SeeSaw: Interactive Ad-hoc Search Over Image Databases
Summary: SeeSaw blends CLIP-like embeddings with box feedback for ad-hoc search in large image collections. Robust methods mitigate feedback-driven degradation, yielding avg AP gains +0.08 from 0.72 and +0.27 on hard queries across four datasets and 1k+ queries. (summarized by gpt-5-nano on Feb 09 2026)
Incoming Non-self Citations Over Time
Authors
- 1. Oscar Moll (Massachusetts Institute of Technology)
- 2. Manuel Favela (Massachusetts Institute of Technology)
- 3. Samuel Madden (Massachusetts Institute of Technology)
- 4. Vijay Gadepally (Massachusetts Institute of Technology)
- 5. Michael Cafarella (Massachusetts Institute of Technology)
BibTeX Citation
@inproceedings{moll_sigmod23,
title = {{SeeSaw: Interactive Ad-hoc Search Over Image Databases}},
author = {Moll, Oscar and Favela, Manuel and Madden, Samuel and Gadepally, Vijay and Cafarella, Michael},
series = {{SIGMOD} '23},
booktitle = {Proceedings of the {ACM} {SIGMOD} International Conference on Management of Data},
publisher = {Association for Computing Machinery},
doi = {10.1145/3626754},
url = {https://dl.acm.org/doi/10.1145/3626754},
year = {2023}
}Incoming Citations (Sorted by Pagerank)
Showing 4 of 4 citing papers.
| Rank | Citing Paper | Year | Venue | Pagerank |
|---|---|---|---|---|
| 3,684 | ThalamusDB: Approximate Query Processing on Multi-Modal Data | 2024 | SIGMOD | 7.2033959e-05 |
| 9,881 | The Image Calculator: 10x Faster Image-AI Inference by Replacing JPEG with Self-designing Storage Format | 2024 | SIGMOD | 5.2040783e-05 |
| 10,247 | GEM: A Native Graph-based Index for Multi-Vector Retrieval | 2026 | SIGMOD | 5.093636e-05 |
| 10,917 | Deja Vu: Efficient Video-Language Query Engine with Learning-based Inter-Frame Computation Reuse | 2025 | VLDB | 5.093636e-05 |
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 |
|---|---|---|---|---|
| 1,862 | MindReader: Querying databases through multiple examples | 1998 | VLDB | 9.5951515e-05 |
| 3,835 | FALCON: Feedback Adaptive Loop for Content-Based Retrieval | 2000 | VLDB | 7.0835179e-05 |
| 4,910 | Actively Soliciting Feedback for Query Answers in Keyword Search-Based Data Integration | 2013 | VLDB | 6.4484207e-05 |
Previous
Page 1 / 1
Next