SeamCam quantifies camouflage by computing one minus the highest IoU recoverable from category-conditioned detection proposals against a ground-truth mask, achieving 78.82% agreement with human judgments.
In: Proceedings of the IEEE conference on computer vision and pattern recognition
3 Pith papers cite this work. Polarity classification is still indexing.
3
Pith papers citing it
fields
cs.CV 3years
2026 3representative citing papers
An agentic mRAG framework uses GRPO-trained visual reranking and active rejection to verify retrieved candidate entities, achieving state-of-the-art on three KB-VQA benchmarks.
A retrieval-based framework using foundation models for pose-aware correspondence to estimate population-level wildlife body proportions from unconstrained images, with reported 10-20% median relative errors on bird and amphibian datasets.
citing papers explorer
-
SeamCam: Quantifying Seamless Camouflage via Multi-Cue Visual Detectability
SeamCam quantifies camouflage by computing one minus the highest IoU recoverable from category-conditioned detection proposals against a ground-truth mask, achieving 78.82% agreement with human judgments.
-
MMAgent-R$^2$: Learning to Rerank and Reject for Agentic mRAG
An agentic mRAG framework uses GRPO-trained visual reranking and active rejection to verify retrieved candidate entities, achieving state-of-the-art on three KB-VQA benchmarks.
-
WildProp: Visual Estimation of Wildlife Body Proportions at Scale
A retrieval-based framework using foundation models for pose-aware correspondence to estimate population-level wildlife body proportions from unconstrained images, with reported 10-20% median relative errors on bird and amphibian datasets.