Chengan Che

Chengan Che

PhD Researcher in Computer Vision

Back to the Feature

less than 1 minute read

Published:

Back to the Feature poster

Back to the Feature: Explaining Video Classifiers with Video Counterfactual Explanations

Chao Wang, Chengan Che, Xinyue Chen, Sophia Tsoka, Luis C. Garcia-Peraza-Herrera

CVPR 2026

Back to the Feature explains video classifiers by generating counterfactual examples in feature space. The method identifies changes that alter model predictions while preserving the temporal and semantic structure of the original video.

Paper ยท Code

You May Also Enjoy

PL-Stitch

less than 1 minute read

Published:

Self-supervised learning of procedure-aware video representations through probabilistic listwise temporal ranking.

LEMON

less than 1 minute read

Published:

A large-scale open-access surgical video dataset and foundation model for transferable surgical visual representation learning.

SurgLIME

less than 1 minute read

Published:

Scalable surgical vision-language pre-training with LLM-generated text and confidence-aware alignment.