# Sample Less, Learn More: Efficient Action Recognition via Frame Feature Restoration

Source: [Sample Less, Learn More: Efficient Action Recognition via Frame Feature Restoration](<https://www.sota2.com/research/paper/68fa702a1e209131cea49891>)

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

Data updated: 2025-10-26T01:35:15.802Z

Authors: Harry Cheng, Yangyang Guo, Liqiang Nie, Zhiyong Cheng, Mohan Kankanhalli

Published: 2023-07-27T13:52:42.000Z

## Abstract

Training an effective video action recognition model poses significant computational challenges, particularly under limited resource budgets. Current methods primarily aim to either reduce model size or utilize pre-trained models, limiting their adaptability to various backbone architectures. This paper investigates the issue of over-sampled frames, a prevalent problem in many approaches yet it has received relatively little attention. Despite the use of fewer frames being a potential solution, this approach often results in a substantial decline in performance. To address this issue, we propose a novel method to restore the intermediate features for two sparsely sampled and adjacent video frames. This feature restoration technique brings a negligible increase in computational requirements compared to resource-intensive image encoders, such as ViT. To evaluate the effectiveness of our method, we conduct extensive experiments on four public datasets, including Kinetics-400, ActivityNet, UCF-101, and HMDB-51. With the integration of our method, the efficiency of three commonly used baselines has been improved by over 50%, with a mere 0.5% reduction in recognition accuracy. In addition, our method also surprisingly helps improve the generalization ability of the models under zero-shot settings.

## 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/2307.14866>)

[PDF](<https://arxiv.org/pdf/2307.14866.pdf>)
