5 papers
Domain Expansion: A Latent Space Construction Framework for Multi-Task Learning
Chi-Yao Huang, Khoa Vo, Aayush Atul Verma +2
Training a single network with multiple objectives often leads to conflicting gradients that degrade shared representations, forcing them into a compromised state that is suboptima…
Event-based Graph Representation with Spatial and Motion Vectors for Asynchronous Object Detection
Aayush Atul Verma, Arpitsinh Vaghela, Bharatesh Chakravarthi +2
Event-based sensors offer high temporal resolution and low latency by generating sparse, asynchronous data. However, converting this irregular data into dense tensors for use in st…
SEPose: A Synthetic Event-based Human Pose Estimation Dataset for Pedestrian Monitoring
Kaustav Chanda, Aayush Atul Verma, Arpitsinh Vaghela +2
Event-based sensors have emerged as a promising solution for addressing challenging conditions in pedestrian and traffic monitoring systems. Their low-latency and high dynamic rang…
Event Quality Score (EQS): Assessing the Realism of Simulated Event Camera Streams via Distances in Latent Space
Kaustav Chanda, Aayush Atul Verma, Arpitsinh Vaghela +2
Event cameras promise a paradigm shift in vision sensing with their low latency, high dynamic range, and asynchronous nature of events. Unfortunately, the scarcity of high-quality…
MC-BEVRO: Multi-Camera Bird Eye View Road Occupancy Detection for Traffic Monitoring
Arpitsinh Vaghela, Duo Lu, Aayush Atul Verma +3
Single camera 3D perception for traffic monitoring faces significant challenges due to occlusion and limited field of view. Moreover, fusing information from multiple cameras at th…