Blog(2)

• Learning Representations from Explainable and Connectionist Approaches for Visual Question Answering

  VQA [1,2] is the field of research that aims to develop methods for answering natural language questions based on the information provided in corresponding images.

• Vision-Language Model Guided Semi-Supervised Learning for No-Reference Video Quality Assessment

  The widespread adoption of mobile devices has led to a rapid growth of video content that is captured, transmitted and shared on various social media platforms.

Research Areas(0)

Publications(3)

• LEARNING TO JOINTLY SHARE AND PRUNE WEIGHTS FOR GROUNDING BASED VISION AND LANGUAGE MODELS

  AuthorShangqian Gao,Burak Uzkent,Yilin Shen,Hongxia Jin

  PublishedInternational Conference on Learning Representation (ICLR)

  Date2023-05-01

• Progressive Attention Memory Network for Movie Story Question Answering

  AuthorJunyeong Kim, Minuk Ma, Kyungsu Kim, Sungjin Kim, Chang D. Yoo

  PublishedComputer Vision and Pattern Recognition (CVPR)

  Date2019-06-21

• Gaining Extra Supervision via Multi-task learning

  AuthorJunyeong Kim, Minuk Ma, Kyungsu Kim, Sungjin Kim, Chang D. Yoo

  PublishedInternational Joint Conference on Neural Networks (IJCNN)

  Date2019-02-08

News(4)

• Samsung R&D Institute Ukraine's Visual Intelligence Team at CVPR 2026

  The competition was a Visual Question Answering (VQA) challenge focused on autonomous driving safety, using dashcam videos from the 2COOOL dataset. Participants had to develop models that accurately answer structured, numeric questions about incident-related details (e.g., weather, road conditions, primary/secondary entities, prevention measures, and points of impact).

• Samsung R&D Institute Ukraine's Visual Intelligence Team at CVPR 2026

  Samsung demonstrated technical superiority in video VQA by securing 4th place in the 'VQA - AUTOPILOT CVPR' competition at the prestigious CVPR 2026

• [Blog] SmoGVLM: A Small, Graph-Enhanced Vision-Language Model

  Large vision-language models (VLMs) have achieved impressive performance across a wide range of multimodal tasks, from visual question answering (VQA) to reasoning over images and text [1, 2]. However, these models often suffer from hallucinations and poor grounding when faced with knowledge-intensive queries.

View More

Others(0)