![Loading...](https://link.springer.com/static/c4a417b97a76cc2980e3c25e2271af3129e08bbe/images/pdf-preview/spacer.gif)
-
Article
State-aware video procedural captioning
Video procedural captioning (VPC), which generates procedural text from instructional videos, is an essential task for scene understanding and real-world applications. The main challenge of VPC is to describe ...
-
Chapter and Conference Paper
Cross-modal Representation Learning for Understanding Manufacturing Procedure
Assembling, biochemical experiments, and cooking are representatives that create a new value from multiple materials through multiple processes. If a machine can computationally understand such manufacturing t...
-
Chapter and Conference Paper
Deep Reinforcement Learning with Hidden Layers on Future States
Deep reinforcement learning algorithms such as Deep Q-Networks have successfully been used to construct a strong agent for Atari games by only performing direct evaluation of the current state and actions. Thi...
-
Chapter and Conference Paper
Exploration Bonuses Based on Upper Confidence Bounds for Sparse Reward Games
Recent deep reinforcement learning (RL) algorithms have achieved super-human-level performance in many Atari games. However, a closer look at their performance reveals that the algorithms fall short of humans ...