mlsanityData to 7 Oct 2026

A Better Baseline for AVA

arXiv 1807.10066 ↗First posted 26 Jul 2018cs.CVcited by 16

Not on the map. Why?

Abstract (arXiv)

We introduce a simple baseline for action localization on the AVA dataset. The model builds upon the Faster R-CNN bounding box detection framework, adapted to operate on pure spatiotemporal features - in our case produced exclusively by an I3D model pretrained on Kinetics. This model obtains 21.9% average AP on the validation set of AVA v2.1, up from 14.5% for the best RGB spatiotemporal model used in the original AVA paper (which was pretrained on Kinetics and ImageNet), and up from 11.3 of the publicly available baseline using a ResNet101 image feature extractor, that was pretrained on ImageNet. Our final model obtains 22.8%/21.9% mAP on the val/test sets and outperforms all submissions to the AVA challenge at CVPR 2018.

Key facts. Cited by 16 papers in the map (data through 7 Oct 2026). First posted on arXiv 26 Jul 2018.

Builds on

No reference list yet.

Built on by

Cited by year

Citing papers per year: 2021: 9; 2022: 4; 2023: 2; 2024: 0; 2025: 1.

16 papers.

Sort:

  1. 2021TubeR: Tubelet Transformer for Video Action Detectioncited by 55
  2. 2021ROAD: The ROad event Awareness Dataset for Autonomous Drivingcited by 54
  3. 2021JRDB-Act: A Large-scale Dataset for Spatio-temporal Action, Social Group and Activity Detectioncited by 38
  4. 2021Deep Learning-based Action Detection in Untrimmed Videos: A Surveycited by 32
  5. 2021Attend What You Need: Motion-Appearance Synergistic Networks for Video Question Answeringcited by 26
  6. 2021SVIP: Sequence VerIfication for Procedures in Videoscited by 16
  7. 2022Spatio-Temporal Action Detection Under Large Motioncited by 14
  8. 2022A Simple and Efficient Pipeline to Build an End-to-End Spatial-Temporal Action Detectorcited by 6
  9. 2025Game State and Spatio-temporal Action Detection in Soccer using Graph Neural Networks and 3D Convolutional Networkscited by 6
  10. 2023A Survey on Deep Learning-based Spatio-temporal Action Detectioncited by 5
  11. 2023CycleACR: Cycle Modeling of Actor-Context Relations for Video Action Detectioncited by 3
  12. 2021Projection: A Mechanism for Human-like Reasoning in Artificial Intelligencecited by 2
4 more
  1. 2021Spatio-Temporal Context for Action Detectioncited by 1
  2. 2021Hierarchical Graph-RNNs for Action Detection of Multiple Activitiescited by 0
  3. 2022Scalable Temporal Localization of Sensitive Activities in Movies and TV Episodescited by 0
  4. 2022Actor-identified Spatiotemporal Action Detection -- Detecting Who Is Doing What in Videoscited by 0