization (OOD) is all about learning invarianc...
We are interested in learning robust models from insufficient data, with...
Face clustering is a promising way to scale up face recognition systems ...
Extracting class activation maps (CAM) is arguably the most standard ste...
We focus on the confounding bias between language and location in the vi...
A good visual representation is an inference map from observations (imag...
Attention module does not always help deep models learn causal features ...
Existing Unsupervised Domain Adaptation (UDA) literature adopts the cova...
Food image segmentation is a critical and indispensible task for develop...
We present a novel counterfactual framework for both Zero-Shot Learning ...
Deep neural network based question answering (QA) models are neither rob...
Class-Incremental Learning (CIL) aims to learn a classification model wi...
We uncover an ever-overlooked deficiency in the prevailing Few-Shot Lear...
We present a causal inference framework to improve Weakly-Supervised Sem...
Feature interactions across space and scales underpin modern visual
reco...
We present a novel unsupervised feature representation learning method,
...
Multi-Class Incremental Learning (MCIL) aims to learn new concepts by
in...
Meta-learning has been proposed as a framework to address the challengin...
Few-shot classification (FSC) is challenging due to the scarcity of labe...
Image-to-image (I2I) translation is a pixel-level mapping that requires ...
Meta-learning has been shown to be an effective strategy for few-shot
le...
We propose a novel approach to jointly perform 3D object retrieval and p...
Meta-learning has been proposed as a framework to address the challengin...
As more and more personal photos are shared and tagged in social media,
...
Generating novel, yet realistic, images of persons is a challenging task...
As more and more personal photos are shared online, being able to obfusc...
This paper proposes the novel Pose Guided Person Generation Network (PG^...