logo

For the Inventor, By the Inventor

Amsterdam, Netherlands

Amirhossein Habibian

USPTO Granted Patents = 19 

Average Co-Inventor Count = 2.9

ph-index = 3

Forward Citations = 34(Granted Patents)


Company Filing History:

goldMedal19 out of 41,672 
 
Qualcomm Incorporated
 patents

Years Active: 2020-2025

Loading Chart...
19 patents (USPTO):Explore Patents
1. 12499676 - Recurrent neural networks for high resolution image and video processing (2025-12-16),
2. 12469281 - Processing video content using gated transformer neural networks (2025-11-11),
3. 12412373 - Saliency-based input resampling for efficient object detection (2025-09-09),
4. 12406481 - Video processing using delta distillation (2025-09-02),
5. 12266179 - Efficient self-attention for video processing (2025-04-01),
6. 12206869 - Skip convolutions for efficient video processing (2025-01-21),
7. 12177462 - Video compression using deep generative models (2024-12-24),
8. 12118810 - Spatiotemporal recycling network (2024-10-15),
9. 11991368 - Video compression using deep generative models (2024-05-21),
10. 11842540 - Adaptive use of video models for holistic video understanding (2023-12-12),
11. 11729406 - Video compression using deep generative models (2023-08-15),
12. 11600007 - Predicting subject body poses and subject movement intent using probabilistic generative models (2023-03-07),
13. 11388416 - Video compression using deep generative models (2022-07-12),
14. 11308350 - Deep cross-correlation learning for object tracking (2022-04-19),
15. 10964033 - Decoupled motion models for object tracking (2021-03-30),

Title: Amirhossein Habibian: Innovator in Video Processing Technologies

Introduction

Amirhossein Habibian is a prominent inventor based in Amsterdam, Netherlands. He has made significant contributions to the field of video processing, holding a total of 19 patents. His work focuses on utilizing advanced machine learning techniques to enhance video content processing.

Latest Patents

Among his latest patents, one notable invention is titled "Processing video content using gated transformer neural networks." This patent outlines techniques and apparatus for processing a video stream using a machine learning model. The method involves generating groups of tokens from video frames and identifying features to be reused or computed, ultimately creating a representation of the second frame.

Another significant patent is "Saliency-based input resampling for efficient object detection." This invention describes a processor-implemented method of video processing that utilizes an artificial neural network to generate a saliency map. The method samples different portions of a video frame at varying resolutions, allowing for efficient inference determination associated with the video.

Career Highlights

Amirhossein Habibian is currently employed at Qualcomm Incorporated, a leading technology company known for its innovations in telecommunications and semiconductor technology. His work at Qualcomm has allowed him to push the boundaries of video processing technologies.

Collaborations

Throughout his career, Amirhossein has collaborated with notable colleagues, including Taco Sebastiaan Cohen and Cornelis Gerardus Maria Snoek. These collaborations have contributed to the advancement of his research and the successful development of his patents.

Conclusion

Amirhossein Habibian is a distinguished inventor whose work in video processing has led to numerous patents and advancements in the field. His innovative approaches continue to shape the future of video technology.

This text is generated by artificial intelligence and may not be accurate.
Please report any incorrect information to support@idiyas.com
Loading…