Devpost
Participate in our public hackathons
Devpost for Teams
Access your company's private hackathons
Grow your developer ecosystem and promote your platform
Drive innovation, collaboration, and retention within your organization
By use case
Blog
Insights into hackathon planning and participation
Customer stories
Inspiration from peers and other industry leaders
Planning guides
Best practices for planning online and in-person hackathons
Webinars & events
Upcoming events and on-demand recordings
Help desk
Common questions and support documentation
A smarter way to translate PDFs without breaking the design.
An intelligent open-vocabulary tracker that learns new views of an object on the fly, using multimodal embeddings and a dynamic memory bank for long-term, occlusion-robust tracking.
Seamless PDF translation with layout perfectly preserved.
English to Mandarin and Mandarin to English document translation system
Scene localisation and tracking
Accurate, layout-preserving document translation across PDFs, scans, and complex page structures.
VisionProbe is a zero-shot real-time AI system that finds and tracks any user-defined object using text/image prompts powered by CLIP GroundingDINO and ByteTrack with cross-camera tracking and memory.
Dimsum AI is a next-generation document translation system that redefines how we experience multilingual text.
The objective is to build an advanced, multi-stage vision system for detecting and tracking a Person of Interest/ Object (PoI) across a network of non-overlapping cameras.
A smart Mandarin-English OCR system that can read and translate text from documents.
PDFLattice delivers flawless Mandarin–English PDF translation with preserved layouts tables, images, columns, and hyperlinks using Deepseek-OCR, and other brand new technologies.
The LPP system is a robust, hackathon-ready solution designed for high-accuracy, bidirectional OCR translation (Mandarin ↔ English) on PDF documents.
Where Vision Meets Understanding
A bidirectional Mandarin–English PDF translation engine using dual pipelines for digital and scanned PDFs, preserving full layout with OCR, DLA, inpainting, and adaptive reconstruction.
Track, identify, and count any object in live video—accurately, robustly, in real time
Crazy Translation
1 – 16 of 16
