MUMBAI, India, June 30 -- Intellectual Property India has published a patent application (202647074199 A) filed by Qualcomm Incorporated on June 15, 2026, for Temporally Consistent And Semantics Guided Text-Based Video Editing Generative Artificial Intelligence (ai) Model With Improved Initialization.
Inventors include Park, Hyojin; Das, Debasmit; Hayat, Munawar; and Porikli, Fatih Murat.
The application for the patent was published on June 26, 2026, under issue no. 26/2026.
Abstract: A processor-implemented method performed for text-based video editing includes receiving a video input and a text prompt. The video input includes a sequence of video frames. Features of the video input are extracted to generate a latent representation of the video input. Noise is injected to the latent representation of the video input to generate a noise injected latent. The noise is conditioned on the video input. An artificial neural network (ANN) model processes the noise injected latent based on the text prompt to adapt the video input according to the text prompt.
Disclaimer: Curated by HT Syndication.
