AI image detection and recognition

PixelProse is a large-scale dataset created by tomg-group-umd that leverages the advanced visual-language model Gemini 1.0 Pro Vision to generate more than 16 million detailed image descriptions. This dataset is of great significance for developing and improving image-to-text conversion technology, which can be used for image description generation, visual question answering and other tasks.

PlantIdentify is an application that uses artificial intelligence technology to quickly identify plant species through photos uploaded by users or taken with mobile phone cameras. It's suitable for gardening enthusiasts, nature lovers, and anyone interested in the plants around them. Key benefits of the app include instant plant identification, free use, multi-language support and the ability to save identification history.

ODIN (Omni-Dimensional INstance segmentation) is a model that can perform segmentation and labeling on 2D RGB images and 3D point clouds using a converter architecture. It differentiates between 2D and 3D feature operations by fusing information alternately within 2D views and between 3D views. ODIN achieves state-of-the-art performance on ScanNet200, Matterport3D and AI2THOR 3D instance segmentation benchmarks, and competitive performance on ScanNet, S3DIS and COCO. It surpasses all previous works when using sampled point clouds from 3D meshes instead of perceptual 3D point clouds. When used as a 3D perception engine in a coachable embodied agent architecture, it sets a new state-of-the-art on the TEACh conversational action benchmark. Our code and checkpoints can be found on the project website.