Abstract: The invention provides a Probiotic microcapsule and a preparation method thereof, relating to the technical field of Probiotic products. The method includes the following steps: (a) preparing a capsule core containing Probiotics: mixing the capsule core materials including Probiotic powder, microcrystalline cellulose and starch, then adding a hydroxypropyl methylcellulose solution thereinto, while mixing evenly, making the obtained mixture materials into spherical particulate capsule cores by the extrusion spherization method; (b) coating by atomization: coating the microcapsule cores with a coating material solution in a single layer or multiple layers by atomization, getting core-shell microcapsules. The Probiotic microcapsules prepared by the present invention have a large encapsulation, uniform microcapsule particles, controllable particle size, storage-resistance, targetability to intestinal tracts, resistance to gastric acids and high temperature stability.

Abstract: A method includes obtaining a set of unlabeled training samples. For each training sample in the set of unlabeled training samples generating, the method includes using a machine learning model and the training sample, a corresponding first prediction, generating, using the machine learning model and a modified unlabeled training sample, a second prediction, the modified unlabeled training sample based on the training sample, and determining a difference between the first prediction and the second prediction. The method includes selecting, based on the differences, a subset of the set of unlabeled training samples. For each training sample in the subset of the set of unlabeled training samples, the method includes obtaining a ground truth label for the training sample, and generating a corresponding labeled training sample based on the training sample paired with the ground truth label. The method includes training the machine learning model using the corresponding labeled training samples.

Abstract: An online system extracts information from non-fixed form documents. The online system receives an image of a form document and obtains a set of phrases and locations of the set of phrases on the form image. For at least one field, the online system determines key scores for the set of phrases. The online system identifies a set of candidate values for the field from the set of identified phrases and identifies a set of neighbors for each candidate value from the set of identified phrases. The online system determines neighbor scores, where a neighbor score for a candidate value and a respective neighbor is determined based on the key score for the neighbor and a spatial relationship of the neighbor to the candidate value. The online system selects a candidate value and a respective neighbor based on the neighbor score as the value and key for the field.

Abstract: Systems and methods are provided for weakly supervised natural language localization (WSNLL), for example, as implemented in a neural network or model. The WSNLL network is trained with long, untrimmed videos, i.e., videos that have not been temporally segmented or annotated. The WSNLL network or model defines or generates a video-sentence pair, which corresponds to a pairing of an untrimmed video with an input text sentence. According to some embodiments, the WSNLL network or model is implemented with a two-branch architecture, where one branch performs segment sentence alignment and the other one conducts segment selection. These methods and systems are specifically used to predict how a video proposal matches a text query using respective visual and text features.

Abstract: Embodiments described herein provide an online domain adaptation framework based on cross-domain bootstrapping for online domain adaptation, in which the target domain streaming data is deleted immediately after adapted. At each online query, the data diversity is increased across domains by bootstrapping the source domain to form diverse combinations with the current target query. To fully take advantage of the valuable discrepancies among the diverse combinations, a set of independent learners are trained to preserve the differences. The knowledge of the learners is then integrated by exchanging their predicted pseudo-labels on the current target query to co-supervise the learning on the target domain, but without sharing the weights to maintain the learners' divergence.

Abstract: Embodiments described herein provide methods and systems for open vocabulary object detection of images. given a pre-trained vision-language model and an image-caption pair, an activation map may be computed in the image that corresponds to an object of interest mentioned in the caption. The activation map is then converted into a pseudo bounding-box label for the corresponding object category. The open vocabulary detector is then directly supervised by these pseudo box-labels, which enables training object detectors with no human-provided bounding-box annotations.

Abstract: An application server may receive an input document including a set of input text fields and an input key phrase querying a value for a key-value pair that corresponds to one or more of the set of input text fields. The application server may extract, using an optical character recognition model, a set of character strings and a set of two-dimensional locations of the set of character strings on a layout of the input document. After extraction, the application server may input the extracted set of character strings and the set of two-dimensional locations into a machine learned model that is trained to compute a probability that a character string corresponds to the value for the key-value pair. The application server may then identify the value for the key-value pair corresponding to the input key phrase and may out the identified value.

Abstract: Embodiments described a field extraction system that does not require field-level annotations for training. Specifically, the training process is bootstrapped by mining pseudo-labels from unlabeled forms using simple rules. Then, a transformer-based structure is used to model interactions between text tokens in the input form and predict a field tag for each token accordingly. The pseudo-labels are used to supervise the transformer training. As the pseudo-labels are noisy, a refinement module that contains a sequence of branches is used to refine the pseudo-labels. Each of the refinement branches conducts field tagging and generates refined labels. At each stage, a branch is optimized by the labels ensembled from all previous branches to reduce label noise.

Abstract: Embodiments described a field extraction system that does not require field-level annotations for training. Specifically, the training process is bootstrapped by mining pseudo-labels from unlabeled forms using simple rules. Then, a transformer-based structure is used to model interactions between text tokens in the input form and predict a field tag for each token accordingly. The pseudo-labels are used to supervise the transformer training. As the pseudo-labels are noisy, a refinement module that contains a sequence of branches is used to refine the pseudo-labels. Each of the refinement branches conducts field tagging and generates refined labels. At each stage, a branch is optimized by the labels ensembled from all previous branches to reduce label noise.

Abstract: Determining object importance in vehicle control systems can include obtaining, for a vehicle in operation, an image of a dynamic scene, identifying an object type associated with one or more objects in the image, determining, based on the object type and a goal associated with the vehicle, an importance metric associated with the one or more objects, and controlling the vehicle based at least in part on the importance metric associated with the one or more objects.

Abstract: An online system extracts information from non-fixed form documents. The online system receives an image of a form document and obtains a set of phrases and locations of the set of phrases on the form image. For at least one field, the online system determines key scores for the set of phrases. The online system identifies a set of candidate values for the field from the set of identified phrases and identifies a set of neighbors for each candidate value from the set of identified phrases. The online system determines neighbor scores, where a neighbor score for a candidate value and a respective neighbor is determined based on the key score for the neighbor and a spatial relationship of the neighbor to the candidate value. The online system selects a candidate value and a respective neighbor based on the neighbor score as the value and key for the field.

Abstract: A system and method for utilizing a temporal recurrent network for online action detection that include receiving image data that is based on at least one image captured by a vehicle camera system. The system and method also include analyzing the image data to determine a plurality of image frames and outputting at least one goal-oriented action as determined during a current image frame. The system and method further include controlling a vehicle to be autonomously driven based on a naturalistic driving behavior data set that includes the at least one goal-oriented action.

Abstract: Embodiments described herein provide a two-stage online detection of action start system including a classification module and a localization module. The classification module generates a set of action scores corresponding to a first video frame from the video, based on the first video frame and video frames before the first video frames in the video. Each action score indicating a respective probability that the first video frame contains a respective action class. The localization module is coupled to the classification module for receiving the set of action scores from the classification module and generating an action-agnostic start probability that the first video frame contains an action start.

Abstract: Embodiments described herein provide systems and methods for a partially supervised training model for online action detection. Specifically, the online action detection framework may include two modules that are trained jointly—a Temporal Proposal Generator (TPG) and an Online Action Recognizer (OAR). In the training phase, OAR performs both online per-frame action recognition and start point detection. At the same time, TPG generates class-wise temporal action proposals serving as noisy supervisions for OAR. TPG is then optimized with the video-level annotations. In this way, the online action detection framework can be trained with video-category labels only without pre-annotated segment-level boundary labels.

Abstract: A method for active learning includes obtaining a set of unlabeled training samples and for each unlabeled training sample, perturbing the unlabeled training sample to generate an augmented training sample. The method includes generating, using a machine learning model, a predicted label for both samples and determining an inconsistency value for the unlabeled training sample that represents variance between the predicted labels for the unlabeled and augmented training samples. The method includes sorting the unlabeled training samples based on the inconsistency values and obtaining, for a threshold number of samples selected from the sorted unlabeled training samples, a ground truth label. The method includes selecting a current set of labeled training samples including each selected unlabeled training samples paired with the corresponding ground truth label. The method includes training, using the current set and a proper subset of unlabeled training samples, the machine learning model.

Abstract: Embodiments described herein provide a two-stage online detection of action start system including a classification module and a localization module. The classification module generates a set of action scores corresponding to a first video frame from the video, based on the first video frame and video frames before the first video frames in the video. Each action score indicating a respective probability that the first video frame contains a respective action class. The localization module is coupled to the classification module for receiving the set of action scores from the classification module and generating an action-agnostic start probability that the first video frame contains an action start.

Abstract: Systems and methods are provided for weakly supervised natural language localization (WSNLL), for example, as implemented in a neural network or model. The WSNLL network is trained with long, untrimmed videos, i.e., videos that have not been temporally segmented or annotated. The WSNLL network or model defines or generates a video-sentence pair, which corresponds to a pairing of an untrimmed video with an input text sentence. According to some embodiments, the WSNLL network or model is implemented with a two-branch architecture, where one branch performs segment sentence alignment and the other one conducts segment selection.

Abstract: Embodiments described herein provide a two-stage online detection of action start system including a classification module and a localization module. The classification module generates a set of action scores corresponding to a first video frame from the video, based on the first video frame and video frames before the first video frames in the video. Each action score indicating a respective probability that the first video frame contains a respective action class. The localization module is coupled to the classification module for receiving the set of action scores from the classification module and generating an action-agnostic start probability that the first video frame contains an action start.

Abstract: Embodiments described herein provide a two-stage online detection of action start system including a classification module and a localization module. The classification module generates a set of action scores corresponding to a first video frame from the video, based on the first video frame and video frames before the first video frames in the video. Each action score indicating a respective probability that the first video frame contains a respective action class. The localization module is coupled to the classification module for receiving the set of action scores from the classification module and generating an action-agnostic start probability that the first video frame contains an action start.

Abstract: Determining object importance in vehicle control systems can include obtaining, for a vehicle in operation, an image of a dynamic scene, identifying an object type associated with one or more objects in the image, determining, based on the object type and a goal associated with the vehicle, an importance metric associated with the one or more objects, and controlling the vehicle based at least in part on the importance metric associated with the one or more objects.