Search Results for author: Shubham Dokania

Found 5 papers, 1 papers with code

IDD-3D: Indian Driving Dataset for 3D Unstructured Road Scenes

no code implementations23 Oct 2022 Shubham Dokania, A. H. Abdul Hafez, Anbumani Subramanian, Manmohan Chandraker, C. V. Jawahar

Autonomous driving and assistance systems rely on annotated data from traffic and road scenarios to model and learn the various object relations in complex real-world scenarios.

3D Object Detection Autonomous Driving +2

TRoVE: Transforming Road Scene Datasets into Photorealistic Virtual Environments

1 code implementation16 Aug 2022 Shubham Dokania, Anbumani Subramanian, Manmohan Chandraker, C. V. Jawahar

We show that using annotations and visual cues from existing datasets, we can facilitate automated multi-modal data generation, mimicking real scene properties with high-fidelity, along with mechanisms to diversify samples in a physically meaningful way.

Semantic Segmentation Synthetic Data Generation

Graph Representation learning for Audio & Music genre Classification

no code implementations23 Oct 2019 Shubham Dokania, Vasudev Singh

Music genre is arguably one of the most important and discriminative information for music and audio content.

Classification General Classification +4

Opportunistic Self Organizing Migrating Algorithm for Real-Time Dynamic Traveling Salesman Problem

no code implementations12 Sep 2017 Shubham Dokania, Sunyam Bagga, Rohit Sharma

Self Organizing Migrating Algorithm (SOMA) is a meta-heuristic algorithm based on the self-organizing behavior of individuals in a simulated social environment.

Traveling Salesman Problem

Hierarchy Influenced Differential Evolution: A Motor Operation Inspired Approach

no code implementations17 Feb 2017 Shubham Dokania, Ayush Chopra, Feroz Ahmad, Anil Singh Parihar

In the present work, we introduce an algorithm for mathematical optimisation that derives its intuition from the hierarchical and distributed operations of the human motor system.

Decision Making

Cannot find the paper you are looking for? You can Submit a new open access paper.