Tag
Pinterest 推出基于其 Pinterest Intelligence 视觉与生成式 AI 的新功能 "Beauty Guides"，可将美发、美甲等灵感 Pins 转化为包含专业术语、时长、价格和维护建议的可执行计划，方便用户带去沙龙。
Apple combines machine learning and homomorphic encryption to enable private server lookups for features like Enhanced Visual Search for Photos, and open-sources an HE library for developers.
Daydream, an AI-powered fashion app, launches new features using Apple Intelligence to let users shop outfits from camera roll photos and search via Siri, enhancing personalized fashion discovery.
The article outlines five ways to use Google Search tools, including AI Mode, Lens, Circle to Search, and Search Live, to enhance home decor projects by visualizing furniture, finding vintage items, and assisting with DIY tasks.
AWS announces an expanded commitment to a long-standing partnership, scaling AI-powered visual search and personalized discovery globally.
Google marks 25 years of Google Images by introducing a new browsable image gallery and AI-powered image generation in Search using the Nano Banana model, enabling users to create custom visuals from text prompts.
PixelRAG is an open-source retrieval system that bypasses HTML parsing by screenshotting web pages and using vision-language models to read answers directly from pixels, claiming significant accuracy improvements over text-based RAG.
Visual-Seeker proposes a visual-native multimodal deep search agent that actively reasons over fine-grained visual details and synthesizes multimodal evidence, achieving state-of-the-art performance on five challenging multimodal search benchmarks.
Amazon's updated search bar generates AI images of clothing and home goods based on text descriptions, allowing users to find similar real products, though the AI images themselves are not purchasable.
Amazon is rolling out AI-generated product images in search results to help shoppers visualize options, but critics question using fake photos in a real product marketplace.
InterLV-Search is a new benchmark introduced in this paper to evaluate interleaved language-vision agentic search, highlighting limitations in current systems regarding visual evidence seeking and multimodal integration.
Google has enhanced its Circle to Search feature by leveraging Gemini 3 to enable holistic scene recognition of screen content, with a particular focus on breaking down fashion ensembles into individual items and supporting virtual try-ons. This update allows users to seamlessly find alternative products and preview how they look without needing to take screenshots, thereby improving the overall visual search experience.
OpenAI demonstrates a new ChatGPT feature that lets users upload room inspiration images and receive shoppable links to similar furniture and decor items.