2 citations · 10 across the 19 of their papers we have counts for
21 papers
WiSPER: Pose-Supervised Predictive and Residual Flow Refinement For Multi-Person 3D Pose Estimation With WiFi CSI
Gabriel Lee Jun Rong, Shanhong Liu, Pai Chet Ng +3
Multi-person 3D pose estimation with WiFi channel state information (CSI) is challenging because reflections from different people overlap without directly identifying individual j…
Profile-Aware Trustworthy Recipe Generation with Planner-Critic Agentic Remediation
Shanhong Liu, Pai Chet Ng, Konstantinos N. Plataniotis
Recipe generation from food images has practical value for intelligent cooking assistance, but traditional one-pass generation often overlooks user-specific safety requirements suc…
Beyond a Joke: Multi-Angle Reasoning for Detecting and Explaining Harmful Humor in Memes
Shanhong Liu, Pai Chet Ng, De Wen Soh +2
Internet memes intertwine visual cues, textual content, and cultural context, making them particularly challenging to interpret in scenarios where humor, sarcasm, and harmful inten…
ARMOR++: Agentic Orchestration of a Multi-Domain Primitive Set for Transferable Attacks on Deepfake Detectors
Christos Korgialas, Gabriel Lee Jun Rong, Dion Jia Xu Ho +3
The reliability of deepfake detectors frequently degrades under black-box adversarial transfer, as these models often rely on fragile, architecture-dependent forensic cues. Existin…
DECODE: Dual-Enhanced Conditioned Diffusion for EEG Forecasting
Mehran Shabanpour, Sadaf Khademi, Konstantinos N Plataniotis +1
Forecasting Electroncephalography (EEG) signals during cognitive events remains a fundamental challenge in neuroscience and Brain-Computer Interfaces (BCIs), as existing methods st…
ARMOR: Agentic Reasoning for Methods Orchestration and Reparameterization for Robust Adversarial Attacks
Gabriel Lee Jun Rong, Christos Korgialas, Dion Jia Xu Ho +3
Existing automated attack suites operate as static ensembles with fixed sequences, lacking strategic adaptation and semantic awareness. This paper introduces the Agentic Reasoning…
Yes FLoReNce, I Will Do Better Next Time! Agentic Feedback Reasoning for Humorous Meme Detection
Olivia Shanhong Liu, Pai Chet Ng, De Wen Soh +1
Humorous memes blend visual and textual cues to convey irony, satire, or social commentary, posing unique challenges for AI systems that must interpret intent rather than surface c…
PanFlow: Decoupled Motion Control for Panoramic Video Generation
Cheng Zhang, Hanwen Liang, Donny Y. Chen +4
Panoramic video generation has attracted growing attention due to its applications in virtual reality and immersive media. However, existing methods lack explicit motion control an…
TiP4GEN: Text to Immersive Panorama 4D Scene Generation
Ke Xing, Hanwen Liang, Dejia Xu +4
With the rapid advancement and widespread adoption of VR/AR technologies, there is a growing demand for the creation of high-quality, immersive dynamic scenes. However, existing ge…
Advancements in Medical Image Classification through Fine-Tuning Natural Domain Foundation Models
Mobina Mansoori, Sajjad Shahabodini, Farnoush Bayatmakou +3
Using massive datasets, foundation models are large-scale, pre-trained models that perform a wide range of tasks. These models have shown consistently improved results with the int…
The Missing Point in Vision Transformers for Universal Image Segmentation
Sajjad Shahabodini, Mobina Mansoori, Farnoush Bayatmakou +3
Image segmentation remains a challenging task in computer vision, demanding robust mask generation and precise classification. Recent mask-based approaches yield high-quality masks…
Wonderland: Navigating 3D Scenes from a Single Image
Hanwen Liang, Junli Cao, Vidit Goel +6
How can one efficiently generate high-quality, wide-scope 3D scenes from arbitrary single images? Existing methods suffer several drawbacks, such as requiring multi-view data, time…
Self-Prompting Polyp Segmentation in Colonoscopy using Hybrid Yolo-SAM 2 Model
Mobina Mansoori, Sajjad Shahabodini, Jamshid Abouei +2
Early diagnosis and treatment of polyps during colonoscopy are essential for reducing the incidence and mortality of Colorectal Cancer (CRC). However, the variability in polyp char…
Leveraging Foundation Models for Efficient Federated Learning in Resource-restricted Edge Networks
S. Kawa Atapour, S. Jamal SeyedMohammadi, S. Mohammad Sheikholeslami +3
Recently pre-trained Foundation Models (FMs) have been combined with Federated Learning (FL) to improve training of downstream tasks while preserving privacy. However, deploying FM…
Polyp SAM 2: Advancing Zero shot Polyp Segmentation in Colorectal Cancer Detection
Mobina Mansoori, Sajjad Shahabodini, Jamshid Abouei +2
Polyp segmentation plays a crucial role in the early detection and diagnosis of colorectal cancer. However, obtaining accurate segmentations often requires labor-intensive annotati…
EX-DRL: Hedging Against Heavy Losses with EXtreme Distributional Reinforcement Learning
Parvin Malekzadeh, Zissis Poulos, Jacky Chen +2
Recent advancements in Distributional Reinforcement Learning (DRL) for modeling loss distributions have shown promise in developing hedging strategies in derivatives markets. A com…
Diffusion4D: Fast Spatial-temporal Consistent 4D Generation via Video Diffusion Models
Hanwen Liang, Yuyang Yin, Dejia Xu +5
The availability of large-scale multimodal datasets and advancements in diffusion models have significantly accelerated progress in 4D content generation. Most prior approaches rel…
Comp4D: LLM-Guided Compositional 4D Scene Generation
Dejia Xu, Hanwen Liang, Neel P. Bhatt +4
Recent advancements in diffusion models for 2D and 3D content creation have sparked a surge of interest in generating 4D content. However, the scarcity of 3D scene datasets constra…
HistoSegCap: Capsules for Weakly-Supervised Semantic Segmentation of Histological Tissue Type in Whole Slide Images
Mobina Mansoori, Sajjad Shahabodini, Jamshid Abouei +2
Digital pathology involves converting physical tissue slides into high-resolution Whole Slide Images (WSIs), which pathologists analyze for disease-affected tissues. However, large…
FedD2S: Personalized Data-Free Federated Knowledge Distillation
Kawa Atapour, S. Jamal Seyedmohammadi, Jamshid Abouei +2
This paper addresses the challenge of mitigating data heterogeneity among clients within a Federated Learning (FL) framework. The model-drift issue, arising from the noniid nature…
NYCTALE: Neuro-Evidence Transformer for Adaptive and Personalized Lung Nodule Invasiveness Prediction
Sadaf Khademi, Anastasia Oikonomou, Konstantinos N. Plataniotis +1
Drawing inspiration from the primate brain's intriguing evidence accumulation process, and guided by models from cognitive psychology and neuroscience, the paper introduces the NYC…