English

Self-Supervised Contrastive Learning for Videos using Differentiable Local Alignment

Computer Vision and Pattern Recognition 2025-03-04 v2

Abstract

Robust frame-wise embeddings are essential to perform video analysis and understanding tasks. We present a self-supervised method for representation learning based on aligning temporal video sequences. Our framework uses a transformer-based encoder to extract frame-level features and leverages them to find the optimal alignment path between video sequences. We introduce the novel Local-Alignment Contrastive (LAC) loss, which combines a differentiable local alignment loss to capture local temporal dependencies with a contrastive loss to enhance discriminative learning. Prior works on video alignment have focused on using global temporal ordering across sequence pairs, whereas our loss encourages identifying the best-scoring subsequence alignment. LAC uses the differentiable Smith-Waterman (SW) affine method, which features a flexible parameterization learned through the training phase, enabling the model to adjust the temporal gap penalty length dynamically. Evaluations show that our learned representations outperform existing state-of-the-art approaches on action recognition tasks.

Keywords

Cite

@article{arxiv.2409.04607,
  title  = {Self-Supervised Contrastive Learning for Videos using Differentiable Local Alignment},
  author = {Keyne Oei and Amr Gomaa and Anna Maria Feit and João Belo},
  journal= {arXiv preprint arXiv:2409.04607},
  year   = {2025}
}

Comments

Accepted in 2nd Workshop on Video Understanding and its Applications, held in conjunction with the British Machine Vision Conference (BMVC) 2024

R2 v1 2026-06-28T18:37:00.924Z