BiMa combines scene-element-aware visual fusion with VAE-based text disentanglement, reporting SOTA retrieval and stronger OOD generalization, but its dataset-derived taxonomy dictionary risks leakage.
Man is to computer programmer as woman is to homemaker? debiasing word embeddings.Annual Conference on Neural Information Processing Systems (NeurIPS), pages 4349–4357,
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
citation-role summary
background 1
citation-polarity summary
fields
cs.CV 1years
2025 1verdicts
CONDITIONAL 1roles
background 1polarities
unclear 1representative citing papers
citing papers explorer
-
BiMa: Towards Biases Mitigation for Text-Video Retrieval via Scene Element Guidance
BiMa combines scene-element-aware visual fusion with VAE-based text disentanglement, reporting SOTA retrieval and stronger OOD generalization, but its dataset-derived taxonomy dictionary risks leakage.