# Learning a Condensed Frame for Memory-Efficient Video Class-Incremental Learning

arXiv: https://arxiv.org/abs/2211.00833 · HTML: https://mlsanity.com/paper/2211.00833/

## Key facts

- Cited by 11 papers in the map (data through 14 Oct 2026).
- Builds on 50 of its 79 references that are in the map.
- First posted on arXiv 2 Nov 2022.

## Builds on (most cited first, 30 of 50)

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale](https://mlsanity.com/paper/2010.11929/) (2020)
- [PyTorch: An Imperative Style, High-Performance Deep Learning Library](https://mlsanity.com/paper/1912.01703/) (2019)
- [Very Deep Convolutional Networks for Large-Scale Image Recognition](https://mlsanity.com/paper/1409.1556/) (2014)
- [Distilling the Knowledge in a Neural Network](https://mlsanity.com/paper/1503.02531/) (2015)
- [Overcoming catastrophic forgetting in neural networks](https://mlsanity.com/paper/1612.00796/) (2016)
- [Prefix-Tuning: Optimizing Continuous Prompts for Generation](https://mlsanity.com/paper/2101.00190/) (2021)
- [The Power of Scale for Parameter-Efficient Prompt Tuning](https://mlsanity.com/paper/2104.08691/) (2021)
- [Quo Vadis, Action Recognition? A New Model and the Kinetics Dataset](https://mlsanity.com/paper/1705.07750/) (2017)
- [Learning without Forgetting](https://mlsanity.com/paper/1606.09282/) (2016)
- [iCaRL: Incremental Classifier and Representation Learning](https://mlsanity.com/paper/1611.07725/) (2016)
- [Pre-train, Prompt, and Predict: A Systematic Survey of Prompting Methods in Natural Language Processing](https://mlsanity.com/paper/2107.13586/) (2021)
- [SlowFast Networks for Video Recognition](https://mlsanity.com/paper/1812.03982/) (2018)
- [Visual Prompt Tuning](https://mlsanity.com/paper/2203.12119/) (2022)
- [Is Space-Time Attention All You Need for Video Understanding?](https://mlsanity.com/paper/2102.05095/) (2021)
- [ViViT: A Video Vision Transformer](https://mlsanity.com/paper/2103.15691/) (2021)
- [Swin Transformer V2: Scaling Up Capacity and Resolution](https://mlsanity.com/paper/2111.09883/) (2021)
- [Continual Learning with Deep Generative Replay](https://mlsanity.com/paper/1705.08690/) (2017)
- [A Closer Look at Spatiotemporal Convolutions for Action Recognition](https://mlsanity.com/paper/1711.11248/) (2017)
- [Memory Aware Synapses: Learning what (not) to forget](https://mlsanity.com/paper/1711.09601/) (2017)
- [The "something something" video database for learning and evaluating visual common sense](https://mlsanity.com/paper/1706.04261/) (2017)
- [Video Swin Transformer](https://mlsanity.com/paper/2106.13230/) (2021)
- [Learning to Prompt for Continual Learning](https://mlsanity.com/paper/2112.08654/) (2021)
- [Dark Experience for General Continual Learning: a Strong, Simple Baseline](https://mlsanity.com/paper/2004.07211/) (2020)
- [Multiscale Vision Transformers](https://mlsanity.com/paper/2104.11227/) (2021)
- [TSM: Temporal Shift Module for Efficient Video Understanding](https://mlsanity.com/paper/1811.08383/) (2018)
- [Large Scale Incremental Learning](https://mlsanity.com/paper/1905.13260/) (2019)
- [DualPrompt: Complementary Prompting for Rehearsal-free Continual Learning](https://mlsanity.com/paper/2204.04799/) (2022)
- [X3D: Expanding Architectures for Efficient Video Recognition](https://mlsanity.com/paper/2004.04730/) (2020)
- [End-to-End Incremental Learning](https://mlsanity.com/paper/1807.09536/) (2018)

## Built on by (most cited first, 11 of 11)

- [Just a Glimpse: Rethinking Temporal Information for Video Continual Learning](https://mlsanity.com/paper/2305.18418/) (2023)
- [StPR: Spatiotemporal Preservation and Routing for Exemplar-Free Video Class-Incremental Learning](https://mlsanity.com/paper/2505.13997/) (2025)
- [Coherent Temporal Synthesis for Incremental Action Segmentation](https://mlsanity.com/paper/2403.06102/) (2024)
- [CSTA: Spatial-Temporal Causal Adaptive Learning for Exemplar-Free Video Class-Incremental Learning](https://mlsanity.com/paper/2501.07236/) (2025)
- [Enlarging Instance-specific and Class-specific Information for Open-set Action Recognition](https://mlsanity.com/paper/2303.15467/) (2023)
- [Hierarchical Augmentation and Distillation for Class Incremental Audio-Visual Video Recognition](https://mlsanity.com/paper/2401.06287/) (2024)
- [Deep incremental learning models for financial temporal tabular datasets with distribution shifts](https://mlsanity.com/paper/2303.07925/) (2023)
- [Decoupled Prompt-Adapter Tuning for Continual Activity Recognition](https://mlsanity.com/paper/2407.14811/) (2024)
- [CRAM: Large-scale Video Continual Learning with Bootstrapped Compression](https://mlsanity.com/paper/2508.05001/) (2025)
- [ESSENTIAL: Episodic and Semantic Memory Integration for Video Class-Incremental Learning](https://mlsanity.com/paper/2508.10896/) (2025)
- [Unsupervised Video Continual Learning via Non-Parametric Deep Embedded Clustering](https://mlsanity.com/paper/2508.21773/) (2025)

## Abstract (arXiv)

Recent incremental learning for action recognition usually stores representative videos to mitigate catastrophic forgetting. However, only a few bulky videos can be stored due to the limited memory. To address this problem, we propose FrameMaker, a memory-efficient video class-incremental learning approach that learns to produce a condensed frame for each selected video. Specifically, FrameMaker is mainly composed of two crucial components: Frame Condensing and Instance-Specific Prompt. The former is to reduce the memory cost by preserving only one condensed frame instead of the whole video, while the latter aims to compensate the lost spatio-temporal details in the Frame Condensing stage. By this means, FrameMaker enables a remarkable reduction in memory but keep enough information that can be applied to following incremental tasks. Experimental results on multiple challenging benchmarks, i.e., HMDB51, UCF101 and Something-Something V2, demonstrate that FrameMaker can achieve better performance to recent advanced methods while consuming only 20% memory. Additionally, under the same memory consumption conditions, FrameMaker significantly outperforms existing state-of-the-arts by a convincing margin.