Controlled counterfactual perturbations reveal no correlation between embedding cosine similarity and approximation behavior in two visual grounding models.
Transvg++: End-to-end visual grounding with language conditioned vision transformer.IEEE Transac- tions on Pattern Analysis and Machine Intelligence, 45(11): 13636–13652
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CV 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
Investigating Anisotropy in Visual Grounding under Controlled Counterfactual Perturbations
Controlled counterfactual perturbations reveal no correlation between embedding cosine similarity and approximation behavior in two visual grounding models.