Abstract: According to one embodiment, a method, computer system, and computer program product for identifying one or more intrinsic physical properties of one or more objects is provided. The present invention may include identifying one or more objects in a video set, extracting observable physical properties of the identified one or more objects from the video set, including one or more trajectories, and inferring, by a property-based graph neural network, intrinsic properties of the one or more objects based on the trajectories.

Abstract: A transfer device and use thereof, and a glass bending forming system are provided. The transfer device includes a suction table. The suction table has a first edge-region and a second edge-region. The first edge-region surrounds the second edge-region. The suction table defines a first suction groove, multiple first suction holes, a first suction channel, and a second suction channel. The first suction groove is defined in the first edge-region. The multiple first suction holes are defined in the second edge-region. The first suction channel is in communication with the first suction groove and is used for providing a first negative pressure. The second suction channel is in communication with the multiple first suction holes and is used for providing a second negative pressure. The first negative pressure and the second negative pressure are used for sucking at least one glass sheet on the transfer device.

Abstract: This application discloses a video clip positioning method performed at a computer device. In this application, the computer device acquires a plurality of video frame features of a target video and a text feature of a target text using a video recognition model to determine a candidate clip that can be matched with the target text. The candidate clip is finely divided based on a degree of matching between a video frame in the candidate clip and the target text to acquire a plurality of sub-clips, and a sub-clip that has the highest degree of matching with the target text is used as a target video clip. According to this application, the video recognition model does not need to learn a boundary feature of the target video clip, and during model training, or precisely label a sample video, thereby shortening a training period of the video recognition model.

Abstract: Mechanisms are provided for performing artificial intelligence-based video question answering. A video parser parses an input video data sequence to generate situation data structure(s), each situation data structure comprising data elements corresponding to entities, and first relationships between entities, identified by the video parser as present in images of the input video data sequence. First machine learning computer model(s) operate on the situation data structure(s) to predict second relationship(s) between the situation data structure(s). Second machine learning computer model(s) execute on a received input question to predict an executable program to execute to answer the received question. The program is executed on the situation data structure(s) and predicted second relationship(s). An answer to the question is output based on results of executing the program.

Abstract: Systems and techniques that facilitate reprogrammable federated learning are provided. In various embodiments, a server device can share a pre-trained and frozen neural network with a set of client devices. In various aspects, the server device can orchestrate reprogrammable federated learning of the pre-trained and frozen neural network among the set of client devices. In various instances, the pre-trained and frozen neural network can be positioned between at least one trainable input layer and at least one trainable output layer, and the reprogrammable federated learning can involve the at least one trainable input layer and the at least one trainable output layer, but not the pre-trained and frozen neural network, being locally adjusted by the set of client devices.

Abstract: A processor may receive a video including a plurality of video frames in sequence and a question regarding the video. For a video frame in the plurality of video frames, a processor may parse the video frame into objects and relationships between the objects, and create a subgraph of nodes representing objects and edges representing the relationships, where parsing and creating are performed for each video frame in the plurality of video frames, where a plurality of subgraphs can be created. A processor may create a hypergraph connecting subgraphs by learning relationships between the nodes of the subgraphs, where a hyper-edge is created to represent a relationship between at least one node of one subgraph and at least one node of another subgraph in the plurality of subgraphs. A processor may generate an answer to the question based on the hypergraph.

Abstract: One or more computer processors improve action recognition by removing inference introduced by visual appearances of objects within a received video segment. The one or more computer processors extract appearance information and structure information from a received video segment. The one or more computer processors calculate a factual inference (TE) for the received video segment utilizing the extracted appearance information and structure information. The one or more computer processors calculate a counterfactual debiasing inference (NDE) for the received video segment. The one or more computer processors calculate a total indirect effect (TIE) by subtracting the calculated counterfactual debiased inference from the calculated factual inference. The one or more computer processors action recognize the received video segment by selecting a classification result associated with a highest calculated TIE.

Abstract: This application discloses a video sequence selection method, applicable to a computer device, the method including: receiving a to-be-matched video and a to-be-matched text, the to-be-matched text having a to-be-matched text feature sequence; invoking a spatiotemporal candidate region generator to extract a spatiotemporal candidate region set from the to-be-matched video, the spatiotemporal candidate region set including N spatiotemporal candidate regions; performing feature extraction on each spatiotemporal candidate region by using a convolutional neural network, to obtain N to-be-matched video feature sequences; invoking an attention-based interactor to obtain a matching score corresponding to each spatiotemporal candidate region, the matching score being used for representing a matching relationship between the spatiotemporal candidate region and the to-be-matched text; and selecting a target spatiotemporal candidate region from the spatiotemporal candidate region set according to the matching score corr

Abstract: Techniques for audio understanding using fixed language models are provided. In one aspect, a system for performing audio understanding tasks includes: a fixed text embedder for, on receipt of a prompt sequence having (e.g., from 0-10) demonstrations of an audio understanding task followed by a new question, converting the prompt sequence into text embeddings; a pretrained audio encoder for converting the prompt sequence into audio embeddings; and a fixed autoregressive language model for answering the new question using the text embeddings and the audio embeddings. A method for performing audio understanding tasks is also provided.

Abstract: A computer-implemented method for fine-grained referring expression comprehension is provided. The computer-implemented method includes receiving, at a processor, a textual expression and an image as inputs and executing, at the processor, fine-grained referring expression comprehension. The executing includes decomposing the textual expression into different textual modules, extracting visual regional proposals from the image, using language-guided graph neural networks to mine fine-grained object relations from the visual regional proposals and aggregating different matching similarities between the different textual modules and the fine-grained object relations.

Abstract: One or more computer processors improve action recognition by removing inference introduced by visual appearances of objects within a received video segment. The one or more computer processors extract appearance information and structure information from a received video segment. The one or more computer processors calculate a factual inference (TE) for the received video segment utilizing the extracted appearance information and structure information. The one or more computer processors calculate a counterfactual debiasing inference (NDE) for the received video segment. The one or more computer processors calculate a total indirect effect (TIE) by subtracting the calculated counterfactual debiased inference from the calculated factual inference. The one or more computer processors action recognize the received video segment by selecting a classification result associated with a highest calculated TIE.

Abstract: A system may include a memory and a processor in communication with the memory. The processor may be configured to perform operations. The operations may include receiving an input, extracting features from the input, and mining object relations using the features. The operations may include determining feature vectors using the object relations and generating, using the feature vectors, an output indicating a target region, wherein the target region corresponds to the input.

Abstract: According to one embodiment, a method, computer system, and computer program product for identifying one or more intrinsic physical properties of one or more objects is provided. The present invention may include identifying one or more objects in a video set, extracting observable physical properties of the identified one or more objects from the video set, including one or more trajectories, and inferring, by a property-based graph neural network, intrinsic properties of the one or more objects based on the trajectories.

Abstract: A processor may receive a video including a plurality of video frames in sequence and a question regarding the video. For a video frame in the plurality of video frames, a processor may parse the video frame into objects and relationships between the objects, and create a subgraph of nodes representing objects and edges representing the relationships, where parsing and creating are performed for each video frame in the plurality of video frames, where a plurality of subgraphs can be created. A processor may create a hypergraph connecting subgraphs by learning relationships between the nodes of the subgraphs, where a hyper-edge is created to represent a relationship between at least one node of one subgraph and at least one node of another subgraph in the plurality of subgraphs. A processor may generate an answer to the question based on the hypergraph.

Abstract: Mechanisms are provided for performing artificial intelligence-based video question answering. A video parser parses an input video data sequence to generate situation data structure(s), each situation data structure comprising data elements corresponding to entities, and first relationships between entities, identified by the video parser as present in images of the input video data sequence. First machine learning computer model(s) operate on the situation data structure(s) to predict second relationship(s) between the situation data structure(s). Second machine learning computer model(s) execute on a received input question to predict an executable program to execute to answer the received question. The program is executed on the situation data structure(s) and predicted second relationship(s). An answer to the question is output based on results of executing the program.

Abstract: This application discloses a video clip positioning method performed at a computer device. In this application, the computer device acquires a plurality of video frame features of a target video and a text feature of a target text using a video recognition model to determine a candidate clip that can be matched with the target text. The candidate clip is finely divided based on a degree of matching between a video frame in the candidate clip and the target text to acquire a plurality of sub-clips, and a sub-clip that has the highest degree of matching with the target text is used as a target video clip. According to this application, the video recognition model does not need to learn a boundary feature of the target video clip, and during model training, or precisely label a sample video, thereby shortening a training period of the video recognition model.

Abstract: This application discloses a video sequence selection method, applicable to a computer device, the method including: receiving a to-be-matched video and a to-be-matched text, the to-be-matched text having a to-be-matched text feature sequence; invoking a spatiotemporal candidate region generator to extract a spatiotemporal candidate region set from the to-be-matched video, the spatiotemporal candidate region set including N spatiotemporal candidate regions; performing feature extraction on each spatiotemporal candidate region by using a convolutional neural network, to obtain N to-be-matched video feature sequences; invoking an attention-based interactor to obtain a matching score corresponding to each spatiotemporal candidate region, the matching score being used for representing a matching relationship between the spatiotemporal candidate region and the to-be-matched text; and selecting a target spatiotemporal candidate region from the spatiotemporal candidate region set according to the matching score corr

Abstract: Processes for forming an actuator having a curved piezoelectric membrane are disclosed. The processes utilize a profile-transferring substrate having a curved surface surrounded by a planar surface to form the curved piezoelectric membrane. The piezoelectric material used for the piezoelectric actuator is deposited on at least the curved surface of the profile-transferring substrate before the profile-transferring substrate is removed from the underside of the curved piezoelectric membrane. The resulting curved piezoelectric membrane includes grain structures that are columnar and aligned, and all or substantially all of the columnar grains are locally perpendicular to the curved surface of the piezoelectric membrane.

Abstract: Processes for forming an actuator having a curved piezoelectric membrane are disclosed. The processes utilize a profile-transferring substrate having a curved surface surrounded by a planar surface to form the curved piezoelectric membrane. The piezoelectric material used for the piezoelectric actuator is deposited on at least the curved surface of the profile-transferring substrate before the profile-transferring substrate is removed from the underside of the curved piezoelectric membrane. The resulting curved piezoelectric membrane includes grain structures that are columnar and aligned, and all or substantially all of the columnar grains are locally perpendicular to the curved surface of the piezoelectric membrane.

Abstract: Processes for forming an actuator having a curved piezoelectric membrane are disclosed. The processes utilize a profile-transferring substrate having a curved surface surrounded by a planar surface to form the curved piezoelectric membrane. The piezoelectric material used for the piezoelectric actuator is deposited on at least the curved surface of the profile-transferring substrate before the profile-transferring substrate is removed from the underside of the curved piezoelectric membrane. The resulting curved piezoelectric membrane includes grain structures that are columnar and aligned, and all or substantially all of the columnar grains are locally perpendicular to the curved surface of the piezoelectric membrane.