Skip to content

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

1 Commit
 
 
 
 
 
 
 
 
 
 
 
 
 
 

Repository files navigation

Learning Object Interactions from Temporal Dynamics

This project explores self-supervised learning of object interactions from raw temporal trajectories using a Transformer-based architecture. The goal is to learn meaningful representations of interaction dynamics without any manual labels.


Problem Statement

Understanding object interactions from motion trajectories is a fundamental problem in computer vision and robotics. Traditional approaches rely on handcrafted features, which often fail to generalize.

This project investigates whether a self-supervised Transformer can learn disentangled representations of interaction types directly from temporal data.


Method

We propose a pipeline consisting of:

  • Temporal trajectory input (synthetic multi-object scenes)
  • Data augmentation for self-supervised learning
  • Transformer encoder for sequence modeling
  • VICReg-based loss function to prevent representation collapse

Architecture

Input: Temporal Object Trajectories (Ball, Box, Cylinder positions over time) │ ▼ Data Augmentation (two stochastic temporal views) │ ├───────────────┐ ▼ ▼ View 1 View 2 │ │ ▼ ▼ Transformer Encoder (shared weights) │ │ ▼ ▼ z₁ ∈ ℝ⁶⁴ z₂ ∈ ℝ⁶⁴ └───────────────┘ │ ▼ VICReg Objective ┌──────────────────────────┐ │ Invariance loss │ │ Variance regularization │ │ Covariance regularization│ └──────────────────────────┘ │ ▼ Learned Embedding Space

Evaluation

We evaluate learned representations using clustering (DBSCAN) and compare them with handcrafted temporal features (baseline method).

Key finding:

  • The model successfully separates interaction types:
    • Chain interactions
    • Pass-by interactions
    • Independent motion

Results

Self-supervised Transformer embeddings show clear cluster separation compared to baseline temporal features, indicating that the model learns meaningful interaction structure without supervision.


Project Structure

src/ Core modules (model, dataset, loss) experiments/ Training & embedding extraction results/ Trained model & embeddings archive/ Old experiments (not required for reproduction)

Author

Sara Haghverdi Mamaghani

About

Self-supervised transformer for learning object interactions from temporal trajectories

Topics

Resources

Stars

0 stars

Watchers

0 watching

Forks

Releases

Packages

Contributors

Languages