Saved in:
Bibliographic Details
Main Authors: Lee, Junho, Shin, Jeongwoo, Ko, Seung Woo, Ha, Seongsu, Lee, Joonseok
Format: Preprint
Published: 2024
Subjects:
Online Access:https://arxiv.org/abs/2409.05260
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866915561979510784
author Lee, Junho
Shin, Jeongwoo
Ko, Seung Woo
Ha, Seongsu
Lee, Joonseok
author_facet Lee, Junho
Shin, Jeongwoo
Ko, Seung Woo
Ha, Seongsu
Lee, Joonseok
contents Given a video with $T$ frames, frame sampling is a task to select $N \ll T$ frames, so as to maximize the performance of a fixed video classifier. Not just brute-force search, but most existing methods suffer from its vast search space of $\binom{T}{N}$, especially when $N$ gets large. To address this challenge, we introduce a novel perspective of reducing the search space from $O(T^N)$ to $O(T)$. Instead of exploring the entire $O(T^N)$ space, our proposed semi-optimal policy selects the top $N$ frames based on the independently estimated value of each frame using per-frame confidence, significantly reducing the computational complexity. We verify that our semi-optimal policy can efficiently approximate the optimal policy, particularly under practical settings. Additionally, through extensive experiments on various datasets and model architectures, we demonstrate that learning our semi-optimal policy ensures stable and high performance regardless of the size of $N$ and $T$.
format Preprint
id arxiv_https___arxiv_org_abs_2409_05260
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Scalable Frame Sampling for Video Classification: A Semi-Optimal Policy Approach with Reduced Search Space
Lee, Junho
Shin, Jeongwoo
Ko, Seung Woo
Ha, Seongsu
Lee, Joonseok
Computer Vision and Pattern Recognition
Given a video with $T$ frames, frame sampling is a task to select $N \ll T$ frames, so as to maximize the performance of a fixed video classifier. Not just brute-force search, but most existing methods suffer from its vast search space of $\binom{T}{N}$, especially when $N$ gets large. To address this challenge, we introduce a novel perspective of reducing the search space from $O(T^N)$ to $O(T)$. Instead of exploring the entire $O(T^N)$ space, our proposed semi-optimal policy selects the top $N$ frames based on the independently estimated value of each frame using per-frame confidence, significantly reducing the computational complexity. We verify that our semi-optimal policy can efficiently approximate the optimal policy, particularly under practical settings. Additionally, through extensive experiments on various datasets and model architectures, we demonstrate that learning our semi-optimal policy ensures stable and high performance regardless of the size of $N$ and $T$.
title Scalable Frame Sampling for Video Classification: A Semi-Optimal Policy Approach with Reduced Search Space
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2409.05260