Demonstration of VCR: A Tabular Data Slicing Approach to Understanding Object Detection Model Performance
Summary: VCR converts vision-foundation-model segment concepts and image metadata into tabular data for scalable frequent-itemset slice discovery in object-detection errors. An interactive workflow supports visual inspection and feedback-driven refinement of concept granularity and labels. (summarized by gpt-5.6-luna on Jul 24 2026)
Incoming Non-self Citations Over Time
No non-self incoming citations found for this paper in this database.
Authors
- 1. Jie Jeff Xu (Georgia Institute of Technology)
- 2. Saahir Dhanani (Georgia Institute of Technology)
- 3. Jorge Piazentin Ono (Bosch Center for AI)
- 4. Wenbin He (Bosch Center for AI)
- 5. Liu Ren (Bosch Center for AI)
- 6. Kexin Rong (Georgia Institute of Technology)
BibTeX Citation
@article{xu_vldb24,
title = {{Demonstration of VCR: A Tabular Data Slicing Approach to Understanding Object Detection Model Performance}},
author = {Xu, Jie Jeff and Dhanani, Saahir and Ono, Jorge Piazentin and He, Wenbin and Ren, Liu and Rong, Kexin},
journal = {PVLDB},
series = {{VLDB} '24},
volume = {17},
number = {12},
pages = {4453--4456},
doi = {10.14778/3685800.3685898},
url = {https://doi.org/10.14778/3685800.3685898},
year = {2024}
}Incoming Citations (Sorted by Pagerank)
Showing 0 of 0 citing papers.
| Rank | Citing Paper | Year | Venue | Pagerank |
|---|
Previous
Page 1 / 1
Next
Outgoing Citations (Sorted by Pagerank)
Showing 3 of 3 cited papers.
Citations counted here include only citations to other VLDB/SIGMOD/CIDR/PODS papers in this database.
| Rank | Cited Paper | Year | Venue | Pagerank |
|---|---|---|---|---|
| 29 | Fast Algorithms for Mining Association Rules | 1994 | VLDB | 0.0005121339 |
| 3,262 | Looking for Trouble: Analyzing Classifier Behavior via Pattern Divergence | 2021 | SIGMOD | 7.4815294e-05 |
| 7,654 | POEM: Pattern-Oriented Explanations of Convolutional Neural Networks | 2023 | VLDB | 5.4772833e-05 |
Previous
Page 1 / 1
Next
Semantically Similar Papers
| # | Overall Rank | Paper | Year | Venue |
|---|---|---|---|---|
| 1 | 11,596 | Optimizing Video Queries with Declarative Clues | 2024 | VLDB |
| 2 | 11,624 | Demonstration of MaskSearch: Efficiently Querying Image Masks for Machine Learning Workflows | 2024 | VLDB |
| 3 | 9,645 | Self-Enhancing Video Data Management System for Compositional Events with Large Language Models | 2025 | SIGMOD |
| 4 | 10,839 | Craw: A Unified and Efficient Querying Framework for Large-Scale Video Datasets | 2026 | VLDB |
| 5 | 10,108 | VOCALExplore: Pay-as-You-Go Video Data Exploration and Model Building | 2023 | VLDB |
| 6 | 2,710 | Panorama: A Data System for Unbounded Vocabulary Querying over Video | 2020 | VLDB |
| 7 | 8,410 | TQVS: Temporal Queries over Video Streams in Action | 2020 | SIGMOD |
| 8 | 7,897 | Using VDMS to Index and Search 100M Images | 2021 | VLDB |
| 9 | 3,429 | SVQ: Streaming Video Queries | 2019 | SIGMOD |
| 10 | 13,827 | Demonstration of Krypton: Optimized CNN Inference for Occlusion-based Deep CNN Explanations | 2019 | VLDB |