@article{dai_das_ryoo_bremond_2023, 
  title={AAN: Attributes-Aware Network for Temporal Action Detection}, 
  abstractNote={The challenge of long-term video understanding remains constrained by the
efficient extraction of object semantics and the modelling of their
relationships for downstream tasks. Although the CLIP visual features exhibit
discriminative properties for various vision tasks, particularly in object
encoding, they are suboptimal for long-term video understanding. To address
this issue, we present the Attributes-Aware Network (AAN), which consists of
two key components: the Attributes Extractor and a Graph Reasoning block. These
components facilitate the extraction of object-centric attributes and the
modelling of their relationships within the video. By leveraging CLIP features,
AAN outperforms state-of-the-art approaches on two popular action detection
datasets: Charades and Toyota Smarthome Untrimmed datasets.}, 
  author={Dai and Das and Ryoo and Bremond}, 
  year={2023}, 
  month={Sep}
  }