The Orbiting Carbon Observatory‐2 (OCO‐2) collects solar‐induced chlorophyll fluorescence (SIF) at high spatial resolution along orbits ( trueSIF¯oco2_orbit), but its discontinuous spatial coverage precludes its full potential for understanding the mechanistic SIF‐photosynthesis relationship. This study developed a spatially contiguous global OCO‐2 SIF product at 0.05° and 16‐day resolutions ( trueSIF¯oco2_005) using machine learning constrained by physiological understandings. This was achieved by stratifying biomes and times for training and predictions, which accounts for varying plant physiological properties in space and time. trueSIF¯oco2_005 accurately preserved the spatiotemporal variations of trueSIF¯oco2_orbit across the globe. Validation of trueSIF¯oco2_005 with Chlorophyll Fluorescence Imaging Spectrometer airborne measurements revealed striking consistency (R2 = 0.72; regression slope = 0.96). Further, without time and biome stratification, (1) trueSIF¯oco2_005 of croplands, deciduous temperate, and needleleaf forests would be underestimated during the peak season, (2) trueSIF¯oco2_005 of needleleaf forests would be overestimated during autumn, and (3) the capability of trueSIF¯oco2_005 to detect drought would be diminished.

Abstract-We propose a new superpixel algorithm based on exploiting the boundary information of an image, as objects in images can generally be described by their boundaries. Our proposed approach initially estimates the boundaries and uses them to place superpixel seeds in the areas in which they are more dense. Afterwards, we minimize an energy function in order to expand the seeds into full superpixels. In addition to standard terms such as color consistency and compactness, we propose using the geodesic distance which concentrates small superpixels in regions of the image with more information, while letting larger superpixels cover more homogeneous regions. By both improving the initialization using the boundaries and coherency of the superpixels with geodesic distances, we are able to maintain the coherency of the image structure with fewer superpixels than other approaches. We show the resulting algorithm to yield smaller Variation of Information metrics in seven different datasets while maintaining Undersegmentation Error values similar to the state-of-the-art methods.

Finding a product in the fashion world can be a daunting task. Everyday, e-commerce sites are updating with thousands of images and their associated metadata (textual information), deepening the problem, akin to finding a needle in a haystack. In this paper, we leverage both the images and textual metadata and propose a joint multi-modal embedding that maps both the text and images into a common latent space. Distances in the latent space correspond to similarity between products, allowing us to effectively perform retrieval in this latent space, which is both efficient and accurate. We train this embedding using large-scale real world e-commerce data by both minimizing the similarity between related products and using auxiliary classification networks to that encourage the embedding to have semantic meaning. We compare against existing approaches and show significant improvements in retrieval tasks on a large-scale e-commerce dataset. We also provide an analysis of the different metadata.

No abstract