Learning Social Etiquette: Human Trajectory Understanding In Crowded Scenes

By Alexandre Robicquet, Amir Sadeghian, Alexandre Alahi, Silvio Savarese. European Conference on Computer Vision, 2016

946 citations recorded by the source corpus.

Subfields: Artificial Intelligence, Computer Vision and Pattern Recognition, Ocean Engineering

View Paper: https://www.semanticscholar.org/paper/d927a7b282c8a5896a72fc1efac6ace7a0fc0b8a

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Artificial Intelligence

In Computer Vision and Pattern Recognition

In Ocean Engineering

Citations in the corpus

Vision Meets Drones: A Challenge (2018, background): “Some recent efforts [9], [10], [11] have been devoted to construct datasets with drone platform focusing on object detection or tracking.”
Future Person Localization in First-Person Videos (2017, methodology): “Several methods have made use of Bayesian approaches [18, 36], recurrent neural networks [1, 19], fully-convolutional networks [12, 43], and other social or contextual features [32, 41] for predicting human trajectories from images or videos.”
Synthetic Data for Deep Learning (2019, background): “, estimating the UAV position and orientation in both 2D (on the map) and in the 3D space; for this problem, real datasets collected by real world UAVs are available [67,495,536,561], and the field is advanced enough to use actual field tests, so synthetic-only results are viewed with suspicion, but”
Naturalistic Driver Intention and Path Prediction Using Recurrent Neural Networks (2018, neutral): “[15] demonstrate their results on vehicle trajectories taken from the KITTI Dataset, and pedestrian sequences taken from the Stanford Drone dataset [17], as it is an unobstructed overhead camera view.”
The Pose Knows: Video Forecasting by Generating Pose Futures (2017, background): “However, the focus in recent work has been in specific data domains such as pedestrian trajectories in outdoor scenes [21, 32, 37] or pose prediction on humanlabeled mocap data [10, 17].”
Social Ways: Learning Multi-Modal Distributions of Pedestrian Trajectories With GANs (2019, methodology): “Moreover, on real trajectories, we have tested our algorithm on the Stanford Drone Dataset (SDD) [15].”
Human motion trajectory prediction: a survey (2019, background): “…2010; Elfring et al. 2014; Ferrer and Sanfeliu 2014; Kretzschmar et al. 2014; Pellegrini et al. 2009; Yamaguchi et al. 2011; Pellegrini et al. 2010; Robicquet et al. 2016; Oli et al. 2013; Karasev et al. 2016; Karamouzas et al. 2009; Karamouzas and Overmars 2010; Paris et al. 2007; Zechel et al.…”
INTERACTION Dataset: An INTERnational, Adversarial and Cooperative moTION Dataset in Interactive Driving Scenarios with Semantic Maps (2019, background): “Other datasets [22], [23] from bird’s eye view are more focused on pedestrian behavior without strong vehicle interactions.”
The inD Dataset: A Drone Dataset of Naturalistic Road User Trajectories at German Intersections (2019, methodology): “Also, we compare the inD dataset with other datasets that are commonly used in research, such as the Stanford Drone Dataset [12].”
The Unmanned Aerial Vehicle Benchmark: Object Detection and Tracking (2018, methodology): “00, Campus [39] 0 .”
From Goals, Waypoints & Paths To Long Term Human Trajectory Forecasting (2020, methodology): “Stanford Drone Dataset: We benchmark our proposed model on the popular Stanford drone dataset [33] where several recently proposed methods have improved stateof-the-art performance significantly in the past few years [45].”
Social GAN: Socially Acceptable Trajectories with Generative Adversarial Networks (2018, background): “[38] have shown that pedestrians have multiple navigation styles in crowded scenes given a mild or aggressive style of navigation.”
How many Observations are Enough? Knowledge Distillation for Trajectory Forecasting (2022, background): “[30] is a large scale dataset collected by a drone monitoring crowded university campus scenarios.”
RemoteCLIP: A Vision Language Foundation Model for Remote Sensing (2023, background): “Stanford [87] 2016 17,351 6 355,443 1424×1088 Stanford Drone dataset contains trajectory and interaction information of 20,000 objects across 8 different scenes on a campus in drones perspective.”
Deep learning in video multi-object tracking: A survey (2019, methodology): “They trained the network on the Stanford Drone Dataset (SDD) [139] and evaluated it on both SDD and MOT15.”
SoPhie: An Attentive GAN for Predicting Paths Compliant to Social and Physical Constraints (2018, background): “We also explore the Stanford Drone Dataset (SDD) [21], a benchmark dataset for trajectory prediction problems.”