Youku Technology
Oct 28, 2022 · Artificial Intelligence
Enlarging Long‑time Dependencies via Reinforcement‑Learning‑Based Memory Network for Movie Affective Analysis
The authors introduce a reinforcement‑learning‑driven memory network that augments long‑range dependencies for continuous valence‑arousal emotion prediction in movies, integrating five multimodal features and a DDPG‑based update policy, which yields state‑of‑the‑art performance across multiple affective‑analysis and summarization benchmarks.
Memory NetworkReinforcement LearningVA affect model
0 likes · 16 min read