27 citations · 50 across the 10 of their papers we have counts for
3 papers · 1 filter
Compositional Structure Learning for Sequential Video Data
Kyoung-Woon On, Eun-Sol Kim, Yu-Jung Heo +1
Conventional sequential learning methods such as Recurrent Neural Networks (RNNs) focus on interactions between consecutive inputs, i.e. first-order Markovian dependency. However,…
Constructing Hierarchical Q&A Datasets for Video Story Understanding
Yu-Jung Heo, Kyoung-Woon On, Seongho Choi +5
Video understanding is emerging as a new paradigm for studying human-like AI. Question-and-Answering (Q&A) is used as a general benchmark to measure the level of intelligence for v…
Visualizing Semantic Structures of Sequential Data by Learning Temporal Dependencies
Kyoung-Woon On, Eun-Sol Kim, Yu-Jung Heo +1
While conventional methods for sequential learning focus on interaction between consecutive inputs, we suggest a new method which captures composite semantic flows with variable-le…