Baidu USA LLC

Beijing Baidu Netcom Science Technology Co., Ltd

Baidu.com Times Technology (beijing) Co. Ltd.

Xing Li

Hao Tian

Le Kang

Xin Zhou

Zhiyu Cheng

Daming Lu

Xi Chen

Lei Wang

Haifeng Wang

Hua Wu

Yueqiang Cheng

Tao Wei

Manjiang Zhang

Zhen Chen

Zhongjun He

Hao Xiong

Davy Huang

Wei Ping

Chuanqiang Zhang

Jeff Chienyu Wang

Zhenyu Zhong

Haofeng Kou

Hairong Liu

Mingbo Ma

Liang Huang

Renjie Zheng

Yichen Hu

Ruichang Cheng

Kaibo Liu

Baigong Zheng

Huimeng Zheng

Bo He

Jingyu Xin

Dapeng Li

Jingya Xun

A system obtains a performance profile corresponding to times taken to perform an inferencing by a machine learning (ML) model using a different number of processing resources from a plurality of processing resources. The system determines one or more groupings of processing resources from the plurality of processing resources, each grouping includes one or more partitions. The system calculates performance speeds corresponding to each grouping based on the performance profile. The system determines a grouping having a best performance speed from the calculated performance speeds. The system partitions the processing resources based on the determined grouping to perform the inferencing.

System on chip parallel computing of ML services and applications for partitioning resources based on the inference times

Presented herein are systems, methods, and datasets for automatically and precisely generating highlight or summary videos of content. In one or more embodiments, the inputs comprise a text (e.g., an article) of the key event(s) (e.g., a goal, a player action, etc.) in an activity (e.g., a game, a concert, etc.) and a video or videos of the activity. In one or more embodiments, the output is a short video of an event or events in the text, in which the video may include commentary about the highlighted events and/or other audio (e.g., music), which may also be automatically synthesized.

Generating highlight video from video and text inputs

With rapidly evolving technologies and emerging tools, sports-related videos generated online are rapidly increasing. To automate the sports video editing/highlight generation process, a key task is to precisely recognize and locate events-of-interest in videos. Embodiments herein comprise a two-stage paradigm to detect categories of events and when these events happen in videos. In one or more embodiments, multiple action recognition models extract high-level semantic features, and a transformer-based temporal detection module locates target events. These novel approaches achieved state-of-the-art performance in both action spotting and replay grounding. While presented in the context of sports, it shall be noted that the systems and methods herein may be used for videos comprising other content and events.

Transformer-based temporal detection in video

The present disclosure provides examples of a method and apparatus for processing a video, a device and a storage medium. The method may include: acquiring a target video and a target comment of the target video; recognizing a picture in the target video to obtain text information of the picture; determining a target comment matching a content of the text information; and inserting, in response to displaying the picture in the target video, the target comment matching the content in a form of a bullet screen.

Method for processing video, device and storage medium

Presented herein are systems, methods, and datasets for automatically and precisely generating highlight or summary videos of content. For example, in one or more embodiments, videos of sporting events may be digested or condensed into highlights, which will dramatically benefit sports media, broadcasters, video creators or commentators, or other short video creators, in terms of cost reduction, fast, and mass production, and saving tedious engineering hours. Embodiment of the framework may also be used or adapted for use to better promote sports teams, players, and/or games, and produce stories to glorify the spirit of sports or its players. While presented in the context of sports, it shall be noted that the methodologies may be used for videos comprising other content and events.

Automatically and precisely generating highlight videos with artificial intelligence

According to various embodiments, an end-to-end TTS framework can integrate a watermarking process into the training of the TTS framework, which enables watermarks to be imperceptible within a synthesized/cloned audio segment generated by the TTS framework. The watermarks added in such a matter are statistically undetectable to prevent authorized removal. According to an exemplary method of training the TTS framework, a TTS neural network model and a watermarking neural network mode in the TTS framework are trained in an end to end manner, with the watermarking being part of the optimization process of the TTS framework. During the training, neuron values of the TTS neural network model are adjusted based on training data to prepare one or more spaces for adding a watermark in a synthesized audio segment to be generated by the TTS framework.

Inaudible watermark enabled text-to-speech framework

Presented herein are embodiments of a prefix-to-prefix framework for simultaneous translation that implicitly learns to anticipates in a single translation. Within these frameworks are effective 'wait-k' policy model embodiments that may be trained to generate a target sentence concurrently with a source sentence but lag behind by a predefined number of words. Embodiments of the prefix-to-prefix framework achieve low latency and better quality when compared to full-sentence translation in four directions: Chinese&#x2194;English and German&#x2194;English. Also presented herein is a novel latency metric that addresses deficiencies of previous latency metrics.

Systems and methods for simultaneous translation with integrated anticipation and controllable latency (STACL)

Growing community of inventors

Sunnyvale, CA, United States of America

Xing Li