# Temporal Sequence Distillation: Towards Few-Frame Action Recognition in Videos

Source: [Temporal Sequence Distillation: Towards Few-Frame Action Recognition in Videos](<https://www.sota2.com/research/paper/68fa64c01e209131cea064aa>)

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

Data updated: 2025-10-25T21:10:58.701Z

Authors: Zhaoyang Zhang, Zhanghui Kuang, Ping Luo, Litong Feng, Wei Zhang

Published: 2018-08-15T13:59:00.000Z

## Abstract

Video Analytics Software as a Service (VA SaaS) has been rapidly growing in recent years. VA SaaS is typically accessed by users using a lightweight client. Because the transmission bandwidth between the client and cloud is usually limited and expensive, it brings great benefits to design cloud video analysis algorithms with a limited data transmission requirement. Although considerable research has been devoted to video analysis, to our best knowledge, little of them has paid attention to the transmission bandwidth limitation in SaaS. As the first attempt in this direction, this work introduces a problem of few-frame action recognition, which aims at maintaining high recognition accuracy, when accessing only a few frames during both training and test. Unlike previous work that processed dense frames, we present Temporal Sequence Distillation (TSD), which distills a long video sequence into a very short one for transmission. By end-to-end training with 3D CNNs for video action recognition, TSD learns a compact and discriminative temporal and spatial representation of video frames. On Kinetics dataset, TSD+I3D typically requires only 50\\% of the number of frames compared to I3D, a state-of-the-art video action recognition algorithm, to achieve almost the same accuracies. The proposed TSD has three appealing advantages. Firstly, TSD has a lightweight architecture and can be deployed in the client, eg. mobile devices, to produce compressed representative frames to save transmission bandwidth. Secondly, TSD significantly reduces the computations to run video action recognition with compressed frames on the cloud, while maintaining high recognition accuracies. Thirdly, TSD can be plugged in as a preprocessing module of any existing 3D CNNs. Extensive experiments show the effectiveness and characteristics of TSD.

## 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/1808.05085>)

[PDF](<https://arxiv.org/pdf/1808.05085.pdf>)
