Abstract: A system includes: a training dataset including first objects of a first modality and second objects of a second modality different than the first modality, where the second objects include text that is descriptive of the first objects; a first matrix including first relevance values indicative of relevance between the first objects and the second objects, respectively; a second matrix including second relevance values indicative of relevance between the second objects and the first objects, respectively; and a training module configured to: assign ones of the second objects to bins based on distances between the ones of the objects and a query; determine a ranking measure based on a number of the ones of the second objects assigned to the bins; determine losses based on the ranking measure and the first and second matrices; determine a final loss based on the losses; train embedding functions based on the final loss.

Abstract: A training system includes: a training dataset including first objects of a first modality and second objects of a second modality that are associated with the first objects, respectively; a first matrix including first relevance values indicative of relevance between the first objects and the second objects, respectively; a second matrix including second relevance values indicative of relevance between the second objects and the first objects, respectively; and a training module configured to: based on similarities between ones of the second objects, generate a third matrix by selectively adding first additional relevance values to the first matrix; based on the similarities between the ones of the second objects, generate a fourth matrix by selectively adding second additional relevance values to the second matrix; and store the third and fourth matrices in memory of a search module for cross-modal retrieval in response to receipt of search queries.

Abstract: A method for processing a new sample in a data stream for updating a machine learning model configured for performing a task. The machine learning model is implemented by a processor in communication with a memory storing previous samples. The new sample is received, and the machine learning model is trained using combined samples including the new sample and the previous samples. The new sample is stored or not stored in the memory based on distances between the samples in an embedding space learned by the machine learning model.

Abstract: A method of performing image retrieval includes: obtaining a query image; generating a global feature descriptor of the query image by inputting the query image into a convolutional neural network (CNN) and obtaining the global feature descriptor as an output of the CNN, where parameters of the CNN are learned during training of the CNN on a batch of training images using a listwise ranking loss function and optimizing a quantized mean average precision ranking evaluation metric; determining similarities between the query image and other images based on distances between the global feature descriptor of the query image and global feature descriptors of the other images, respectively; ranking the other images based on the similarities, respectively; and selecting a set of the other images based on the similarities between the query image and the other images.

Abstract: Management and processing of floating aquatic plants such as the species Pistia stratiotes (Araceae) and other water macrophytes produce (I) macrophyte paste, (II) macrophyte broth, (III) macrophyte bagasse, (IV) macrophyte bran and (V) macrophyte protein concentrates. The interaction of these by-products with ingredients used in animal and human feed significantly increase the final protein concentration of the feed obtaining high potential to supply animal and human demands for protein. The system provides a sustainable model for protein production that provides the essential benefits of treating effluent with high concentrations of organic matter in bodies of water such as rivers, lakes and dams to thereby provide an incalculable capacity for producing animal feeds and great potential for meeting human demand for protein.

Abstract: A system for detecting and describing keypoints in images is described. A camera is configured to capture an image including a plurality of pixels. A fully convolutional network is configured to jointly and concurrently: generate descriptors for each of the pixels, respectively; generate reliability scores for each of the pixels, respectively; and generate repeatability scores for each of the pixels, respectively. A scoring module is configured to generate scores for the pixels, respectively, based on the reliability scores and the repeatability scores of the pixels, respectively. A keypoint list module is configured to: select X of the pixels having the X highest scores, where X is an integer greater than 1; and generate a keypoint list including: locations of the selected X pixels; and the descriptors of the selected X pixels.

Abstract: A training system includes: a training dataset including first objects of a first modality and second objects of a second modality that are associated with the first objects, respectively; a first matrix including first relevance values indicative of relevance between the first objects and the second objects, respectively; a second matrix including second relevance values indicative of relevance between the second objects and the first objects, respectively; and a training module configured to: based on similarities between ones of the second objects, generate a third matrix by selectively adding first additional relevance values to the first matrix; based on the similarities between the ones of the second objects, generate a fourth matrix by selectively adding second additional relevance values to the second matrix; and store the third and fourth matrices in memory of a search module for cross-modal retrieval in response to receipt of search queries.

Abstract: A system for detecting and describing keypoints in images is described. A camera is configured to capture an image including a plurality of pixels. A fully convolutional network is configured to jointly and concurrently: generate descriptors for each of the pixels, respectively; generate reliability scores for each of the pixels, respectively; and generate repeatability scores for each of the pixels, respectively. A scoring module is configured to generate scores for the pixels, respectively, based on the reliability scores and the repeatability scores of the pixels, respectively. A keypoint list module is configured to: select X of the pixels having the X highest scores, where X is an integer greater than 1; and generate a keypoint list including: locations of the selected X pixels; and the descriptors of the selected X pixels.

Abstract: A method of performing image retrieval includes: obtaining a query image; generating a global feature descriptor of the query image by inputting the query image into a convolutional neural network (CNN) and obtaining the global feature descriptor as an output of the CNN, where parameters of the CNN are learned during training of the CNN on a batch of training images using a listwise ranking loss function and optimizing a quantized mean average precision ranking evaluation metric; determining similarities between the query image and other images based on distances between the global feature descriptor of the query image and global feature descriptors of the other images, respectively; ranking the other images based on the similarities, respectively; and selecting a set of the other images based on the similarities between the query image and the other images.

Abstract: A process for ore moisture removal by exposure of the ore to a hot and dry air stream is described. Also described is a conveyor belt and a transfer chute adapted for the use of the above process. Among other aspects, the process has the function of reducing moisture in ores prior to the shipping stage of this material.

Abstract: A process for ore moisture removal by exposure of the ore to a hot and dry air stream is described. Also described is a conveyor belt and a transfer chute adapted for the use of the above process. Among other aspects, the process has the function of reducing moisture in ores prior to the shipping stage of this material.

Abstract: The present invention relates to a system which makes use of a multiple reel on which groups of flexible lines supported by articulated structures (8, 9) are wound. The groups of flexible lines are interconnected at one end to flexible production and utility lines (4) emerging from the seabed and, at the other end, to connection blocks (10, 11) which may be connected to connection plates (15, 16, 17, 18) on at least one connection tower (13, 14) fixed to the vessel. As the connections are redundant, it is always possible to reposition one group of flexible lines while another group is connected, which gives the transfer system (2) total freedom of movement.