Sequential Decision-Making for Active Object Detection from Hand

10/21/2021
by   Qichen Fu, et al.
0

A key component of understanding hand-object interactions is the ability to identify the active object – the object that is being manipulated by the human hand – despite the occlusion induced by hand-object interactions. Based on the observation that hand appearance is a strong indicator of the location and size of the active object, we set up our active object detection method as a sequential decision-making process that is conditioned on the location and appearance of the hands. The key innovation of our approach is the design of the active object detection policy that uses an internal representation called the Relational Box Field, which allows for every pixel to regress an improved location of an active object bounding box, essentially giving every pixel the ability to vote for a better bounding box location. The policy is trained using a hybrid imitation learning and reinforcement learning approach, and at test time, the policy is used repeatedly to refine the bounding box location of the active object. We perform experiments on two large-scale datasets: 100DOH and MECCANO, improving AP50 performance by 8 of the art.

READ FULL TEXT

page 3

page 5

page 6

page 11

page 12

research
04/15/2019

Universal Bounding Box Regression and Its Applications

Bounding-box regression is a popular technique to refine or predict loca...
research
11/02/2022

OPA-3D: Occlusion-Aware Pixel-Wise Aggregation for Monocular 3D Object Detection

Despite monocular 3D object detection having recently made a significant...
research
10/15/2018

Multi-Stage Reinforcement Learning For Object Detection

We present a reinforcement learning approach for detecting objects withi...
research
09/09/2019

Connected Assembly and Reconfiguration by Finite Automata

We consider methods for connected reconfigurations by finite automate in...
research
06/03/2020

CircleNet: Anchor-free Detection with Circle Representation

Object detection networks are powerful in computer vision, but not neces...
research
05/20/2020

Range Conditioned Dilated Convolutions for Scale Invariant 3D Object Detection

This paper presents a novel 3D object detection framework that processes...
research
12/09/2015

Window-Object Relationship Guided Representation Learning for Generic Object Detections

In existing works that learn representation for object detection, the re...

Please sign up or login with your details

Forgot password? Click here to reset