# Unified Vision-Centric Pedestrian Crossing Action Prediction via Adaptive Patch Projection and Proactive Spatial Rectification

arXiv: https://arxiv.org/abs/2609.07420 · HTML: https://mlsanity.com/paper/2609.07420/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Placed in Driving VLMs and open-vocabulary detection, one of 16 directions in Multimodal LLMs / vision-language models.
- Builds on 30 of its 52 references that are in the map.
- First posted on arXiv 7 Sep 2026.

## Placed in

- Multimodal LLMs / vision-language models / [Driving VLMs and open-vocabulary detection](https://mlsanity.com/mllm/driving-vlms-and-open-vocabulary-detection/)

## Builds on (most cited first, 30 of 30)

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [Very Deep Convolutional Networks for Large-Scale Image Recognition](https://mlsanity.com/paper/1409.1556/) (2014)
- [Swin Transformer: Hierarchical Vision Transformer using Shifted Windows](https://mlsanity.com/paper/2103.14030/) (2021)
- [Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks](https://mlsanity.com/paper/1506.01497/) (2015)
- [Visual Instruction Tuning](https://mlsanity.com/paper/2304.08485/) (2023)
- [You Only Look Once: Unified, Real-Time Object Detection](https://mlsanity.com/paper/1506.02640/) (2015)
- [Qwen2-VL: Enhancing Vision-Language Model's Perception of the World at Any Resolution](https://mlsanity.com/paper/2409.12191/) (2024)
- [Quo Vadis, Action Recognition? A New Model and the Kinetics Dataset](https://mlsanity.com/paper/1705.07750/) (2017)
- [Pyramid Vision Transformer: A Versatile Backbone for Dense Prediction without Convolutions](https://mlsanity.com/paper/2102.12122/) (2021)
- [Convolutional LSTM Network: A Machine Learning Approach for Precipitation Nowcasting](https://mlsanity.com/paper/1506.04214/) (2015)
- [Realtime Multi-Person 2D Pose Estimation using Part Affinity Fields](https://mlsanity.com/paper/1611.08050/) (2016)
- [Simple Online and Realtime Tracking with a Deep Association Metric](https://mlsanity.com/paper/1703.07402/) (2017)
- [Conditional DETR for Fast Training Convergence](https://mlsanity.com/paper/2108.06152/) (2021)
- [Long-Term On-Board Prediction of People in Traffic Scenes under Uncertainty](https://mlsanity.com/paper/1711.09026/) (2017)
- [Predicting Pedestrian Crossing Intention with Feature Fusion and Spatio-Temporal Attention](https://mlsanity.com/paper/2104.05485/) (2021)
- [Bifold and Semantic Reasoning for Pedestrian Behavior Prediction](https://mlsanity.com/paper/2012.03298/) (2020)
- [Real-time Intent Prediction of Pedestrians for Autonomous Ground Vehicles via Spatio-Temporal DenseNet](https://mlsanity.com/paper/1904.09862/) (2019)
- [Is the Pedestrian going to Cross? Answering by 2D Pose Estimation](https://mlsanity.com/paper/1807.10580/) (2018)
- [PedFormer: Pedestrian Behavior Prediction via Cross-Modal Attention Modulation and Gated Multitask Learning](https://mlsanity.com/paper/2210.07886/) (2022)
- [RNN-based Pedestrian Crossing Prediction using Activity and Pose-related Features](https://mlsanity.com/paper/2008.11647/) (2020)
- [Pedestrian Trajectory Prediction with Convolutional Neural Networks](https://mlsanity.com/paper/2010.05796/) (2020)
- [Is attention to bounding boxes all you need for pedestrian action prediction?](https://mlsanity.com/paper/2107.08031/) (2021)
- [GPT-4V Takes the Wheel: Promises and Challenges for Pedestrian Behavior Prediction](https://mlsanity.com/paper/2311.14786/) (2023)
- [Deep Virtual-to-Real Distillation for Pedestrian Crossing Prediction](https://mlsanity.com/paper/2211.00856/) (2022)
- [Multimodal Large Models Are Effective Action Anticipators](https://mlsanity.com/paper/2501.00795/) (2025)
- [TAMFormer: Multi-Modal Transformer with Learned Attention Mask for Early Intent Prediction](https://mlsanity.com/paper/2210.14714/) (2022)
- [Context Model for Pedestrian Intention Prediction using Factored Latent-Dynamic Conditional Random Fields](https://mlsanity.com/paper/1907.11881/) (2019)
- [Synthetic Data Generation Framework, Dataset, and Efficient Deep Model for Pedestrian Intention Prediction](https://mlsanity.com/paper/2401.06757/) (2024)
- [Orientation-Aware Leg Movement Learning for Action-Driven Human Motion Prediction](https://mlsanity.com/paper/2310.14907/) (2023)
- [Diving Deeper Into Pedestrian Behavior Understanding: Intention Estimation, Action Prediction, and Event Risk Assessment](https://mlsanity.com/paper/2407.00446/) (2024)

## Abstract (arXiv)

Vision cues are available and informative for pedestrian action prediction, but obtaining stable target-centric representations from video frames remains challenging without frame-level external perception cues. Thus, most methods rely on additional perception modules or multi-source information fusion, leaving the reliability of vision-centric setting an open question. To this end, we propose ViCross, a vision-centric pedestrian crossing action prediction framework powered by multimodal large language models, which maintains target-centric reasoning from video frames without additional perception modules beyond first-frame target initialization. While multimodal large language models exhibit strong visual understanding, applying them directly to vision-centric action prediction faces two challenges. First, accurately perceiving target pedestrians often requires high resolution inputs and dense visual tokenization, making full-frame encoding computationally prohibitive. ViCross tackles this with Variable Resolution Patch Mapping module for efficient token allocation while preserving key pedestrian details. Second, missing spatiotemporal priors hinder consistent cross frame reasoning. ViCross mitigates this with a Spatial Constraint Enhancement Strategy that captures past motion, future locations, and action semantics for training-time proactive spatial rectification. Extensive experiments show that ViCross delivers clear gains in vision-centric prediction settings and is competitive with multi-source fusion approaches in several settings. Code is available at https://github.com/2tianyao1/ViCross.git.