Crowds by Example

By Alon Lerner, Y. Chrysanthou, Dani Lischinski. Computer graphics forum (Print), 2007

1,385 citations recorded by the source corpus.

Subfields: Computer Vision and Pattern Recognition, Control and Systems Engineering, Ocean Engineering

View Paper: https://www.semanticscholar.org/paper/3921f459a9ee26827963abc4abf013b4cc9cbd32

How researchers see this paper

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

In Computer Vision and Pattern Recognition

In Control and Systems Engineering

In Ocean Engineering

Citations in the corpus

It Is Not the Journey but the Destination: Endpoint Conditioned Trajectory Prediction (2020, methodology): “Third , we show that our model can predict stable and plausible intermediate goals that enable setting a new state-of-the-art on several trajectory prediction benchmarks, improving by 19.5 % on SDD [5] & 40.8% on ETH [6] & UCY [7].”
You'll never walk alone: Modeling social behavior for multi-target tracking (2009, methodology): “To test the prediction performance of our model, we use annotated data provided by the authors of [17].”
Large Scale Interactive Motion Forecasting for Autonomous Driving : The Waymo Open Motion Dataset (2021, background): “We also note there are a host of other motion forecasting datasets which, while popular, are orders of magnitude smaller, have O(10) unique locations, and/or are not focused on driving environment, for example the Stanford Drone Dataset [30], NGSIM [10], ETH [24], UCY [21], Town Center [2].”
Multiple object tracking: A literature review (2014, methodology): “ry, (b) semi-crowded scenery and (c) over-crowded scenery. From left to right, top to bottom, images are from CAVIAR data set, PETS2009 data set, UCF Crowds data set, Zara data set, TUD data set and [Lerner et al. 2007]. 2.2. MOT Scenarios We largely categorize the scenarios where the MOT problem ar”
AgentFormer: Agent-Aware Transformers for Socio-Temporal Multi-Agent Forecasting (2021, methodology): “We evaluate our method on well-established pedestrian datasets, ETH [38] and UCY [28], and an autonomous driving dataset, nuScenes [3].”
Trajectron++: Dynamically-Feasible Trajectory Forecasting with Heterogeneous Data (2020, methodology): “Our method is evaluated on three publicly-available datasets: The ETH [37], UCY [33], and nuScenes [6] datasets.”
Transformer Networks for Trajectory Forecasting (2020, methodology): “Prior to TrajNet, most literature have benchmarked forecasting performance on a set of 5 datasets, namely the ETH-univ and ETH-hotel [33] video sequences and the UCY-zara01, UCY-zara02 and UCY-univ [28] videos.”
Stochastic Trajectory Prediction via Motion Indeterminacy Diffusion (2022, methodology): “Experimental results demonstrate the superiority of our method which achieves state-of-the-art performance on the Stanford Drone and ETH/UCY benchmarks.”
STGAT: Modeling Spatial-Temporal Interactions for Human Trajectory Prediction (2019, methodology): “In this section, we present the results on two publicly available pedestrian trajectory datasets: ETH [21] and UCY [17].”
SS-LSTM: A Hierarchical LSTM Model for Pedestrian Trajectory Prediction (2018, background): “ETH and UCY: ETH [19] and UCY [15] are two publicly available datasets of pedestrian trajectories that cover challenging movement patterns like walking together and collision avoidance.”
TraPHic: Trajectory Prediction in Dense and Heterogeneous Traffic Using Weighted Interactions (2018, background): “There are some pedestrian trajectory datasets like ETH [31] and UCY [28], but they are limited to pedestrians in a crowd.”
The inD Dataset: A Drone Dataset of Naturalistic Road User Trajectories at German Intersections (2019, methodology): “In Table I, we compare the inD dataset with current public datasets, which are the most similar to the inD dataset: Crowds UCY/Zara [7], Ko-PER [16], DUT [18], CITR [18], BIWI Hotel/ETH [9], VRU Trajectory Dataset [4] and Stanford Drone [12].”
Social Attention: Modeling Attention in Human Crowds (2017, methodology): “We evaluate our model, which we call Social Attention , on two publicly available datasets: ETH [32], and UCY [33].”
LEMMA: A Multi-view Dataset for Learning Multi-agent Multi-task Activities (2020, background): “Another related stream of work is the learning of group-level activities in a multi-agent setting [26], such as detecting key actors [43], predicting future trajectories [40,34], and recognizing collective activities [11,39,50].”
Peeking Into the Future: Predicting Future Person Activities and Locations in Videos (2019, methodology): “ETH [23] and UCY [16] are common datasets for person trajectory prediction benchmark [1, 7, 21, 26].”
Socially compliant mobile robot navigation via inverse reinforcement learning (2016, background): “Lerner et al. (2007) inferred a database of navigation rules from video data.”
PIE: A Large-Scale Dataset and Models for Pedestrian Intention Estimation and Trajectory Prediction (2019, background): “A number of datasets for trajectory prediction contain videos collected from a top-down view [18, 25, 22, 31] or surveillance camera perspective [23, 4, 45].”
From Goals, Waypoints & Paths To Long Term Human Trajectory Forecasting (2020, methodology): “We also report results on the ETH/UCY benchmark in Table 2.”
Social Ways: Learning Multi-Modal Distributions of Pedestrian Trajectories With GANs (2019, methodology): “The ETH dataset contains 2 experiments (coined as ETH and Hotel) and the UCY dataset contains 3 experiments (ZARA01, ZARA02 and Univ).”