Computer Vision to Analyze Protests in Social Media [PDF]
, 2020 Images are central to understanding protests and mass activism today for its impact in shaping public opinion. Previously, analyzing protest images required human annotation, which is laborious and expensive.
Chan, Alexander
core
A Scoping Review of Bullying and Harassment in Nonprofit and Voluntary Organizations
Nonprofit Management and Leadership, Volume 35, Issue 4, Page 813-836, Summer 2025.ABSTRACT Approximately 15% of workers are exposed to bullying in their workplace. However, few studies appear to have been conducted in nonprofit and voluntary organizations. This scoping review explored prevalence and structural and contextual factors that influence bullying in nonprofit and voluntary organizations.
Margaret Hodgins +4 more
wiley +1 more source
Molecular Retrosynthesis Top‐K Prediction Based on the Latent Generation Process
CAAI Transactions on Intelligence Technology, Volume 10, Issue 3, Page 902-911, June 2025.ABSTRACT In the field of organic synthesis, the core objective of retrosynthetic methods is to deduce possible synthetic routes and precursor molecules for complex target molecules. Traditional retrosynthetic methods, such as template‐based retrosynthesis, have high accuracy and interpretability in specific types of reactions but are limited by the ...
Yupeng Liu, Han Zhang, Rui Hu
wiley +1 more source
Building Text‐to‐Speech Models for Low‐Resourced Languages From Crowdsourced Data
Applied AI Letters, Volume 6, Issue 2, April 2025.Natural‐sounding TTS for low‐resource languages like Luganda and Kiswahili is achieved by fine‐tuning VITS on carefully preprocessed crowdsourced speech from intonation‐matched speakers. ABSTRACT Text‐to‐speech (TTS) models have expanded the scope of digital inclusivity by becoming a basis for assistive communication technologies for visually impaired ...
Andrew Katumba +4 more
wiley +1 more source
, 2019 Deep neural networks (DNNs) have been shown to tolerate "brain damage": cumulative changes to the network's parameters (e.g., pruning, numerical perturbations) typically result in a graceful degradation of classification accuracy.
Dumitraş, Tudor +4 more
core +2 more sources
On Decentralized Cloud Storage Security and an Efficient Post-Quantum Encryption Scheme [PDF]
In this thesis, we address three main security problems related to cryptography andcloud storage. To tackle the challenge posed by a quantum computer, we needencryption that is resistant to quantum computers.
Kundu, Rohon
core
Watch Your Step: Optimal Retrieval for Continual Learning at Scale
In continual learning, a model learns incrementally over time while minimizing interference between old and new tasks. One of the most widely used approaches in continual learning is referred to as replay.
Hickok, Truman, Kudithipudi, Dhireesha
core
Explainable multilingual and multimodal fake-news detection: toward robust and trustworthy AI for combating misinformation. [PDF]
Front Artif IntellJadhav R +5 more
europepmc +1 more source
Detecting freebooted content in social media ads: multimodal provenance and e-commerce implications. [PDF]
Front Artif IntellWeinlich P, Semeradova T.
europepmc +1 more source
The mosaic memory of large language models. [PDF]
Nat CommunShilov I, Meeus M, de Montjoye YA.
europepmc +1 more source