Blog(26)

• Unified Arbitrary-Time Video Frame Interpolation and Prediction

  Video frame interpolation and prediction are long-standing tasks in computer vision.

• On-device hand model for robust gesture detection

  Human gesture interaction enables more natural and intuitive forms of communication.

• Find Details in Long Videos: Tower-of-Thoughts and Self-Retrieval Augmented Generation for Video Understanding

  The Large Vision-Language Model (LVLM) has achieved impressive performance in the field of visual-language understanding.

View More

Research Areas(2)

• Robotics

  Overview For many years in the past, the concept of ‘Robot’ had remained the same: to help people with routine labor mainly in industrial applications. Now, with the rapid development of AI, robotics, and cloud computing, the concept of robot has been revolutionized and redefined, allowing for the emergence of a new intelligent robot market not just for the industrial world but for various professional and personal use cases in people’s normal lives. To address ...

• Next Generation Display & Media

  Overview The media device and service market is expected to change dramatically because of recent environmental and technological factors, such as the consumers’ need for an improved sense of reality, an increase in one-person households, and shifting content consumption patterns from broadcast to streaming-based services. For consumers’ needs for highly realistic media, not only technologies for improving resolution like 8K TVs, but also new and highly immersive...

Publications(181)

• CLIP-DPO: Vision-Language Models as a Source of Preference for Fixing Hallucinations in LVLMs

  AuthorYassine Ouali, Adrian Bulat, Brais Martinez, Georgios Tzimiropoulos

  PublishedEuropean Conference on Computer Vision (ECCV)

  Date2024-09-30

• Towards Neural Architecture Search through Hierarchical Generative Modeling

  AuthorAbhinav Mehrotra, Hongkai Wen

  PublishedInternational Conference on Machine Learning (ICML)

  Date2024-07-23

• UPR-Net: A Unified Pyramid Recurrent Network for Video Frame

  AuthorXin Jin, Longhai Wu, Jie Chen, Youxin Chen, Jayoon Koo, Cheul-Hee Hahm

  PublishedInternational Journal of Computer Vision (IJCV)

  Date2024-07-17

View More

News(69)

• Samsung R&D Institute Bangladesh Celebrates Bengali New Year 1432

  Samsung R&D Institute Bangladesh (SRBD) celebrated the Bengali New Year on April 15, 2025, marking the first day of the Bengali calendar. Observed annually on April 14 as a national holiday, the occasion was commemorated with vibrant festivities at SRBD.

• Samsung R&D Institute Bangladesh Launches SmartThings Experience Zone

  Samsung R&D Institute Bangladesh (SRBD) celebrated the Bengali New Year on April 15, 2025, marking the first day of the Bengali calendar. Observed annually on April 14 as a national holiday, the occasion was commemorated with vibrant festivities at SRBD.

• Samsung's New Breakthrough in Speech and Image Signal Processing

  The 2024 IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP) has accepted five research papers from Samsung R&D Institute China-Beijing (SRC-B). ICASSP, organized by the Institute of Electrical and Electronics Engineers (IEEE), represents a premier international conference in signal processing with substantial international influence.

View More

Others(5)

• Who We Are

  SAMSUNG Research Samsung Research is the advanced research and development (R&D) hub of Samsung’s Consumer Electronics (CE) Division and IT & Mobile Communications (IM) Division. Samsung Research leads the development of the future technologies with more than 10,000 researchers and developers working in overseas R&D centers. Under the vision of “Shape the Future with Innovation and Intelligence”, it is actively conducting research and development (R&D) to identify ...

• Samsung AI Forum 2019

  Seoul, November 4 ~ 5 Samsung AI Forum is an academic event for the foremost minds of today’s world to come together and share their views on the current and future development of Artificial Intelligence technology. On-line pre-registration will open on September 24, 2019. Samsung AI Forum 2019Play Participants Anyone with an interest in AI technology including undergraduate and graduate students, university faculty members, researchers, and members of the general ...

• Samsung AI Forum 2019

  제3회 삼성 AI 포럼 2019. 11. 4 - 11. 5 삼성 AI포럼은 Global 최고의 연구자분들과 함께 최신 AI 연구 동향을 공유하고 응용 및 혁신 방향을 모색하는 기술 교류의 장입니다. 2019년 9월 24일부터 온라인 사전등록이 시작됩니다. Samsung AI Forum 2019Play 참가 대상 국내외 대학(원)생, 교수, 연구원, 일반인 등 AI 기술 트렌드에 관심있는 누구나 참가 신청2019. 9. 24(화) ~ 선착순 마감 Day 1 11. 4(월) 삼성전자 서초사옥 삼성종합기술원 주관 >> Day 2 11. 5(화) 삼성전자 서울R&D캠퍼스 삼성리서치 주관 Registration Samsung AI Forum - Day 2 2일차 참가 신청 기간2019. 9. 24 ~ 참가신청이 마감되었으며, 당일 현장등록이 가능합니다. Schedule Day 211.5(화) 삼성전자 서울R&D캠퍼스 AB/D타워...

View More