8 papers
Modality Agreement- and Conflict-Aware Prototype Hypergraph Learning for Multimodal Intent Understanding
Mohnish Raj, Suraj Kumar, Soumi Chattopadhayay +2
Multimodal intent recognition requires understanding not only what textual, acoustic, and visual signals share, but also how they disagree. Such disagreement is frequently class-in…
Adaptive Modality Reliability Diagnosis and Restoration for Robust Multimodal Intent Recognition
Suraj Kumar, Mohnish Raj, Soumi Chattopadhayay +2
Multimodal intent recognition combines linguistic, acoustic, and visual evidence, but individual modalities may be noisy, missing, semantically conflicting, or disproportionately d…
ProtoSiTex: Learning Semi-Interpretable Prototypes for Multi-label Text Classification
Utsav Kumar Nareti, Suraj Kumar, Soumya Pandey +3
The rapid growth of user-generated text across digital platforms has intensified the need for interpretable models capable of fine-grained text classification and explanation. Exis…
Anomaly Resilient Temporal QoS Prediction using Hypergraph Convoluted Transformer Network
Suraj Kumar, Soumi Chattopadhyay, Chandranath Adak
Quality-of-Service (QoS) prediction is a critical task in the service lifecycle, enabling precise and adaptive service recommendations by anticipating performance variations over t…
Agentic Multi-Persona Framework for Evidence-Aware Fake News Detection
Roopa Bukke, Soumya Pandey, Suraj Kumar +2
The rapid proliferation of online misinformation threatens the stability of digital social systems and poses significant risks to public trust, policy, and safety, necessitating re…
Blurb-Refined Inference from Crowdsourced Book Reviews using Hierarchical Genre Mining with Dual-Path Graph Convolutions
Suraj Kumar, Utsav Kumar Nareti, Soumi Chattopadhyay +2
Accurate book genre classification is fundamental to digital library organization, content discovery, and personalized recommendation. Existing approaches typically model genre pre…