Abstract: The disclosed embodiments relate to a video generation method, apparatus, device, and medium. The method comprises: obtaining product information of a target product; determining, based on the product information, character information corresponding to at least two target virtual characters; wherein the character information comprises character characteristics, character lines, and character appearance time; and generating a target video based on the character information of the target virtual characters; wherein the target video is a communication video of the at least two target virtual characters for the target product. The disclosed embodiments can directly generate a communication video of a plurality of virtual characters for the target product, requiring low cost and providing efficient production, thereby effectively showcasing and introducing the relevant product.

Abstract: Methods, systems, and apparatus, including computer programs encoded on computer storage media, for training a generative neural network that has parameters. In one aspect, one of the methods include: obtaining a context input; processing, by the generative neural network, the context input to generate a plurality of training outputs; for each objective in a set of objectives and for each of the plurality of training outputs: determining a respective quality score of the training output relative to each other training input in the plurality of training outputs with respect to the objective; and determining a calibrated reward for the training output with respect to the objective based on the respective quality scores of the training output with respect to the objective; selecting a positive training output and a negative training output; and training the generative neural network on the positive training output and the negative training output.

Abstract: The present disclosure provides a video processing method and related devices. The method includes: acquiring attribute information of a target object and an initial video, where the initial video includes audio data related to the target object; obtaining a video category and a video effect list of the initial video based on a target text corresponding to the audio data and the attribute information; determining a target material corresponding to an effect object based on the video category and an effect material label; and adding the target material to the initial video based on a target timestamp of the text segment in the audio data, to obtain a target video.

Abstract: Methods, systems, and apparatus, including computer programs encoded on computer storage media, for training a diffusion neural network using a region-aware fine-tuning process. After training, the diffusion neural network can be used to generate an image conditioned on a conditioning input.

Abstract: Methods and systems for modifying a digital image are described herein. The method can include performing vividness scoring for a plurality of pixels of the digital image, determining one or more candidate pixels based on the vividness scoring for the plurality of pixels, and agglomerating the one or more candidate pixels into one or more suggested agglomerates. The method can also include determining at least one subject of the digital image, removing at least one agglomerate from the one or more suggested agglomerates based on at least one of the at least one subject of the digital image or one or more characteristics of the at least one agglomerate, generating a modified digital image with the one or more suggested agglomerates modified, and outputting the modified digital image.

Abstract: Aspects of the disclosed technology include computer-implemented systems and methods for machine-learned multimodal models. A machine-learned multimodal model includes one or more embedding layers configured to generate one or more image tokens and one or more text tokens in response to the imagery and the text, a transformer encoder configured to receive the one or more image tokens and the one or more text tokens and generate one or more fused image tokens and one or more fused text tokens, a heatmap predictor configured to obtain the one or more fused image tokens and generate at least one image heatmap, and a sequence predictor configured to obtain the one or more fused image tokens and the one or more fused text tokens and generate a predicted sequence associated with the image.

Abstract: The technology provides for enhanced image cropping via in-context learning. It includes an efficient prompt retrieval mechanism for image cropping to automate the selection of in-context examples. It also includes an iterative refinement strategy to iteratively enhance the predicted crops. The image cropping framework is applicable to a wide range of cropping tasks, including free-form cropping, subject-aware cropping, and aspect ratio-aware cropping. The approach employs a trained large vision-language model associated with in-context learning. For instance, given an input image (whether from free-form, subject-aware or aspect ratio-aware cropping), the top-K semantically similar images from a dataset are retrieved as an in-context learning prompt. Then the in-context learning prompt is fed to a pretrained vision-language model to generate a set of crops. The crop candidates of the set are iteratively refined to yield a final output crop.

Abstract: An embedding cassette marking machine and an operating method are provided. The embedding cassette marking machine includes: a housing; a feeding mechanism; a laser marking mechanism for marking the embedding cassette that slides down to the slideway assembly; and a discharging mechanism, which includes a pushing assembly and a material-carrying rail. The pushing assembly includes a pushing block, and the pushing block is configured to reciprocate toward or away from the material-carrying rail, so as to push the marked embedding cassette to the material-carrying rail.

Abstract: Aspects of the disclosed technology include computer-implemented systems and methods for machine-learned multimodal models for feedback predictions for synthetic content. A machine-learned multimodal model is configured to generate a feature map based at least in part on fusion of image information and text information from a synthetic image and a text prompt. The model is configured to generate a set of text tokens based at least in part on fusion of the image information and the text information. The model is configured to generate at least one misalignment or implausibility heatmap based at least in part on the at least one feature map. The model is configured to generate at least one predicted misalignment sequence based at least in part on the set of text tokens.

Abstract: Techniques for tuning an image editing operator for reducing a distractor in raw image data are presented herein. The image editing operator can access the raw image data and a mask. The mask can indicate a region of interest associated with the raw image data. The image editing operator can process the raw image data and the mask to generate processed image data. Additionally, a trained saliency model can process at least the processed image data within the region of interest to generate a saliency map that provides saliency values. Moreover, a saliency loss function can compare the saliency values provided by the saliency map for the processed image data within the region of interest to one or more target saliency values. Subsequently, the one or more parameter values of the image editing operator can be modified based at least in part on the saliency loss function.

Abstract: Improved methods are provided for generating heatmaps or other summary map data from multiple users' data (e.g., probability distributions) in a manner that preserves the privacy of the users' data while also generating heatmaps that are visually similar to the ‘true’ heatmap. These methods include decomposing the average of the users' data (the ‘true’ heatmap) into multiple different spatial scales, injecting random noise into the data at the multiple different spatial scales, and then reconstructing the privacy-preserving heatmap based on the noisy multi-scale representations. The magnitude of the noise injected at each spatial scale is selected to ensure preservation of privacy while also resulting in heatmaps that are visually similar to the ‘true’ heatmap.

Abstract: Provided are systems and methods for training and using a machine-learned model to predict a visual attention center for an image. As one example, the predicted visual attention center for the image can be used in ordering image regions for encoding, decoding, transmitting, and/or loading in a progressive image loading format.

Abstract: Techniques for tuning an image editing operator for reducing a distractor in raw image data are presented herein. The image editing operator can access the raw image data and a mask. The mask can indicate a region of interest associated with the raw image data. The image editing operator can process the raw image data and the mask to generate processed image data. Additionally, a trained saliency model can process at least the processed image data within the region of interest to generate a saliency map that provides saliency values. Moreover, a saliency loss function can compare the saliency values provided by the saliency map for the processed image data within the region of interest to one or more target saliency values. Subsequently, the one or more parameter values of the image editing operator can be modified based at least in part on the saliency loss function.

Abstract: Methods, systems, and apparatus, including computer programs encoded on computer storage media, for characterizing a gaze position of a user in a query image. One of the methods includes obtaining a query image of a user captured by a camera of a mobile device; obtaining device characteristics data specifying (ii) characteristics of the mobile device, (ii) characteristics of the camera of the mobile device, or (iii) both; and processing a neural network input comprising (i) one or more images derived from the query image and (ii) the device characteristics data using a gaze prediction neural network, wherein the gaze prediction neural network is configured to, at run time and after the gaze prediction neural network has been trained, process the neural network input to generate a neural network output that characterizes a gaze position of the user in the query image.

Abstract: The present invention relates to the technical field of wastewater treatment, and discloses a bioaugmentation treatment process for lithium battery producing wastewater. The method comprises the following steps: 1) introducing wastewater into a hydrolytic acidification tank, and adding Enterobacter sp. NJUST50 and activated sludge to the hydrolytic acidification tank for hydrolytic acidification treatment; 2) introducing the effluent into an anoxic tank, and adding Enterobacter sp. NJUST50 and anaerobic activated sludge for anoxic treatment; 3) introducing the effluent into an aerobic tank, and adding Enterobacter sp. NJUST50 and aerobic activated sludge for aerobic treatment; 4) introducing the effluent into an anoxic filter tank, and adding Enterobacter sp. NJUST50 and anaerobic activated sludge to the filter tank for treatment; and 5) introducing the effluent into a biological aerated filter tank, and adding a sludge mixture of Enterobacter sp.

Abstract: Methods, systems, and apparatus, including computer programs encoded on computer storage media, for characterizing a gaze position of a user in a query image. One of the methods includes obtaining a query image of a user captured by a camera of a mobile device; obtaining device characteristics data specifying (ii) characteristics of the mobile device, (ii) characteristics of the camera of the mobile device, or (iii) both; and processing a neural network input comprising (i) one or more images derived from the query image and (ii) the device characteristics data using a gaze prediction neural network, wherein the gaze prediction neural network is configured to, at run time and after the gaze prediction neural network has been trained, process the neural network input to generate a neural network output that characterizes a gaze position of the user in the query image.

Abstract: Improved methods are provided for generating heatmaps or other summary map data from multiple users' data (e.g., probability distributions) in a manner that preserves the privacy of the users' data while also generating heatmaps that are visually similar to the ‘true’ heatmap. These methods include decomposing the average of the users' data (the ‘true’ heatmap) into multiple different spatial scales, injecting random noise into the data at the multiple different spatial scales, and then reconstructing the privacy-preserving heatmap based on the noisy multi-scale representations. The magnitude of the noise injected at each spatial scale is selected to ensure preservation of privacy while also resulting in heatmaps that are visually similar to the ‘true’ heatmap.

Abstract: Techniques for tuning an image editing operator for reducing a distractor in raw image data are presented herein. The image editing operator can access the raw image data and a mask. The mask can indicate a region of interest associated with the raw image data. The image editing operator can process the raw image data and the mask to generate processed image data. Additionally, a trained saliency model can process at least the processed image data within the region of interest to generate a saliency map that provides saliency values. Moreover, a saliency loss function can compare the saliency values provided by the saliency map for the processed image data within the region of interest to one or more target saliency values. Subsequently, the one or more parameter values of the image editing operator can be modified based at least in part on the saliency loss function.

Abstract: Methods, systems, and apparatus, including computer programs encoded on computer storage media, for characterizing a gaze position of a user in a query image. One of the methods includes obtaining a query image of a user captured by a camera of a mobile device; obtaining device characteristics data specifying (ii) characteristics of the mobile device, (ii) characteristics of the camera of the mobile device, or (iii) both; and processing a neural network input comprising (i) one or more images derived from the query image and (ii) the device characteristics data using a gaze prediction neural network, wherein the gaze prediction neural network is configured to, at run time and after the gaze prediction neural network has been trained, process the neural network input to generate a neural network output that characterizes a gaze position of the user in the query image.

Abstract: The present invention relates to the technical field of wastewater treatment, and discloses a bioaugmentation treatment process for lithium battery producing wastewater. The method comprises the following steps: 1) introducing wastewater into a hydrolytic acidification tank, and adding Enterobacter sp. NJUST50 and activated sludge to the hydrolytic acidification tank for hydrolytic acidification treatment; 2) introducing the effluent into an anoxic tank, and adding Enterobacter sp. NJUST50 and anaerobic activated sludge for anoxic treatment; 3) introducing the effluent into an aerobic tank, and adding Enterobacter sp. NJUST50 and aerobic activated sludge for aerobic treatment; 4) introducing the effluent into an anoxic filter tank, and adding Enterobacter sp. NJUST50 and anaerobic activated sludge to the filter tank for treatment; and 5) introducing the effluent into a biological aerated filter tank, and adding a sludge mixture of Enterobacter sp.