This paper proposes a new active learning method for semantic segmentati...
A common practice in metric learning is to train and test an embedding m...
Referring image segmentation, the task of segmenting any arbitrary entit...
We live in a vast ocean of data, and deep neural networks are no excepti...
In a joint vision-language space, a text feature (e.g., from "a photo of...
Learning semantic segmentation requires pixel-wise annotations, which ca...
We study human pose estimation in extremely low-light images. This task ...
Supervision for metric learning has long been given in the form of
equiv...
This paper presents the first attempt to learn semantic boundary detecti...
Cross-modal retrieval across image and text modalities is a challenging ...
Domain generalization is the task of learning models that generalize to
...
Metric learning aims to build a distance metric typically by learning an...
We consider the problem of active domain adaptation (ADA) to unlabeled t...
Neural networks are prone to be biased towards spurious correlations bet...
We present a novel self-taught framework for unsupervised metric learnin...
Group activity recognition is the task of understanding the activity
con...
This paper studies semi-supervised learning of semantic segmentation, wh...
Robust visual recognition under adverse weather conditions is of great
i...
The inherent challenge of detecting symmetries stems from arbitrary
orie...
Referring image segmentation is an advanced semantic segmentation task w...
Grounded situation recognition is the task of predicting the main activi...
Deep metric learning aims to learn an embedding space where the distance...
Grounded Situation Recognition (GSR) is the task that not only classifie...
Convolution has been arguably the most important feature transform for m...
Domain generalization for semantic segmentation is highly demanded in re...
Attribute-based person search is the task of finding person images that ...
This paper studies probability distributions of penultimate activations ...
This paper presents a novel method for embedding transfer, a task of
tra...
Spatio-temporal convolution often fails to learn motion dynamics in vide...
Motion plays a crucial role in understanding videos and most state-of-th...
Despite the great advances in visual recognition, it has been witnessed ...
Existing metric learning losses can be categorized into two classes:
pai...
Metric Learning for visual similarity has mostly adopted binary supervis...
Bounding-box regression is a popular technique to refine or predict
loca...
This paper presents a novel approach for learning instance segmentation ...
The deficiency of segmentation labels is one of the main obstacles to
se...
We propose a novel algorithm for weakly supervised semantic segmentation...
We propose an online visual tracking algorithm by learning discriminativ...
This paper addresses unsupervised discovery and localization of dominant...