Object Instance Identification in Dynamic Environments
Not on the map. Why?
Abstract (arXiv)
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.
Key facts. No citing papers in the map yet (data through 14 Oct 2026). Builds on 6 of its 21 references that are in the map. First posted on arXiv 10 Jun 2022.
Builds on
6 of 21 references.
References · 6
- 2015Deep Residual Learning for Image Recognitioncited by 52,096
- 2016Grad-CAM: Visual Explanations from Deep Networks via Gradient-based Localizationcited by 6,733
- 2015Deep Metric Learning via Lifted Structured Feature Embeddingcited by 449
- 2017CORe50: a New Dataset and Benchmark for Continuous Object Recognitioncited by 289
- 2021Learning Open-World Object Proposals without Learning to Classifycited by 109
- 2018The Toybox Dataset of Egocentric Visual Object Transformationscited by 6
Built on by
Not cited yet.