TwelveLabs

We're transforming film production workflows with cutting-edge AI. ?? Forget the manual grind of sorting daily rushes; our Marengo model automatically organizes your footage. Imagine quickly categorizing a "Game of Thrones" style epic into scenes like “Battle Sequences” or “Dialogue in the Throne Room” at the click of a button! ?? What’s more? Our Pegasus model sifts through these scenes to highlight key moments, create summaries, and even suggests captions or titles, speeding up the process of repurposing or reviewing content dramatically. ?? Dive deeper into how our technology not only supports but amplifies the creative process, ensuring that artistry always takes center stage. Check out our blog for more on how Twelve Labs is setting new standards in film production. Read all about it here:?https://lnkd.in/ghndYHWF #VideoAI #TwelveLabs

In the era of multimodal content, extracting meaningful insights from video data requires sophisticated tools that can process and interpret multiple modalities such as text, audio, and visuals. TwelveLabs'?Embed API?empowers developers to generate rich, multimodal embeddings that encapsulate the essence of video content, including visual expressions, spoken words, and contextual interactions. These embeddings enable advanced applications like semantic video search by providing a unified vector representation of videos. ?? On the other hand,?Vespa.ai, a platform designed for low-latency computation over large datasets, excels in indexing and querying structured and vector data. With its support for approximate nearest-neighbor search and hybrid ranking capabilities, Vespa is an ideal partner for deploying scalable video search solutions. ?? Here are the key benefits of this integration: ?? Multimodal Understanding: Unified embeddings from TwelveLabs ensure a comprehensive representation of video content across modalities. ?? Scalability: Vespa.ai handles large datasets with ease, supporting low-latency queries even at scale. ?? Hybrid Search: Combining lexical (BM25) and semantic (ANN-based) search ensures precise retrieval of relevant results. ?? Flexibility: Developers can customize schemas, rank profiles, and query logic to fit specific use cases.

~ New Webinar ~ Check out #MultimodalWeekly 74 recording with Ce Zhang, Mohaiminul Islam, and Shoubin Yu: https://lnkd.in/gy4r3wny ?? They discussed: ?? LLoVi, a simple yet effective LLM framework for long-range video question-answering: https://lnkd.in/gCTkTzM9 ?? BIMBA, a selective-scan compression algorithm for long-range video question-answering ?? CREMA, a generalizable, highly efficient, and modular modality-fusion framework that can incorporate?any new modality?to enhance video reasoning: https://lnkd.in/gfJWqv6p Enjoy!

We're thrilled to announce that Soyoung Lee, co-founder of TwelveLabs, will be speaking at the HumanX event! Join her on March 11th from 9:30 AM - 10:15 AM on Stage 1, Infrastructure Track, as she participates in a panel titled "Aligning human expertise with AI infrastructure." This session will explore how businesses can design AI systems that amplify human expertise while boosting efficiency, enhancing decision-making, and driving innovation. Soyoung will share the stage with fellow experts Birago Jones from Pienso, Christopher Stephens from Appen, Greg Shove from Section, and Stephen Messer from Collective[i], with John Furrier, co-founder & CEO of SiliconANGLE & theCUBE, moderating the discussion. ??? Date: March 11 ?? Time: 9:30 AM - 10:15 AM ?? Location: Stage 1, HumanX Don't miss this opportunity to gain insights into integrating human and machine capabilities in your organization! #HumanX #TwelveLabs #VideoAI

??Join TwelveLabs at MWC Barcelona, from March 3-6! Visit us at SK Telecom's booth (Hall 3 Stand 3130) where we'll be showcasing our latest video understanding innovations. This year's "Converge. Connect. Create" theme perfectly aligns with how our technology is helping organizations extract meaningful insights from video content. Drop by to see demos of our AI-powered solutions and discuss specific applications for media and sports workflows. See you in Barcelona! #MWC25 #VideoAI #TwelveLabs

In the 74th?session of #MultimodalWeekly, we have three exciting presentations on video question-answering and video-language reasoning. ??Ce Zhang?will present?LLoVi, a simple yet effective LLM framework for long-range video question-answering. ??Mohaiminul Islam?will present BIMBA, a selective-scan compression algorithm for long-range video question-answering. ??Shoubin Yu?will present?CREMA, a generalizable, highly efficient, and modular modality-fusion framework that can incorporate?any new modality?to enhance video reasoning. Register for the webinar here: https://lnkd.in/gJGtscSH Join our Discord community: https://lnkd.in/gykKUF4K

Being in Doha, I can really sense the growth of our company. With Jae Lee and I here, it really feels TwelveLabs is growing into a truly global company we always believed it could become. Thank you to Web Summit Qatar and the Qatar Investment Authority for the invitation to visit and meet with the region’s top investment funds and business partners. We are thankful for the wonderful hospitality and look forward to developing a long-term relationship. Heading out tomorrow to Barcelona for Mobile World Congress to continue building global relationships with key stakeholders around the world. #TwelveLabs #GlobalExpansion #WebSummit #Qatar #MWC #Doha #Barcelona

??? Just in from Davos! Watch TwelveLabs' CEO Jae Lee and Global Head of Operations Anthony Giuliani discuss how our video understanding platform is helping organizations unlock value from their vast video libraries. Catch the full conversation on Snowflake's 'Data Cloud Now' with anchor Ryan C. Green?to hear how TwelveLabs is making video data more accessible and actionable than ever before ???? https://lnkd.in/gjyPy_dy #VideoAI #TwelveLabs

?? Join Twelve Labs' CEO, Jae Lee, at Web Summit Qatar! Jae will be on Centre Stage on February 26 to discuss "A SpaceX, not a Sputnik, moment”- exploring what DeepSeek’s recent breakthrough means for AI development. We'll dive into its market-shifting impact alongside AI luminaries Gilles Backhus from Recogni and tech journalist Rob Pegoraro from PCMag. Interested in how these advancements might reshape tech? Join us for this conversation! https://lnkd.in/gUCjhq4g #WebSummitQatar #AITech

In today’s data-driven world, video content is a rich source of information that combines multiple modalities, including visuals, audio, and text. However, due to their complexity, extracting meaningful insights from videos and enabling semantic search across them can be challenging. This is where the integration of TwelveLabs Embed API and Qdrant comes into play. The TwelveLabs Embed API empowers developers to create multimodal embeddings that capture the essence of video content, including visual expressions, body language, spoken words, and contextual cues. These embeddings are optimized for a unified vector space, enabling seamless cross-modal understanding. On the other hand, Qdrant is a powerful vector similarity search engine that allows you to store and query these embeddings efficiently. Our new integration demonstrates how to build a semantic video search workflow by combining TwelveLabs’ multimodal embedding capabilities with Qdrant’s vector search engine: ? Generate multimodal embeddings for videos using the TwelveLabs Embed API. ? Store and manage these embeddings in Qdrant. ? Perform semantic searches across video content using text or other modalities. Relevant links: ?? Complete tutorial: https://lnkd.in/gCzfPnfk ?? Colab notebook: https://lnkd.in/ghzFU6ne ?? TwelveLabs on Qdrant docs: https://lnkd.in/gWCHjJ-w