Abstract: A method of personalized image retrieval includes obtaining a natural language query including a name; replacing the name in the natural language query with a generic term to provide an anonymized query and named entity information; obtaining a plurality of initial ranking scores and a plurality of attention weights corresponding to a plurality of images using a trained scoring model that inputs the anonymized query and the plurality of images; obtaining a plurality of delta scores corresponding to the plurality of images using a re-scoring model that inputs the plurality of attention weights and the named entity information; and obtaining a plurality of final ranking scores by modifying the plurality of initial ranking scores based on the plurality of delta scores. The trained scoring model performs semantic based searching and the re-scoring model determines a probability that faces detected in the plurality of images correspond to the name.

Abstract: A method of personalized image retrieval includes obtaining a natural language query including a name; replacing the name in the natural language query with a generic term to provide an anonymized query and named entity information; obtaining a plurality of initial ranking scores and a plurality of attention weights corresponding to a plurality of images using a trained scoring model that inputs the anonymized query and the plurality of images; obtaining a plurality of delta scores corresponding to the plurality of images using a re-scoring model that inputs the plurality of attention weights and the named entity information; and obtaining a plurality of final ranking scores by modifying the plurality of initial ranking scores based on the plurality of delta scores. The trained scoring model performs semantic based searching and the re-scoring model determines a probability that faces detected in the plurality of images correspond to the name.

Abstract: A method for multimodal content retrieval, may include: receiving a search query corresponding to a request for content; aggregating word features extracted from the search query based on a first set of learned weights; aggregating region features extracted from each of a plurality of images, based on a second set of learned weights, independently of the word features; computing a similarity score between the aggregated words features and the aggregated region features for each of the plurality of images; selecting candidate images from the plurality of images based on the similarity scores between each of the plurality of images and the search query; and selecting at least one final image from the candidate images as a response to the search query, based on attended similarity scores of the candidate images with respect to the search query.

Abstract: The present disclosure relates to systems and methods for analyzing citationally related content and identifying, based on the analysis, a risk of impliedly overruled content. Embodiments provide for receiving case law data from a document source, for extracting a case triple that includes a first case overruling or abrogating a second case, and a third case citationally related to the second case. Features may be generated from case triple, such as natural processing language features comparing the language in the various cases of the triple, and feeding the generated features to a main classifier. In embodiments, the main classifier classifies the case triple into a class indicating the risk probability that the second case is impliedly overruled by the first case.

Abstract: An apparatus for providing similar contents, using a neural network, includes a memory storing instructions, and a processor configured to execute the instructions to obtain a plurality of similarity values between a user query and a plurality of images, using a similarity neural network, obtain a rank of each the obtained plurality of similarity values, and provide, as a most similar image to the user query, at least one among the plurality of images that has a respective one among the plurality of similarity values that corresponds to a highest rank among the obtained rank of each of the plurality of similarity values. The similarity neural network is trained with a divergence neural network for outputting a divergence between a first distribution of first similarity values for positive pairs, among the plurality of similarity values, and a second distribution of second similarity values for negative pairs, among the plurality of similarity values.

Abstract: An utterance in any of various languages is processed to derive a predicted label using a generated grammar. The grammar is suitable for deriving meaning of utterances from several languages (polyglot). The utterance is processed by an encoder using word embeddings. The encoder and a decoder process the utterance using the polyglot grammar to obtain a machine-readable result. The machine-readable result is well-formed based on accounting for re-entrances of intermediate variable references. A machine then takes action on the machine-readable result. Ambiguity is reduced by the decoder by the well-formed machine-readable result. Sparseness of the generated polyglot grammar is reduced by using a two-pass approach including placeholders which are ultimately replaced by edge labels.

Abstract: A method of personalized image retrieval includes obtaining a natural language query including a name; replacing the name in the natural language query with a generic term to provide an anonymized query and named entity information; obtaining a plurality of initial ranking scores and a plurality of attention weights corresponding to a plurality of images using a trained scoring model that inputs the anonymized query and the plurality of images; obtaining a plurality of delta scores corresponding to the plurality of images using a re-scoring model that inputs the plurality of attention weights and the named entity information; and obtaining a plurality of final ranking scores by modifying the plurality of initial ranking scores based on the plurality of delta scores. The trained scoring model performs semantic based searching and the re-scoring model determines a probability that faces detected in the plurality of images correspond to the name.

Abstract: An apparatus for video searching, includes a memory storing instructions, and a processor configured to execute the instructions to split a video into scenes, obtain, from the scenes into which the video is split, one or more textual descriptors describing each of the scenes, encode the obtained one or more textual descriptors describing each of the scenes into a video scene vector of each of the scenes, encode a user query into a query vector having a same semantic representation as that of the video scene vector of each of the scenes into which the one or more textual descriptors describing each of the scenes are encoded, and identify whether the video scene vector of at least one among the scenes corresponds to the query vector into which the user query is encoded.

Abstract: An apparatus for vision and language-assisted smartphone task automation, includes a processor configured to execute instructions to identify whether an utterance of a user refers to one among at least one existing automation script, and based on the utterance being identified to not refer to the one among the at least one existing automation script, capture one or more screenshots and one or more coordinates of a display, the one or more screenshots and the one or more coordinates corresponding to one or more interactions of the user with the display while the user is demonstrating a new automation script, perform object detection and optical character recognition on the captured one or more screenshots and the captured one or more coordinates to obtain user interface (UI) elements corresponding to the one or more interactions, and obtain the new automation script, based on the obtained UI elements.

Abstract: An utterance in any of various languages is processed to derive a predicted label using a generated grammar. The grammar is suitable for deriving meaning of utterances from several languages (polyglot). The utterance is processed by an encoder using word embeddings. The encoder and a decoder process the utterance using the polyglot grammar to obtain a machine-readable result. The machine-readable result is well-formed based on accounting for re-entrances of intermediate variable references. A machine then takes action on the machine-readable result. Ambiguity is reduced by the decoder by the well-formed machine-readable result. Sparseness of the generated polyglot grammar is reduced by using a two-pass approach including placeholders which are ultimately replaced by edge labels.

Abstract: An apparatus for video searching, includes a memory storing instructions, and a processor configured to execute the instructions to split a video into scenes, obtain, from the scenes into which the video is split, one or more textual descriptors describing each of the scenes, encode the obtained one or more textual descriptors describing each of the scenes into a video scene vector of each of the scenes, encode a user query into a query vector having a same semantic representation as that of the video scene vector of each of the scenes into which the one or more textual descriptors describing each of the scenes are encoded, and identify whether the video scene vector of at least one among the scenes corresponds to the query vector into which the user query is encoded.

Abstract: An apparatus for providing similar contents, using a neural network, includes a memory storing instructions, and a processor configured to execute the instructions to obtain a plurality of similarity values between a user query and a plurality of images, using a similarity neural network, obtain a rank of each the obtained plurality of similarity values, and provide, as a most similar image to the user query, at least one among the plurality of images that has a respective one among the plurality of similarity values that corresponds to a highest rank among the obtained rank of each of the plurality of similarity values. The similarity neural network is trained with a divergence neural network for outputting a divergence between a first distribution of first similarity values for positive pairs, among the plurality of similarity values, and a second distribution of second similarity values for negative pairs, among the plurality of similarity values.

Abstract: An apparatus for vision and language-assisted smartphone task automation, includes a processor configured to execute instructions to identify whether an utterance of a user refers to one among at least one existing automation script, and based on the utterance being identified to not refer to the one among the at least one existing automation script, capture one or more screenshots and one or more coordinates of a display, the one or more screenshots and the one or more coordinates corresponding to one or more interactions of the user with the display while the user is demonstrating a new automation script, perform object detection and optical character recognition on the captured one or more screenshots and the captured one or more coordinates to obtain user interface (UI) elements corresponding to the one or more interactions, and obtain the new automation script, based on the obtained UI elements.

Abstract: The present disclosure relates to systems and methods for analyzing citationally related content and identifying, based on the analysis, a risk of impliedly overruled content. Embodiments provide for receiving case law data from a document source, for extracting a case triple that includes a first case overruling or abrogating a second case, and a third case citationally related to the second case. Features may be generated from case triple, such as natural processing language features comparing the language in the various cases of the triple, and feeding the generated features to a main classifier. In embodiments, the main classifier classifies the case triple into a class indicating the risk probability that the second case is impliedly overruled by the first case.