44 citations · 123 across the 7 of their papers we have counts for
8 papers
How to Boost Face Recognition with StyleGAN?
Artem Sevastopolsky, Yury Malkov, Nikita Durasov +2
State-of-the-art face recognition systems require vast amounts of labeled training data. Given the priority of privacy in face recognition applications, the data is limited to cele…
TwHIN-BERT: A Socially-Enriched Pre-trained Language Model for Multilingual Tweet Representations at Twitter
Xinyang Zhang, Yury Malkov, Omar Florez +4
Pre-trained language models (PLMs) are fundamental for natural language processing applications. Most existing PLMs are not tailored to the noisy user-generated text on social medi…
TwHIN: Embedding the Twitter Heterogeneous Information Network for Personalized Recommendation
Ahmed El-Kishky, Thomas Markovich, Serim Park +8
Social networks, such as Twitter, form a heterogeneous information network (HIN) where nodes represent domain entities (e.g., user, content, advertiser, etc.) and edges represent o…
Textured Neural Avatars
Aliaksandra Shysheya, Egor Zakharov, Kara-Ali Aliev +9
We present a system for learning full-body neural avatars, i.e. deep networks that produce full-body renderings of a person for varying body pose and camera position. Our system ta…
Learnable Triangulation of Human Pose
Karim Iskakov, Egor Burkov, Victor Lempitsky +1
We present two novel solutions for multi-view 3D human pose estimation based on new learnable triangulation methods that combine 3D information from multiple 2D views. The first (b…
Revisiting the Inverted Indices for Billion-Scale Approximate Nearest Neighbors
Dmitry Baranchuk, Artem Babenko, Yury Malkov
This work addresses the problem of billion-scale nearest neighbor search. The state-of-the-art retrieval systems for billion-scale databases are currently based on the inverted mul…
Geometric explanation of the rich-club phenomenon in complex networks
Máté Csigi, Attila Kőrösi, József Bíró +3
The rich club organization (the presence of highly connected hub core in a network) influences many structural and functional characteristics of networks including topology, the ef…
Off the Beaten Path: Let's Replace Term-Based Retrieval with k-NN Search
Leonid Boytsov, David Novak, Yury Malkov +1
Retrieval pipelines commonly rely on a term-based search to obtain candidate records, which are subsequently re-ranked. Some candidates are missed by this approach, e.g., due to a…