Abstract: A progressive localization method for text-to-video clip localization. The method comprises: first, respectively extracting features of two modes, namely a video mode and a text mode by using different feature extraction methods; then progressively selecting different step sizes, and learning the correlation between the video and the text in multiple stages; and finally, training a model in an end-to-end manner based on the correlation loss of each stage. Moreover, the fine time granularity stage is fused with information of the coarse time granularity stage by means of a condition feature update module and up-sampling connection, such that different stages are mutually promoted. Different stages can pay attention to clips with different time granularities, and the model can cope with the situation that the length of a target clip is obviously changed based on the interrelation between the stages.

Abstract: A progressive localization method for text-to-video clip localization. The method comprises: first, respectively extracting features of two modes, namely a video mode and a text mode by using different feature extraction methods; then progressively selecting different step sizes, and learning the correlation between the video and the text in multiple stages; and finally, training a model in an end-to-end manner based on the correlation loss of each stage. Moreover, the fine time granularity stage is fused with information of the coarse time granularity stage by means of a condition feature update module and up-sampling connection, such that different stages are mutually promoted. Different stages can pay attention to clips with different time granularities, and the model can cope with the situation that the length of a target clip is obviously changed based on the interrelation between the stages.

Abstract: A method for voice recognition includes: performing by an electronic device, voice recognition on voice information; and updating by the electronic device, a waiting duration for EPD from a first preset duration to a second preset duration in response to recognizing a preset keyword from the voice information, where the first preset duration is less than the second preset duration.

Abstract: The present application discloses a voice data processing method, an apparatus, a device and a storage media. The specific implementation solution is: starting a microphone management thread to collect audio data acquired by a microphone in a process of a voice interactive application, and when the voice interactive application is in a non-wake-up state, starting a wake-up thread to perform wake-up processing on the voice interactive application according to the audio data, there is no need to request the microphone separately by a recognition engine which performs voice recognition on the audio data collected by the microphone management thread, thereby realizing the wake-up engine and the recognition engine in the same process. The wake-up engine and the recognition engine avoid a problem of losing part of data due to waiting for preparation of the microphone, and improve efficiency and accuracy of the voice interactive application.