Amazon’s papers at this year’s International Conference on Computer Vision, arranged by topic. 3-D Hal3d: Hierarchical active learning for fine-grained 3D sub-markingFengen Yu, Yiming Qian, Francisca Gil Urata, Brian Jackson, Eric Bennett, Richard Zhang IMGEON: Image induced geometry-noticing voxel representation for 3D vision with multiple viewpointTao You, Shun-Po Chuang, Yu-Lun Liu, Cheng Sun, Ke Zhang, … Read more
Many recent progress in artificial intelligence is the result of representation learning: A machine learning model learns to take data elements such as vectors in a multidimenal space where geometric relationships between vectors correspond to semantic relationships between objects. The M5 team at Amazon strives to construct general semantic representations of data related to Amazon … Read more
Recent Basic Models-As Large Language Models-Has achieved advanced performance by learning how to restructure randomly masked text or images. Without any human supervision, these models can learn powerful representations from Large Corpora of unmarked data by simple “filling in the gaps”. Related content Four CVPR papers from Prime Video examine a wide set of topics … Read more
Vision-language models that map images and text into a common representative space have shown remacable performance on a wide range of multimodal AI tasks. But they are typically trained on text images: Each text input is connected to a single image. This limits the usability of the models. For example, you may wish that a … Read more
Many machine learning (ML) involves applications that embed data in a representation room where the geometric relations between embedders have semantic content. Performing a useful task often involves picking up a embedding closest neighbors in the room: For example, the answer near an inquiry that is embedded, the image is embarking near the embedding of … Read more