Huawei Technologies Co., Limited

Chao Xing

Li Qian

Juwei Lu

Peng Dai

Md Akmal Haidar

Deepak Sridhar

Niamul Quader

Jinghui Xiao

Arnab Kumar Mondal

An abstract generation method and apparatus are provided, and relate to the field of artificial intelligence. The method includes: obtaining a content object; obtaining N thumbnails based on N pictures; generating M candidate abstracts based on text information and the N thumbnails; obtaining preference information of a user; selecting one of the M candidate abstracts as an abstract of the content object based on the preference information; and sending the abstract to a terminal device. In the method, a possibility that the user taps the abstract can be increased, and a content object delivery effect can be improved.

Abstract generation method and apparatus

Computer implemented method and system for automatic speech recognition. A first speech sequence is processed, using a time reduction operation of an encoder NN, into a second speech sequence comprising a second set of speech frame feature vectors that each concatenate information from a respective plurality of speech frame feature vectors included in the first set and includes fewer speech frame feature vectors than the first speech sequence. The second speech sequence is transformed, using a self-attention operation of the encoder NN, into a third speech sequence comprising a third set of speech frame feature vectors. The third speech sequence is processed using a probability operation of the encoder NN, to predict a sequence of first labels corresponding to the third set of speech frame feature vectors, and using a decoder NN to predict a sequence of second labels corresponding to the third set of speech frame feature vectors.

Transformer-based automatic speech recognition system incorporating time-reduction layer

Methods and systems are described for performing video retrieval together with video grounding. A word-based query for a video is and encoded into a query representation using a trained query encoder. One or more similar video representations are identified, from a plurality of video representations that are similar to the query representation. Each similar video representation represents a respective relevant video. A grounding is generated for each relevant video by forward propagating each respective similar video representation together with the query representation through a trained grounding module. The relevant videos or identifiers of the relevant videos are outputted together with the grounding generated for each relevant video.

Systems and methods for video retrieval and grounding

Growing community of inventors

Montréal, Canada

Chao Xing