mlsanityData to 7 Oct 2026

AAN: Attributes-Aware Network for Temporal Action Detection

arXiv 2309.00696 ↗First posted 1 Sep 2023cs.CVcited by 1

Not on the map. Why?

Abstract (arXiv)

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.

Key facts. Cited by 1 paper in the map (data through 7 Oct 2026). Builds on 40 of its 46 references that are in the map. First posted on arXiv 1 Sep 2023.

Builds on

40 of 46 references.

References · 40

  1. 2014Adam: A Method for Stochastic Optimizationcited by 36,960
  2. 2021Learning Transferable Visual Models From Natural Language Supervisioncited by 33,456
  3. 2020An Image is Worth 16x16 Words: Transformers for Image Recognition at Scalecited by 29,915
  4. 2016Semi-Supervised Classification with Graph Convolutional Networkscited by 11,282
  5. 2019Momentum Contrast for Unsupervised Visual Representation Learningcited by 7,482
  6. 2017Quo Vadis, Action Recognition? A New Model and the Kinetics Datasetcited by 3,259
  7. 2017The Kinetics Human Action Video Datasetcited by 1,894
  8. 2021ViViT: A Video Vision Transformercited by 1,610
  9. 2021Open-vocabulary Object Detection via Vision and Language Knowledge Distillationcited by 903
  10. 2021CLIP4Clip: An Empirical Study of CLIP for End to End Video Clip Retrievalcited by 645
  11. 2020X3D: Expanding Architectures for Efficient Video Recognitioncited by 635
  12. 2016Hollywood in Homes: Crowdsourcing Data Collection for Activity Understandingcited by 535
28 more
  1. 2019Self-Attention Graph Poolingcited by 421
  2. 2021How Much Can CLIP Benefit Vision-and-Language Tasks?cited by 321
  3. 2021ActionCLIP: A New Paradigm for Video Action Recognitioncited by 317
  4. 2018Video Action Transformer Networkcited by 316
  5. 2018Videos as Space-Time Region Graphscited by 221
  6. 2022Frozen CLIP Models are Efficient Video Learnerscited by 181
  7. 2017R-C3D: Region Convolutional 3D Network for Temporal Activity Detectioncited by 161
  8. 2019Learning Semantic-Specific Graph Representation for Multi-Label Image Recognitioncited by 116
  9. 2021VLM: Task-agnostic Video-Language Model Pre-training for Video Understandingcited by 102
  10. 2015Every Moment Counts: Dense Detailed Labeling of Actions in Complex Videoscited by 93
  11. 2022A CLIP-Hitchhiker's Guide to Long Video Retrievalcited by 57
  12. 2020Toyota Smarthome Untrimmed: Real-World Untrimmed Videos for Activity Detectioncited by 42
  13. 2021MS-TCT: Multi-Scale Temporal ConvTransformer for Action Detectioncited by 42
  14. 2022ProposalCLIP: Unsupervised Open-Category Object Proposal Generation via Exploiting CLIP Cuescited by 42
  15. 2018Temporal Gaussian Mixture Layer for Videoscited by 40
  16. 2021VPN++: Rethinking Video-Pose embeddings for understanding Activities of Daily Livingcited by 35
  17. 2021Modeling Multi-Label Action Dependencies for Temporal Action Localizationcited by 32
  18. 2021Learning an Augmented RGB Representation with Cross-Modal Knowledge Distillation for Action Detectioncited by 32
  19. 2017Learning Latent Super-Events to Detect Multiple Activities in Videoscited by 30
  20. 2021Coarse-Fine Networks for Temporal Activity Detection in Videoscited by 28
  21. 2023VicTR: Video-conditioned Text Representations for Activity Recognitioncited by 28
  22. 2018Stacked Spatio-Temporal Graph Convolutional Networks for Action Segmentationcited by 25
  23. 2022Token Turing Machinescited by 25
  24. 2016Asynchronous Temporal Fields for Action Recognitioncited by 21
  25. 2021CTRN: Class-Temporal Relational Network for Action Detectioncited by 15
  26. 2015Action Recognition by Hierarchical Mid-level Action Elementscited by 6
  27. 2021Weakly-guided Self-supervised Pretraining for Temporal Activity Detectioncited by 5
  28. 2022THORN: Temporal Human-Object Relation Network for Action Recognitioncited by 2

Built on by

Cited by year

Citing papers per year: 2025: 1.

1 paper.

  1. 2025Reframing Dense Action Detection (RefDense): A Paradigm Shift in Problem Solving & a Novel Optimization Strategycited by 0