Text-guided class-agnostic counting models exhibit significant weaknesses in grounding textual prompts to visual objects, as demonstrated by new negative-label and distractor tests on a multi-category dataset.
Learning to count anything: Reference-lessclass-agnosticcountingwithweaksupervision
2 Pith papers cite this work, alongside 12 external citations. Polarity classification is still indexing.
2
Pith papers citing it
12
external citations · external index
fields
cs.CV 2years
2026 2verdicts
UNVERDICTED 2representative citing papers
RT-Counter introduces VPT and Weaformer modules to achieve competitive accuracy and real-time inference in text-guided open-vocabulary object counting.
citing papers explorer
-
Does it Really Count? Assessing Semantic Grounding in Text-Guided Class-Agnostic Counting
Text-guided class-agnostic counting models exhibit significant weaknesses in grounding textual prompts to visual objects, as demonstrated by new negative-label and distractor tests on a multi-category dataset.
-
RT-Counter: Real-Time Text-Guided Open-Vocabulary Object Counting
RT-Counter introduces VPT and Weaformer modules to achieve competitive accuracy and real-time inference in text-guided open-vocabulary object counting.