4 papers
Pinterest Canvas: Large-Scale Image Generation at Pinterest
Yu Wang, Eric Tzeng, Raymond Shiau +3
While recent image generation models demonstrate a remarkable ability to handle a wide variety of image generation tasks, this flexibility makes them hard to control via prompting…
PinPoint: Evaluation of Composed Image Retrieval with Explicit Negatives, Multi-Image Queries, and Paraphrase Testing
Rohan Mahadev, Joyce Yuan, Patrick Poirson +3
Composed Image Retrieval (CIR) has made significant progress, yet current benchmarks are limited to single ground-truth answers and lack the annotations needed to evaluate false po…
PinCLIP: Large-scale Foundational Multimodal Representation at Pinterest
Josh Beal, Eric Kim, Jinfeng Rao +3
While multi-modal Visual Language Models (VLMs) have demonstrated significant success across various domains, the integration of VLMs into recommendation and retrieval systems rema…
Visual Product Graph: Bridging Visual Products And Composite Images For End-to-End Style Recommendations
Yue Li Du, Ben Alexander, Mikhail Antonenka +3
Retrieving semantically similar but visually distinct contents has been a critical capability in visual search systems. In this work, we aim to tackle this problem with Visual Prod…