Related papers: CAMERA: Adapting to Semantic Camouflage in Unsuper…
Existing Unsupervised Domain Adaptation (UDA) literature adopts the covariate shift and conditional shift assumptions, which essentially encourage models to learn common features across domains. However, due to the lack of supervision in…
Pedestrian detection is fundamental to autonomous driving, robotics, and surveillance. Despite progress in deep learning, reliable identification remains challenging due to occlusions, cluttered backgrounds, and degraded visibility. While…
Camouflaged scene understanding (CSU) has attracted significant attention due to its broad practical implications. However, in this field, robust image-text cross-modal alignment remains under-explored, hindering deeper understanding of…
Automated systems that detect deception in high-stakes situations can enhance societal well-being across medical, social work, and legal domains. Existing models for detecting high-stakes deception in videos have been supervised, but…
Graph Retrieval-Augmented Generation (GraphRAG) has emerged as a key technique for enhancing Large Language Models (LLMs) with proprietary Knowledge Graphs (KGs) in knowledge-intensive applications. As these KGs often represent an…
This paper introduces advanced techniques of Topological Data Analysis (TDA) for unsupervised anomaly detection and customer segmentation in banking data. Using the Mapper algorithm and persistent homology, we develop unsupervised…
Handwritten signature verification is a crucial aspect of identity authentication, with applications in various domains such as finance and e-commerce. However, achieving high accuracy in signature verification remains challenging due to…
Facial Expression Recognition (FER) is an important task in computer vision and has wide applications in human-computer interaction, intelligent security, emotion analysis, and other fields. However, the limited size of FER datasets limits…
Current State-of-the-Art models in Named Entity Recognition (NER) are neural models with a Conditional Random Field (CRF) as the final network layer, and pre-trained "contextual embeddings". The CRF layer is used to facilitate global…
With the rapid development of social media, the importance of analyzing social network user data has also been put on the agenda. User representation learning in social media is a critical area of research, based on which we can conduct…
Modern financial electronic exchanges are an exciting and fast-paced marketplace where billions of dollars change hands every day. They are also rife with manipulation and fraud. Detecting such activity is a major undertaking, which has…
Graph fraud detection has long depended on Graph Neural Networks (GNNs) to propagate and aggregate information across relational data. A critical obstacle in practice, however, is that fraudsters frequently disguise themselves by forging…
Deepfakes are realistic face manipulations that can pose serious threats to security, privacy, and trust. Existing methods mostly treat this task as binary classification, which uses digital labels or mask signals to train the detection…
Rapid growth of modern technologies such as internet and mobile computing are bringing dramatically increased e-commerce payments, as well as the explosion in transaction fraud. Meanwhile, fraudsters are continually refining their tricks,…
Semi-supervised learning has emerged as a promising approach to tackle the challenge of label scarcity in facial expression recognition (FER) task. However, current state-of-the-art methods primarily focus on one side of the coin, i.e.,…
Recent advances in large-scale text-to-image generation models have led to a surge in subject-driven text-to-image generation, which aims to produce customized images that align with textual descriptions while preserving the identity of…
Partially annotated clips contain rich temporal contexts that can complement the sparse key frame annotations in providing supervision for model training. We present a novel paradigm called Temporally-Adaptive Features (TAF) learning that…
Text anomaly detection (TAD) plays a critical role in various language-driven real-world applications, including harmful content moderation, phishing detection, and spam review filtering. While two-step "embedding-detector" TAD methods have…
Graph anomaly detection (GAD) has garnered increasing attention in recent years, yet remains challenging due to two key factors: (1) label scarcity stemming from the high cost of annotations and (2) homophily disparity at node and class…
Credit card fraud has been a persistent issue since the last century, causing significant financial losses to the industry. The most effective way to prevent fraud is by contacting customers to verify suspicious transactions. However, while…