research
∙
08/09/2023
High-Level Features Parallelization for Inference Cost Reduction Through Selective Attention
In this work, we parallelize high-level features in deep networks to sel...
share
research
∙
07/27/2023
Small, but important: Traffic light proposals for detecting small traffic lights and beyond
Traffic light detection is a challenging problem in the context of self-...
research
∙
06/02/2023
Audio-Visual Speech Enhancement with Score-Based Generative Models
This paper introduces an audio-visual speech enhancement system that lev...
research
∙
04/15/2023
Teacher Network Calibration Improves Cross-Quality Knowledge Distillation
We investigate cross-quality knowledge distillation (CQKD), a knowledge ...
research
∙
03/21/2022
Segmenting Medical Instruments in Minimally Invasive Surgeries using AttentionMask
Precisely locating and segmenting medical instruments in images of minim...
research
∙
02/23/2022
Localizing Small Apples in Complex Apple Orchard Environments
The localization of fruits is an essential first step in automated agric...
research
∙
08/07/2021
DeepFH Segmentations for Superpixel-based Object Proposal Refinement
Class-agnostic object proposal generation is an important first step in ...
research
∙
03/02/2021
CloudAAE: Learning 6D Object Pose Regression with On-line Data Synthesis on Point Clouds
It is often desired to train 6D pose estimation systems on synthetic dat...
research
∙
02/12/2021
Annotation Cleaning for the MSR-Video to Text Dataset
The video captioning task is to describe the video contents with natural...
research
∙
01/12/2021
Superpixel-based Refinement for Object Proposal Generation
Precise segmentation of objects is an important problem in tasks like cl...
research
∙
07/04/2020
Multi-Sensor Next-Best-View Planning as Matroid-Constrained Submodular Maximization
3D scene models are useful in robotics for tasks such as path planning, ...
research
∙
01/24/2020
6D Object Pose Regression via Supervised Learning on Point Clouds
This paper addresses the task of estimating the 6 degrees of freedom pos...
research
∙
11/21/2018
AttentionMask: Attentive, Efficient Object Proposal Generation Focusing on Small Objects
We propose a novel approach for class-agnostic object proposal generatio...
research
∙
11/10/2018
Multi-label Object Attribute Classification using a Convolutional Neural Network
Objects of different classes can be described using a limited number of ...
research
∙
09/12/2018
Attention based visual analysis for fast grasp planning with multi-fingered robotic hand
We present an attention based visual analysis framework to compute grasp...
research
∙
08/16/2018