Related papers: VASSL: A Visual Analytics Toolkit for Social Spamb…
Current self-supervised learning (SSL) methods (e.g., SimCLR, DINO, VICReg,MOCOv3) target primarily on representations at instance level and do not generalize well to dense prediction tasks, such as object detection and segmentation.Towards…
Scribble-based weakly-supervised semantic segmentation using sparse scribble supervision is gaining traction as it reduces annotation costs when compared to fully annotated alternatives. Existing methods primarily generate pseudo-labels by…
Vertical federated learning (VFL) enables multiple parties with disjoint features to collaboratively train models without sharing raw data. While privacy vulnerabilities of VFL are extensively-studied, its security threats-particularly…
Compromised accounts on social networks are regular user accounts that have been taken over by an entity with malicious intent. Since the adversary exploits the already established trust of a compromised account, it is crucial to detect…
In this work, we introduce Scribbles for All, a label and training data generation algorithm for semantic segmentation trained on scribble labels. Training or fine-tuning semantic segmentation models with weak supervision has become an…
The use of large-scale vision-language datasets is limited for object detection due to the negative impact of label noise on localization. Prior methods have shown how such large-scale datasets can be used for pretraining, which can provide…
This paper proposes a powerful Visual Speech Recognition (VSR) method for multiple languages, especially for low-resource languages that have a limited number of labeled data. Different from previous methods that tried to improve the VSR…
Targeted Sentiment Analysis (TSA) is a central task for generating insights from consumer reviews. Such content is extremely diverse, with sites like Amazon or Yelp containing reviews on products and businesses from many different domains.…
Malicious WebShells pose a significant and evolving threat by compromising critical digital infrastructures and endangering public services in sectors such as healthcare and finance. While the research community has made significant…
Webly supervised learning becomes attractive recently for its efficiency in data expansion without expensive human labeling. However, adopting search queries or hashtags as web labels of images for training brings massive noise that…
Twitter is one of the popular social media platforms where people share news or reactions towards an event or topic using short text messages called "tweets". Emotion analysis in these tweets can play a vital role in understanding peoples'…
The surge of e-commerce reviews has presented a challenge in manually annotating the vast volume of reviews to comprehend their underlying aspects and sentiments. This research focused on leveraging weakly supervised learning to tackle…
In this paper we introduce vSTS, a new dataset for measuring textual similarity of sentences using multimodal information. The dataset is comprised by images along with its respectively textual captions. We describe the dataset both…
Active learning aims to alleviate the amount of labor involved in data labeling by automating the selection of unlabeled samples via an acquisition function. For example, variational adversarial active learning (VAAL) leverages an…
Object detection in streaming images is a major step in different detection-based applications, such as object tracking, action recognition, robot navigation, and visual surveillance applications. In mostcases, image quality is noisy and…
Supervised learning demands large amounts of precisely annotated data to achieve promising results. Such data curation is labor-intensive and imposes significant overhead regarding time and costs. Self-supervised learning (SSL) partially…
Recently, a new window to explore tweet data has been opened in TExVis tool through visualizing the relations between the frequent keywords. However, timeline exploration of tweet data, not present in TExVis, could play a critical factor in…
Social engineering (SE) aims at deceiving users into performing actions that may compromise their security and privacy. These threats exploit weaknesses in human's decision making processes by using tactics such as pretext, baiting,…
User sequence modeling is crucial for modern large-scale recommendation systems, as it enables the extraction of informative representations of users and items from their historical interactions. These user representations are widely used…
Twitter is a web application playing dual roles of online social networking and micro-blogging. The popularity and open structure of Twitter have attracted a large number of automated programs, known as bots. Legitimate bots generate a…