mlsanityData to 7 Oct 2026

IntFormer: Predicting pedestrian intention with the aid of the Transformer architecture

arXiv 2105.08647 ↗First posted 18 May 2021cs.CV cs.AIcited by 13

Not on the map. Why?

Abstract (arXiv)

Understanding pedestrian crossing behavior is an essential goal in intelligent vehicle development, leading to an improvement in their security and traffic flow. In this paper, we developed a method called IntFormer. It is based on transformer architecture and a novel convolutional video classification model called RubiksNet. Following the evaluation procedure in a recent benchmark, we show that our model reaches state-of-the-art results with good performance (≈ 40 seq. per second) and size (8× smaller than the best performing model), making it suitable for real-time usage. We also explore each of the input features, finding that ego-vehicle speed is the most important variable, possibly due to the similarity in crossing cases in PIE dataset.

Key facts. Cited by 13 papers in the map (data through 7 Oct 2026). Builds on 11 of its 21 references that are in the map. First posted on arXiv 18 May 2021.

Builds on

11 of 21 references.

References · 11

  1. 2017Attention Is All You Needcited by 59,932
  2. 2016Realtime Multi-Person 2D Pose Estimation using Part Affinity Fieldscited by 1,061
  3. 2021Transformers in Vision: A Surveycited by 1,009
  4. 2018TSM: Temporal Shift Module for Efficient Video Understandingcited by 852
  5. 2019Human Motion Trajectory Prediction: A Surveycited by 231
  6. 2020A Comprehensive Study of Deep Video Action Recognitioncited by 87
  7. 2019Real-time Intent Prediction of Pedestrians for Autonomous Ground Vehicles via Spatio-Temporal DenseNetcited by 28
  8. 2019Looking Ahead: Anticipating Pedestrians Crossing with Future Frames Predictioncited by 25
  9. 2020RNN-based Pedestrian Crossing Prediction using Activity and Pose-related Featurescited by 21
  10. 2020FuSSI-Net: Fusion of Spatio-temporal Skeletons for Intention Prediction Networkcited by 17
  11. 2018Joint Attention in Driver-Pedestrian Interaction: from Theory to Practicecited by 4

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2022: 2; 2023: 0; 2024: 3; 2025: 6; 2026: 2.

13 papers.

Sort:

  1. 2022Behavioral Intention Prediction in Driving Scenes: A Surveycited by 30
  2. 2022Assessing Cross-dataset Generalization of Pedestrian Crossing Predictorscited by 11
  3. 2024GTransPDM: A Graph-embedded Transformer with Positional Decoupling for Pedestrian Crossing Intention Predictioncited by 4
  4. 2025Multi-Context Fusion Transformer for Pedestrian Crossing Intention Prediction in Urban Environmentscited by 3
  5. 2025ACIT: Attention-Guided Cross-Modal Interaction Transformer for Pedestrian Crossing Intention Predictioncited by 3
  6. 2024Can Reasons Help Improve Pedestrian Intent Estimation? A Cross-Modal Approachcited by 2
  7. 2025Seeing Beyond Frames: Zero-Shot Pedestrian Intention Prediction with Raw Temporal Video and Multimodal Cuescited by 2
  8. 2026VIT-Ped: Visionary Intention Transformer for Pedestrian Behavior Analysiscited by 2
  9. 2024Gating Syn-to-Real Knowledge for Pedestrian Crossing Prediction in Safe Drivingcited by 1
  10. 2025Pedestrian Crossing Intention Prediction Using Multimodal Fusion Networkcited by 1
  11. 2025Temporal-contextual Event Learning for Pedestrian Crossing Intent Predictioncited by 0
  12. 2025Enhancing Customer Service Chatbots with Context-Aware NLU through Selective Attention and Multi-task Learningcited by 0
1 more
  1. 2026Adaptive Cross-Modal Fusion with Sparse Attention for Pedestrian Crossing Intention Predictioncited by 0