DeepAI AI Chat
Log In Sign Up

Object Instance Identification in Dynamic Environments

by   Takuma Yagi, et al.
The University of Tokyo

We study the problem of identifying object instances in a dynamic environment where people interact with the objects. In such an environment, objects' appearance changes dynamically by interaction with other entities, occlusion by hands, background change, etc. This leads to a larger intra-instance variation of appearance than in static environments. To discover the challenges in this setting, we newly built a benchmark of more than 1,500 instances built on the EPIC-KITCHENS dataset which includes natural activities and conducted an extensive analysis of it. Experimental results suggest that (i) robustness against instance-specific appearance change (ii) integration of low-level (e.g., color, texture) and high-level (e.g., object category) features (iii) foreground feature selection on overlapping objects are required for further improvement.


page 1

page 2

page 3

page 7

page 9

page 10


re-OBJ: Jointly Learning the Foreground and Background for Object Instance Re-identification

Conventional approaches to object instance re-identification rely on mat...

LIP: Learning Instance Propagation for Video Object Segmentation

In recent years, the task of segmenting foreground objects from backgrou...

Multiple-object tracking in cluttered and crowded public spaces

This paper addresses the problem of tracking moving objects of variable ...

Generic Instance Search and Re-identification from One Example via Attributes and Categories

This paper aims for generic instance search from one example where the i...

InstMove: Instance Motion for Object-centric Video Segmentation

Despite significant efforts, cutting-edge video segmentation methods sti...

Discovering Objects that Can Move

This paper studies the problem of object discovery – separating objects ...

UAV Visual Teach and Repeat Using Only Semantic Object Features

We demonstrate the use of semantic object detections as robust features ...