Reproduce “STARE: Scene Text-Aware multimodal Retrieval for Everyday objects” on OpenResearch
Turn your favorite coding agents into research agents that review literature, develop hypotheses, and run experiments.
Universal app for Apple silicon and Intel. Requires macOS 11 or later.
About this paper
Kento Tokura, Ryosuke Korekata, Daichi Yashima, Kei Katsumata, Kanon Amemiya, Miyu Goko, Komei Sugiura
STARE helps robots retrieve objects from pre-collected images by combining visual features with scene text and reranking candidates against named entities in instructions. It stores image-side representations during pre-exploration, then expands instructions and matches named clues to detected text at query time. On GoGetIt-Instruction, it achieves 92.8 ± 0.6% recall@10, establishing performance on that retrieval benchmark.
Summary by alphaXiv.
Tip: change arxiv.org to autoarxiv.org in any arXiv abstract link to open the paper here.