Code review is an essential activity for ensuring the quality and
mainta...
Optical metasurfaces composed of precisely engineered nanostructures hav...
Recommender systems (RSs) have become an indispensable part of online
pl...
Communication-reduction techniques are a popular way to improve scalabil...
Federated semi-supervised learning (FSSL), facilitates labeled clients a...
Conventional image signal processing (ISP) frameworks are designed to
re...
Protecting individuals' private information while still allowing modeler...
Federated learning (FL) facilitates multiple clients to jointly train a
...
DNN-based video object detection (VOD) powers autonomous driving and vid...
Adversarial patch attacks that craft the pixels in a confined region of ...
Building user trust in dialogue agents requires smooth and consistent
di...
Ranking is the most important component in a search system. Mostsearch
s...
Most modern Multi-Object Tracking (MOT) systems typically apply REID-bas...
We present a hybrid particle/grid approach for simulating incompressible...
Winograd's minimal filtering algorithm has been widely used in Convoluti...
Recent emerged quantization technique (i.e., using low bit-width fixed-p...
LinkedIn Talent Solutions business contributes to around 65
annual reven...
Talent search and recommendation systems at LinkedIn strive to match the...
Scene motion, multiple reflections, and sensor noise introduce artifacts...
The increasing attention on deep learning has tremendously spurred the d...
Deep network pruning is an effective method to reduce the storage and
co...
Face photo synthesis from simple line drawing is a one-to-many task as s...
Many works have concentrated on visualizing and understanding the inner
...
Multi-object tracking remains challenging due to frequent occurrence of
...
The time people spend in front of computers has been increasing steadily...
Data races can significantly affect the executions of multi-threaded
pro...