# Temporal Contrastive Learning with Curriculum

Source: [Temporal Contrastive Learning with Curriculum](<https://www.sota2.com/research/paper/68fa6d591e209131cea39597>)

Collection index: [llms.txt](<https://www.sota2.com/research/llms.txt>)

Data updated: 2025-10-28T13:56:55.079Z

Authors: Shuvendu Roy, Ali Etemad

Published: 2022-09-02T00:12:05.000Z

## Abstract

We present ConCur, a contrastive video representation learning method that uses curriculum learning to impose a dynamic sampling strategy in contrastive training. More specifically, ConCur starts the contrastive training with easy positive samples (temporally close and semantically similar clips), and as the training progresses, it increases the temporal span effectively sampling hard positives (temporally away and semantically dissimilar). To learn better context-aware representations, we also propose an auxiliary task of predicting the temporal distance between a positive pair of clips. We conduct extensive experiments on two popular action recognition datasets, UCF101 and HMDB51, on which our proposed method achieves state-of-the-art performance on two benchmark tasks of video action recognition and video retrieval. We explore the impact of encoder backbones and pre-training strategies by using R(2+1)D and C3D encoders and pre-training on Kinetics-400 and Kinetics-200 datasets. Moreover, a detailed ablation study shows the effectiveness of each of the components of our proposed method.

## Recorded benchmark results

A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage.

## Original sources and implementation

[Original paper](<https://arxiv.org/abs/2209.00760>)

[PDF](<https://arxiv.org/pdf/2209.00760.pdf>)