Rishav Agarwal

Towards Rotation Invariance in Object Detection

Rotation augmentations generally improve a model's invariance/equivariance to rotation - except in object detection. In object detection the shape is not known, therefore rotation creates a label...

MatrixNets: A New Scale and Aspect Ratio Aware Architecture for Object Detection

We present MatrixNets (xNets), a new deep architecture for object detection. xNets map objects with similar sizes and aspect ratios into many specialized layers, allowing xNets to provide a scale...

Auditing Quality Filters for Long-Tail Human Data Curation

Robots on construction sites must detect workers who are kneeling or bending, which we call low poses. These workers can be lost from training datasets during automatic labeling. We study a...

Towards Rotation Invariance in Object Detection

PocketView: Through-Fabric Information Displays

Computer Vision Assisted Autonomous Intra-Row Weeder

3D-Object Perception Transformer (3PT)

Towards Co-Evaluation of Cameras, HDR, and Algorithms for Industrial-Grade 6DoF Pose Estimation

Generative Animations: A Multi-Model Pipeline for Prompt-Driven Motion Synthesis

Animation elevates digital documents into immersive experiences, yet creating custom motion paths remains cumbersome, requiring designers to manually select presets, plot B\'ezier points, and...

Text Style Transfer with Machine Translation for Graphic Designs

Globalization of graphic designs such as those used in marketing materials and magazines is increasingly important for communication to broad audiences. To accomplish this, the textual content in...