43 citations · 54 across the 13 of their papers we have counts for
13 papers
SHARDeg: A Benchmark for Skeletal Human Action Recognition in Degraded Scenarios
Simon Malzard, Nitish Mital, Richard Walters +3
Computer vision (CV) models for detection, prediction or classification tasks operate on video data-streams that are often degraded in the real world, due to deployment in real-tim…
Improving Object Detection by Modifying Synthetic Data with Explainable AI
Nitish Mital, Simon Malzard, Richard Walters +3
Limited real-world data severely impacts model performance in many computer vision domains, particularly for samples that are underrepresented in training. Synthetically generated…
Features-over-the-Air: Contrastive Learning Enabled Cooperative Edge Inference
Haotian Wu, Nitish Mital, Krystian Mikolajczyk +1
We study the collaborative image retrieval problem at the wireless edge, where multiple edge devices capture images of the same object, which are then used jointly to retrieve simi…
Collaborative Semantic Communication for Edge Inference
Wing Fei Lo, Nitish Mital, Haotian Wu +1
We study the collaborative image retrieval problem at the wireless edge, where multiple edge devices capture images of the same object from different angles and locations, which ar…
Neural Distributed Image Compression with Cross-Attention Feature Alignment
Nitish Mital, Ezgi Ozyilkan, Ali Garjani +1
We consider the problem of compressing an information source when a correlated one is available as side information only at the decoder side, which is a special case of the distrib…
Functional Broadcast Repair of Multiple Partial Failures in Wireless Distributed Storage Systems
Nitish Mital, Katina Kralevska, Cong Ling +1
We consider a distributed storage system with nodes, where a user can recover the stored file from any nodes, and study the problem of repairing partially failed nodes.…
Neural Distributed Image Compression using Common Information
Nitish Mital, Ezgi Ozyilkan, Ali Garjani +1
We present a novel deep neural network (DNN) architecture for compressing an image when a correlated image is available as side information only at the decoder. This problem is kno…
Dopamine: Differentially Private Federated Learning on Medical Data
Mohammad Malekzadeh, Burak Hasircioglu, Nitish Mital +3
While rich medical datasets are hosted in hospitals distributed across the world, concerns on patients' privacy is a barrier against using such data to train deep neural networks (…
Secure Distributed Matrix Computation with Discrete Fourier Transform
Nitish Mital, Cong Ling, Deniz Gunduz
We consider the problem of secure distributed matrix computation (SDMC), where a \textit{user} queries a function of data matrices generated at distributed \textit{source} nodes. W…
Coded Caching in Multi-server System with Random Topology
Nitish Mital, Deniz Gunduz, Cong Ling
Cache-aided content delivery is studied in a multi-server system with servers and users, each equipped with a local cache memory. In the delivery phase, each user connects…
Practical Functional Regenerating Codes for Broadcast Repair of Multiple Nodes
Nitish Mital, Katina Kralevska, Cong Ling +1
A code construction and repair scheme for optimal functional regeneration of multiple node failures is presented, which is based on stitching together short MDS codes on carefully…
Storage-Repair Bandwidth Trade-off for Wireless Caching with Partial Failure and Broadcast Repair
Nitish Mital, Katina Kralevska, Deniz Gunduz +1
Repair of multiple partially failed cache nodes is studied in a distributed wireless content caching system, where out of a total of cache nodes lose part of their cached d…
Coded Caching in a Multi-Server System with Random Topology
Nitish Mital, Deniz Gunduz, Cong Ling
Cache-aided content delivery is studied in a multi-server system with servers and users, each equipped with a local cache memory. In the delivery phase, each user connects…