49 citations · 59 across the 27 of their papers we have counts for
7 papers · 1 filter
Simple Features and Honest Calibration for Ambivalence and Hesitancy Recognition in Video
Vikas Kumar, Aditya Mishra, Haroon R. Lone
We address ambivalence and hesitancy (A/H) recognition in the ABAW 2026 BAH Challenge: given a short interview video, predict whether the person shows signs of A/H. Our system comb…
Beyond Benchmarks: Continuous Edge Inference for Fine-Grained Roadside Perception
Aditya Mishra, Haroon Lone
Continuous AI inference on resource-constrained edge hardware introduces deployment effects that are largely invisible to conventional benchmark evaluation, including temporal inst…
Q-LocalAdam: Memory-Efficient Client-Side Adaptive Optimization for Edge Federated Learning
Vedant Waykole, Haroon R. Lone
Federated learning on edge devices must cope with non-IID client data and tight memory budgets. Adaptive optimizers like Adam stabilize training under data heterogeneity but requir…
FedPrism: Adaptive Personalized Federated Learning under Non-IID Data
Prakash Kumbhakar, Shrey Srivastava, Haroon R Lone
Federated Learning (FL) suffers significant performance degradation in real-world deployments characterized by moderate to extreme statistical heterogeneity (non-IID client data).…
CA-AFP: Cluster-Aware Adaptive Federated Pruning
Om Govind Jha, Harsh Shukla, Haroon R. Lone
Federated Learning (FL) faces major challenges in real-world deployments due to statistical heterogeneity across clients and system heterogeneity arising from resource-constrained…
DohaScript: A Large-Scale Multi-Writer Dataset for Continuous Handwritten Hindi Text
Kunwar Arpit Singh, Ankush Prakash, Haroon R Lone
Despite having hundreds of millions of speakers, handwritten Devanagari text remains severely underrepresented in publicly available benchmark datasets. Existing resources are limi…
Evaluating Federated Learning for Cross-Country Mood Inference from Smartphone Sensing Data
Sharmad Kalpande, Saurabh Shirke, Haroon R. Lone
Mood instability is a key behavioral indicator of mental health, yet traditional assessments rely on infrequent and retrospective reports that fail to capture its continuous nature…