-
Notifications
You must be signed in to change notification settings - Fork 2
Commit
This commit does not belong to any branch on this repository, and may belong to a fork outside of the repository.
Update bib information and supp file
- Loading branch information
1 parent
016d490
commit 12d73aa
Showing
2 changed files
with
6 additions
and
10 deletions.
There are no files selected for viewing
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Original file line number | Diff line number | Diff line change |
---|---|---|
|
@@ -8,15 +8,15 @@ cover-img: /subassets/img/head.JPG | |
* @Author: Conghao Wong | ||
* @Date: 2023-03-21 17:52:21 | ||
* @LastEditors: Conghao Wong | ||
* @LastEditTime: 2023-10-26 17:01:35 | ||
* @LastEditTime: 2024-03-26 17:16:21 | ||
* @Description: file content | ||
* @Github: https://cocoon2wong.github.io | ||
* Copyright 2023 Conghao Wong, All Rights Reserved. | ||
--> | ||
|
||
## Information | ||
|
||
This is the homepage of our paper "SocialCircle: Learning the Angle-based Social Interaction Representation for Pedestrian Trajectory Prediction". | ||
This is the homepage of our paper "SocialCircle: Learning the Angle-based Social Interaction Representation for Pedestrian Trajectory Prediction" (CVPR2024). | ||
The paper is available on arXiv. | ||
Click the buttons below for more information. | ||
|
||
|
@@ -33,7 +33,7 @@ Click the buttons below for more information. | |
|
||
![SocialCircle](./subassets/img/method.png) | ||
|
||
Analyzing and forecasting trajectories of agents like pedestrians and cars in complex scenes has become more and more significant in many intelligent systems and applications. The diversity and uncertainty in socially interactive behaviors among a rich variety of agents make this task more challenging than other deterministic computer vision tasks. Researchers have made a lot of efforts to quantify the effects of these interactions on future trajectories through different mathematical models and network structures, but this problem has not been well solved. Inspired by marine animals that localize the positions of their companions underwater through echoes, we build a new anglebased trainable social representation, named SocialCircle, for continuously reflecting the context of social interactions at different angular orientations relative to the target agent. We validate the effect of the proposed SocialCircle by training it along with several newly released trajectory prediction models, and experiments show that the SocialCircle not only quantitatively improves the prediction performance, but also qualitatively helps better consider social interactions when forecasting pedestrian trajectories in a way that is consistent with human intuitions. | ||
Analyzing and forecasting trajectories of agents like pedestrians and cars in complex scenes has become more and more significant in many intelligent systems and applications. The diversity and uncertainty in socially interactive behaviors among a rich variety of agents make this task more challenging than other deterministic computer vision tasks. Researchers have made a lot of efforts to quantify the effects of these interactions on future trajectories through different mathematical models and network structures, but this problem has not been well solved. Inspired by marine animals that localize the positions of their companions underwater through echoes, we build a new anglebased trainable social interaction representation, named SocialCircle, for continuously reflecting the context of social interactions at different angular orientations relative to the target agent. We validate the effect of the proposed SocialCircle by training it along with several newly released trajectory prediction models, and experiments show that the SocialCircle not only quantitatively improves the prediction performance, but also qualitatively helps better simulate social interactions when forecasting pedestrian trajectories in a way that is consistent with human intuitions. | ||
|
||
## Citation | ||
|
||
|
@@ -42,7 +42,7 @@ If you find this work useful, it would be grateful to cite our paper! | |
```bib | ||
@article{wong2023socialcircle, | ||
title={SocialCircle: Learning the Angle-based Social Interaction Representation for Pedestrian Trajectory Prediction}, | ||
author={Wong, Conghao and Xia, Beihao and You, Xinge}, | ||
author={Wong, Conghao and Xia, Beihao and Zou, Ziqian and Wang, Yulong and You, Xinge}, | ||
journal={arXiv preprint arXiv:2310.05370}, | ||
year={2023} | ||
} | ||
|
@@ -51,9 +51,5 @@ If you find this work useful, it would be grateful to cite our paper! | |
## Contact us | ||
|
||
Conghao Wong ([@cocoon2wong](https://github.com/cocoon2wong)): [email protected] | ||
Beihao Xia ([@NorthOcean](https://github.com/NorthOcean)): [email protected] | ||
|
||
--- | ||
*SocialCircle (Project Silverbullet) with Qpid version [db144af | ||
](https://github.com/cocoon2wong/Project-Qpid/tree/db144af30fda8b76e946756368ececd7039c62fc) and Dataset version [f58dde5](https://github.com/cocoon2wong/Project-Luna/tree/f58dde59e51eb43068b3d6f03169dea46208a4de). | ||
Copyright 2023 Conghao Wong and Beihao Xia, All Rights Reserved.* | ||
Beihao Xia ([@NorthOcean](https://github.com/NorthOcean)): [email protected] | ||
Ziqian Zou ([LivepoolQ](https://github.com/LivepoolQ)): [email protected] |
Binary file not shown.