Abstract: A system and method for end-to-end semi-supervised object detection is provided. The system retrieves labeled and unlabeled images from an image dataset and generates an input batch by application of image transformation(s) on the images. The system further generates a first result for each image of the input batch by application of a teacher neural network on the input batch. For an object in an unlabeled image of the batch, the first result includes candidate bounding boxes and scores for the boxes. The system determines a threshold score based on the scores and selects a foreground bounding box from the candidates. The system generates a second result by application of a student neural network on the unlabeled image and computes a training loss over the input batch based on the foreground bounding box and the second result. The system trains the student neural network based on the training loss.

Abstract: A system and method of landmark detection using emotion recognition in multimedia videos using multi-modal fusion based deep neural network is provided. The system includes circuitry and a memory configured to store a multimodal fusion network which includes one or more feature extractors, a network of transformer encoders, a fusion attention network, and an output network coupled to the fusion attention network. The system inputs a multimodal input to the one or more feature extractors. The multimodal input is associated with an utterance depicted in one or more videos. The system generates input embeddings as an output of the one or more feature extractors for the input and further generates a set of emotion-relevant features based on the input embeddings. The system further generates a fused-feature representation of the set of emotion-relevant features and predicts an emotion label for the utterance based on fused-feature representation.

Abstract: A system and method of landmark detection using deep neural network with multi-frequency self-attention is provided. The system includes an encoder network that receives an image of an object of interest as an input and generates multi-frequency feature maps as output. The system further includes an attention layer that receives the generated multi-frequency feature maps and refines the generated multi-frequency feature maps based on correlations or associations between the received multi-frequency feature maps. The system further includes a decoder network that receives the refined multi-frequency feature maps as a second input from the attention layer and generates a landmark detection result based on the second input. The landmark detection result includes a heatmap image of the object of interest and the heatmap image indicates locations of landmark points on the object of interest in the image.

Abstract: [Problem] To reduce psychological anxiety of the user regarding acquisition of information in utilizing agent functions. [Solution] Provided is an information processing device, including a control unit that controls an information acquisition function to acquire information regarding a state of a user, in which the control unit controls a transition to an information protection mode that restricts at least part of the information acquisition function on the basis of a start of a protection target act by the user having been estimated. In addition, there is provided an information processing method, including controlling an information acquisition function by a processor to acquire information regarding a state of a user, in which the controlling further includes controlling a transition to an information protection mode that restricts at least part of the information acquisition function on the basis of a start of a protection target act by the user having been estimated. [Selected Drawing] FIG.

Abstract: The present technique relates particularly to an information processing device, an information processing method, and a program which can improve sleep efficiency. The information processing device according to one aspect of the present technique has: an acquisition unit which acquires information which indicates an action schedule of a user; and a first determination unit which determines whether the user needs to wake up or sleep, and determines the degree of necessity of waking up when determining that the user needs to wake up and the degree of necessity of sleeping when determining the user needs to sleep, according to the action schedule of the user. The present technique is applicable to a mobile device such as a mobile telephone, a PDA and a digital camera.

Abstract: An information processing device includes an image acquirer that acquires a shot image of a user, a registered user information holder that holds face identification data of a registered user, and a face authentication section that detects a face image of a registered user existing in the shot image by using face identification data held in the registered user information holder. The information processing device further includes an information processing section that executes information processing based on a detection result by the face authentication section, and a face identification data registration section that updates the face identification data based on a face image extracted from a shot image of a user at predetermined timings. The face identification data registration section determines whether or not to update the face identification data with a condition corresponding to a situation in which the timing is generated.

Abstract: An information processing apparatus includes an image generation unit configured to generate a viewpoint image in a case where a watch point set in a three-dimensional virtual space is viewed from a predetermined virtual viewpoint, a detection unit configured to detect a movement of an operator, and a viewpoint displacement unit configured to displace the virtual viewpoint with the set watch point as a reference on the basis of the detected movement of the operator.

Abstract: An image processing device includes: a determination unit determining whether each character included as a subject in a captured image is an unnoted non-main character; and a controller controlling an image-related process which is a process related to an image on the basis of a status of the character determined as a non-main character.

Abstract: An information processing device includes an image acquirer that acquires a shot image of a user, a registered user information holder that holds face identification data of a registered user, and a face authentication section that detects a face image of a registered user existing in the shot image by using face identification data held in the registered user information holder. The information processing device further includes an information processing section that executes information processing based on a detection result by the face authentication section, and a face identification data registration section that updates the face identification data based on a face image extracted from a shot image of a user at predetermined timings. The face identification data registration section determines whether or not to update the face identification data with a condition corresponding to a situation in which the timing is generated.

Abstract: A correction unit corrects parameters of an ensemble learner having a plurality of weak learners that receive characteristic amounts extracted from an input image and output weak hypotheses indicating whether or not a predetermined target is reflected in the input image using correction information. A discrimination processing unit integrates the weak hypotheses output from the weak learners with respect to the characteristic amounts using the ensemble learner of which the parameters are corrected and discriminates whether or not the target is reflected in the input image based on an integrated value of the weak hypotheses. The correction information is calculated based on a light source illuminating the target in a correction information calculation unit 54. The present technology may be applied, for example, to a case of discriminating whether or not the target is reflected in the input image, and so forth.

Abstract: An image processing device includes: a determination unit determining whether each character included as a subject in a captured image is an unnoted non-main character; and a controller controlling an image-related process which is a process related to an image on the basis of a status of the character determined as a non-main character.

Abstract: An image processing device includes: a determination unit determining whether each character included as a subject in a captured image is an unnoted non-main character; and a controller controlling an image-related process which is a process related to an image on the basis of a status of the character determined as a non-main character.

Abstract: The present technique relates particularly to an information processing device, an information processing method, and a program which can improve sleep efficiency. The information processing device according to one aspect of the present technique has: an acquisition unit which acquires information which indicates an action schedule of a user; and a first determination unit which determines whether the user needs to wake up or sleep, and determines the degree of necessity of waking up when determining that the user needs to wake up and the degree of necessity of sleeping when determining the user needs to sleep, according to the action schedule of the user. The present technique is applicable to a mobile device such as a mobile telephone, a PDA and a digital camera.

Abstract: An image processing apparatus includes a face detector for detecting a face region from an image including a face of a user, a part detector for detecting a positional layout of a part of the face included in the face region detected by the face detector, a determiner for determining an attribute of the face on the basis of the positional layout of the part detected by the part detector and calculating a score indicating attribute determination results, a model selector for selecting, on the basis of the score calculated by the determiner, a model that is to be displayed in place of the face of the user in the image, and an image generator for generating an image of a face of the model selected by the model selector and synthesizing the image of the face of the model with the face of the user within the face region.

Abstract: An image processing apparatus includes: a first image storing unit that stores a first history image including a first picked-up image forming a picked-up moving image; an image transforming unit that transforms, on the basis of transformation information concerning the first picked-up image and a second picked-up image forming the picked-up moving image located after the first picked-up image on a time axis of the picked-up moving image, the second picked-up image; and an image combining unit that causes a second image storing unit different from the first image storing unit to store the transformed second picked-up image, overwrites the first history image stored in the first image storing unit on the second picked-up image stored in the second image storing unit, and combines the first history image and the second picked-up image.

Abstract: An information processing apparatus includes an image generation unit configured to generate a viewpoint image in a case where a watch point set in a three-dimensional virtual space is viewed from a predetermined virtual viewpoint, a detection unit configured to detect a movement of an operator, and a viewpoint displacement unit configured to displace the virtual viewpoint with the set watch point as a reference on the basis of the detected movement of the operator.

Abstract: A correction unit corrects parameters of an ensemble learner having a plurality of weak learners that receive characteristic amounts extracted from an input image and output weak hypotheses indicating whether or not a predetermined target is reflected in the input image using correction information. A discrimination processing unit integrates the weak hypotheses output from the weak learners with respect to the characteristic amounts using the ensemble learner of which the parameters are corrected and discriminates whether or not the target is reflected in the input image based on an integrated value of the weak hypotheses. The correction information is calculated based on a light source illuminating the target in a correction information calculation unit 54. The present technology may be applied, for example, to a case of discriminating whether or not the target is reflected in the input image, and so forth.

Abstract: An image processing apparatus includes a face detector for detecting a face region from an image including a face of a user, a part detector for detecting a positional layout of a part of the face included in the face region detected by the face detector, a determiner for determining an attribute of the face on the basis of the positional layout of the part detected by the part detector and calculating a score indicating attribute determination results, a model selector for selecting, on the basis of the score calculated by the determiner, a model that is to be displayed in place of the face of the user in the image, and an image generator for generating an image of a face of the model selected by the model selector and synthesizing the image of the face of the model with the face of the user within the face region.

Abstract: An image processing device includes: a determination unit determining whether each character included as a subject in a captured image is an unnoted non-main character; and a controller controlling an image-related process which is a process related to an image on the basis of a status of the character determined as a non-main character.

Abstract: An image processing apparatus includes: a first image storing unit that stores a first history image including a first picked-up image forming a picked-up moving image; an image transforming unit that transforms, on the basis of transformation information concerning the first picked-up image and a second picked-up image forming the picked-up moving image located after the first picked-up image on a time axis of the picked-up moving image, the second picked-up image; and an image combining unit that causes a second image storing unit different from the first image storing unit to store the transformed second picked-up image, overwrites the first history image stored in the first image storing unit on the second picked-up image stored in the second image storing unit, and combines the first history image and the second picked-up image.