Ragav Sachdeva

.@TakeCareOS is an AI-first operating system for care agencies. It consolidates every function an agency runs on — rostering, shifts, CRM, care notes, messaging, invoicing, timesheets, and compliance — into one place, with AI agents that automate the admin work coordinators currently do by hand. Congrats on the launch, @ragavsachdeva! ycombinator.com/launches/QLS-t…

🚨🚨🚨Deadline <10 days 🚨🚨🚨 Submit your extended abstracts on AI driven comic analysis to the COMIQ workshop #ICCV2025 comiq-iccv25.github.io

🚨 #ICCV2025 Workshop Alert! 🚨 🔥[COMIQ] Comic Intelligence Quotient: Advances and Challenges in AI-driven Comic Analysis We’re exploring how machines interpret abstract visual storytelling media; dare I say, a true test for AGI 🫣 🔗 Pls consider submitting abstracts. Link👇

🚀 Exciting news! Our paper "CoMix: A Comprehensive Benchmark for Multi-Task Comic Understanding" has been accepted at #NeurIPS2024 (B&D)! It sets a new standard for multi-task comic analysis, please dive into the details here: arxiv.org/abs/2407.03550, and: see you in Vancouver!

Tails Tell Tales Chapter-Wide Manga Transcriptions with Character Names huggingface.co/papers/2408.00… Enabling engagement of manga by visually impaired individuals presents a significant challenge due to its inherently visual nature. With the goal of fostering accessibility, this paper aims to generate a dialogue transcript of a complete manga chapter, entirely automatically, with a particular emphasis on ensuring narrative consistency. This entails identifying (i) what is being said, i.e., detecting the texts on each page and classifying them into essential vs non-essential, and (ii) who is saying it, i.e., attributing each dialogue to its speaker, while ensuring the same characters are named consistently throughout the chapter. To this end, we introduce: (i) Magiv2, a model that is capable of generating high-quality chapter-wide manga transcripts with named characters and significantly higher precision in speaker diarisation over prior works; (ii) an extension of the PopManga evaluation dataset, which now includes annotations for speech-bubble tail boxes, associations of text to corresponding tails, classifications of text as essential or non-essential, and the identity for each character box; and (iii) a new character bank dataset, which comprises over 11K characters from 76 manga series, featuring 11.5K exemplar character images in total, as well as a list of chapters in which they appear.

@CVPR Manga Whisperer had a beautiful poster themed like a manga!

📢 The Manga Whisperer will appear at #CVPR2024 @CVPR 🚀 I really didn't expect 1600+ downloads on 🤗Hugging Face in the last two months. See you all in Seattle! 🫰

📃 The Manga Whisperer: Automatically Generating Transcriptions for Comics ✍️ Ragav Sachdeva, Andrew Zisserman @Oxford_VGG 📕 arXiv: arxiv.org/abs/2401.10224 💻 github: github.com/ragavsachdeva/… 🤗try it yourself: huggingface.co/spaces/ragavsa…

The Change You Want to See (Now in 3D) @RagavSachdeva, Andrew Zisserman tl;dr: wide baseline change detection via image matching and monodepth. arxiv.org/abs/2308.10417…

ZoeDepth: Zero-shot Transfer by Combining Relative and Metric Depth abs: arxiv.org/abs/2302.12288