Brown University

Conference Program - SISAP 2024

17th International Conference on Similarity Search and Applications

Providence, RI, USA, Nov. 4th-6th, 2024

Presentations:

Saturday, November 2nd

17:30-21:00

WaterFire

Participants can meet in the lobby at Hampton Inn Downtown at 19:00 and walk along the Providence River to enjoy WaterFire.

Sunday, November 3rd

10:00-18:00

Newport Outing

Meet at the Hampton Inn Downtown at 10:00. A trolley will transport the participants to/from Newport.

Monday, November 4th

08:00

Poster Pickup

Those who printed posters at Fedex may pickup starting at 08:00.
08:30-09:00

Registration

Registration desk is open
09:00-09:15

Opening

Chairs: Benjamin Kimia (Brown University, USA) and Edgar Chávez (CICESE, México)
09:15-10:45

Keynote 1: Graph-based algorithms for similarity search: challenges and opportunities

Piotr Indyk (MIT, USA)
Chair: Benjamin Kimia
10:45-11:00 Coffee Break
11:00-12:00

Session 1: Approximate Nearest Neighbor

Chair: Michael E. Houle
Reon Uemura, Daichi Amagata, and Takahiro Hara
An Efficient Framework for Approximate Nearest Neighbor Search on High-dimensional Multi-metric Data
Malte Helin Johnsen and Martin Aumüller
An Empirical Evaluation of Search Strategies for Locality-Sensitive Hashing: Lookup, Voting, and Natural Classifier Search
12:00-13:00 Lunch and Poster Session
13:00-15:30

Session 2: Short Papers

Chair: Jan Sedmidubsky
Richard Connor, Alan Dearle, and Ben Claydon
Scalable Polyadic Queries
Ben Claydon, Richard Connor, Alan Dearle, and Lucia Vadicamo
Demonstrating the Efficacy of Polyadic Queries
Muhammad Rajabinasab, Anton Lautrup, Tobias Hyrup, and Arthur Zimek
A Dynamic Evaluation Metric for Feature Selection
Jan David Hüwel, Georg Stefan Schlake, Kevin Albrechts, and Christian Beecks
Identifying Propagating Signals with Spatio-Temporal Clustering in Multivariate Time Series
14:20-14:30 10 minute break
Félix Iglesias Vázquez, Conrado Martínez, and Tanja Zseby
Impact of the Neighborhood Parameter on Outlier Detection Algorithms
Philipp Röchner, Henrique Oliveira Marques, Ricardo Gabrielli Barreto Campello, Arthur Zimek and Franz Rothlauf
Robust Statistical Scaling of Outlier Scores: Improving the Quality of Outlier Probabilities for Outliers
Victor Reyes, Margarita Liarou, and Stephane Marchand-Maillet
A Topological Evaluation Model for Manifold Learning and Embedding Techniques
15:30-16:00 Coffee Break
16:00-17:30

Session 3: Similarity Models

Chair: Vlastislav Dohnal
Konstantin Schall, Kai Uwe Barthel, Nico Hezel, and Klaus Jung
Optimizing CLIP Models for Image Retrieval with Maintained Joint-Embedding Alignment
Mbasa Molo, Lucia Vadicamo, Emanuele Carlini, Claudio Gennaro, and Richard Connor
Information Dissimilarity Measures in Decentralized Knowledge Distillation: A Comparative Analysis
Miriama Jánošová, Petra Budikova, and Jan Sedmidubsky
Personalized Similarity Models for Evaluating Rehabilitation Exercises from Monocular Videos

Tuesday, November 5th

08:30-09:00

Registration

Registration desk is open
09:00-10:30

Keynote 2: Embeddings of and for the mind

Bradley C. Love (University College London)
Chair: Marco Patella
10:30-11:00 Coffee Break
11:00-12:30

Session 4: Clustering

Chair: Lucia Vadicamo
Miriama Jánošová, Andreas Lang, Petra Budíková, Erich Schubert, and Vlastislav Dohnal
Advancing the PAM Algorithm to Semi-Supervised k-Medoids Clustering
Camilla Birch Okkels, Martin Aumüller, and Arthur Zimek
On the Design of Scalable Outlier Detection Methods using Approximate Nearest Neighbor Graphs
Erich Schubert
Hierarchical Clustering without Pairwise Distances by Incremental Similarity Search
12:30-13:30 Lunch and Poster Session
13:30-15:00

Session 5: Indexing Challenge

Chairs: Martin Aumüller and Vladimir Mic
Martin Aumüller and Vladimir Mic
Introduction: the SISAP 2024 Indexing Challenge
David Procházka, Terézia Slanináková, Jozef Čerňanský, Jaroslav Oľha, Matej Antol, and Vlastislav Dohnal
Scaling Learned Metric Index to 100M Datasets
Erik Thordsen and Erich Schubert
Grouping Sketches to Index High-Dimensional Data in a Resource Limited Setting
Nico Hezel, Bruno Schilling, Kai Barthel, Konstantin Schall, and Klaus Jung
Adapting the Exploration Graph for high throughput in low recall regimes
Cole Foster, Edgar Chávez, and Benjamin Kimia
Top-Down Construction of Locally Monotonic Graphs for Similarity Search
Martin Aumüller and Vladimir Mic
Debate: Future of the SISAP Indexing Challenge
15:00-15:30 Coffee Break
15:30-16:30

Session 6: Applications of Similarity Search

Chair: Richard Connor
Andrej Cernek, Jan Sedmidubsky, and Petra Budikova
REHAB24-6: Physical Therapy Dataset for Analyzing Pose Estimation Methods
Jan Sedmidubsky, Nicol Dostálová, Roman Švaříček, and Wolf Culemann
ETDD70: Eye-Tracking Dataset for Classification of Dyslexia using AI-based Methods
16:30-17:30

Panel Discussion
The Next Frontier: Challenges and Applications of Trillion-Scale Vector Databases

Piotr Indyk, Bradley C. Love, Sanjiv Kumar
Chair: Benjamin Kimia & Edgar Chávez
18:00

Banquet Dinner at Red Stripe

15 minute walk from the conference venue

Wednesday, November 6th

08:30-09:00

Registration

Registration desk is open
09:00-10:30

Keynote 3: New Learning Objectives for Massive Scale Similarity Search

Sanjiv Kumar (Google Research)
Chair: Vincent Oria
10:30-11:00 Coffee Break and Group Photo
11:00-12:30

Session 7: Foundations of Similarity Search

Chair: Björn Þór Jónsson
Zaher Joukhadar, Hanxun Huang, Sarah Monazam Erfani, Ricardo J. G. B. Campello, Michael E. Houle, and James Bailey
Bayesian Estimation Approaches for Local Intrinsic Dimensionality
Marek Mahrík, Matúš Šikyňa, Vladimir Mic, and Pavel Zezula
Towards Personalized Similarity Search for Vector Databases
Michael E. Houle, Vincent Oria, and Hamideh Sabaei
Local Intrinsic Dimensionality and the Convergence Order of Fixed-Point Iteration
12:30-12:45

Closing and Announcement of Next SISAP Venue
12:45-14:00 Lunch