SEEK-CBM: Editable and Interpretable Retrieval for Elephant Re-Identification

Name: SEEK-CBM: Interpretable and Editable Retrieval for Elephant Re-Identification
Uploaded: 2026-07-29
Duration: 59 min 26 s
Description: Reading-group talk on SEEK-CBM: editable, interpretable concept-bottleneck retrieval for elephant re-identification.

Antoine Salaün; Vaibhav Balloli; Timm Haucke; Elizabeth Bondi-Kelly; Sara Beery

Figure from “SEEK-CBM: Editable and Interpretable Retrieval for Elephant Re-Identification”

Summary

SEEK-CBM upgrades CHAIR to modern vision architectures and self-supervised techniques to achieve a 497% improvement in performance.

How this fits together

Builds on Are They the Same Picture? Adapting Concept Bottleneck Models for Human-AI Collaboration in Image Retrieval

See the full research lineage →

Talk

Topics

Cite this paper

@inproceedings{seekcbm2026salaun,
  title     = {{SEEK}-{CBM}: Editable and Interpretable Retrieval for Elephant Re-Identification},
  author    = {Sala{\"u}n, Antoine and Balloli, Vaibhav and Haucke, Timm and Bondi-Kelly, Elizabeth and Beery, Sara},
  booktitle = {6th Workshop on CV4Animals: Computer Vision for Animal Behavior Tracking and Modeling, in conjunction with CVPR 2026},
  year      = {2026}
}

← All publications