Table of Contents
Fetching ...

SocialCircle: Learning the Angle-based Social Interaction Representation for Pedestrian Trajectory Prediction

Conghao Wong, Beihao Xia, Ziqian Zou, Yulong Wang, Xinge You

TL;DR

This document outlines the CVPR 2024 style and submission guidelines, detailing language, dual-submission policies, page limits, and formatting requirements. It prescribes numbered sections and equations, blind-review anonymization, margin and typography rules, and standardized handling of references, figures, and color. The guidelines ensure consistent presentation and fair review by dictating how content should be organized, cited, and prepared for publication. Adherence to these rules facilitates efficient editorial processing and reproducible formatting across submissions.

Abstract

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.

SocialCircle: Learning the Angle-based Social Interaction Representation for Pedestrian Trajectory Prediction

TL;DR

This document outlines the CVPR 2024 style and submission guidelines, detailing language, dual-submission policies, page limits, and formatting requirements. It prescribes numbered sections and equations, blind-review anonymization, margin and typography rules, and standardized handling of references, figures, and color. The guidelines ensure consistent presentation and fair review by dictating how content should be organized, cited, and prepared for publication. Adherence to these rules facilitates efficient editorial processing and reproducible formatting across submissions.

Abstract

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.
Paper Structure (18 sections, 2 equations, 2 figures, 1 table)

This paper contains 18 sections, 2 equations, 2 figures, 1 table.

Figures (2)

  • Figure 1: Example of caption. It is set in Roman so that mathematics (always set in Roman: $B \sin A = A \sin B$) may be included without an ugly clash.
  • Figure 2: Example of a short caption, which should be centered.