AAN : Attributes-Aware Network for Temporal Action Detection - Inria - Institut national de recherche en sciences et technologies du numérique Access content directly
Conference Papers Year : 2023

AAN : Attributes-Aware Network for Temporal Action Detection

Rui Dai
  • Function : Author
  • PersonId : 1057956
Srijan Das
  • Function : Author
  • PersonId : 21855
  • IdHAL : srijan-das
Michael Ryoo
  • Function : Author
  • PersonId : 1294527

Abstract

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 OpenAI's 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.
Fichier principal
Vignette du fichier
BMVC2023.pdf (1.66 Mo) Télécharger le fichier
Origin Files produced by the author(s)

Dates and versions

hal-04241623 , version 1 (13-10-2023)

Identifiers

  • HAL Id : hal-04241623 , version 1

Cite

Rui Dai, Srijan Das, Michael Ryoo, Francois Bremond. AAN : Attributes-Aware Network for Temporal Action Detection. BMVC 2023 - The 34th British Machine Vision Conference, Nov 2023, Aberdeen, United Kingdom. ⟨hal-04241623⟩
83 View
40 Download

Share

Gmail Mastodon Facebook X LinkedIn More