Classification is a strong baseline for deep metric learning
Deep metric learning aims to learn a function mapping image pixels to embedding feature
vectors that model the similarity between images. Two major applications of metric learning …
vectors that model the similarity between images. Two major applications of metric learning …
Qair: Practical query-efficient black-box attacks for image retrieval
We study the query-based attack against image retrieval to evaluate its robustness against
adversarial examples under the black-box setting, where the adversary only has query …
adversarial examples under the black-box setting, where the adversary only has query …
Billion-scale pretraining with vision transformers for multi-task visual representations
Large-scale pretraining of visual representations has led to state-of-the-art performance on a
range of benchmark computer vision tasks, yet the benefits of these techniques at extreme …
range of benchmark computer vision tasks, yet the benefits of these techniques at extreme …
Deepstyle: Multimodal search engine for fashion and interior design
I Tautkute, T Trzciński, AP Skorupa, Ł Brocki… - IEEE …, 2019 - ieeexplore.ieee.org
In this paper, we propose a multimodal search engine that combines visual and textual cues
to retrieve items from a multimedia database aesthetically similar to the query. The goal of …
to retrieve items from a multimedia database aesthetically similar to the query. The goal of …
[HTML][HTML] Metaverse search system: Architecture, challenges, and potential applications
S Yang, H Joo, J Kim - ICT Express, 2023 - Elsevier
Like numerous new websites created globally every day on the web, new spaces are
constantly produced in the metaverse and interconnected to each other through the Internet …
constantly produced in the metaverse and interconnected to each other through the Internet …
Learning a unified embedding for visual search at pinterest
At Pinterest, we utilize image embeddings throughout our search and recommendation
systems to help our users navigate through visual content by powering experiences like …
systems to help our users navigate through visual content by powering experiences like …
GrokNet: Unified computer vision model trunk and embeddings for commerce
In this paper, we present GrokNet, a deployed image recognition system for commerce
applications. GrokNet leverages a multi-task learning approach to train a single computer …
applications. GrokNet leverages a multi-task learning approach to train a single computer …
Awjedni: a reverse-image-search application
H Al-Lohibi, T Alkhamisi, M Assagran… - ADCAIJ: Advances in …, 2020 - torrossa.com
The abundance of photos on the internet, along with smartphones that could implement
computer vision technologies allow for a unique way to browse the web. These technologies …
computer vision technologies allow for a unique way to browse the web. These technologies …
Margin-based deep learning networks for human activity recognition
Human activity recognition (HAR) is a popular and challenging research topic, driven by a
variety of applications. More recently, with significant progress in the development of deep …
variety of applications. More recently, with significant progress in the development of deep …
Jizhi: A fast and cost-effective model-as-a-service system for web-scale online inference at baidu
In modern internet industries, deep learning based recommender systems have became an
indispensable building block for a wide spectrum of applications, such as search engine …
indispensable building block for a wide spectrum of applications, such as search engine …