# Detect or Track: Towards Cost-Effective Video Object Detection/Tracking

Source: [Detect or Track: Towards Cost-Effective Video Object Detection/Tracking](<https://www.sota2.com/research/paper/68fa65171e209131cea083d2>)

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

Data updated: 2025-10-28T13:56:37.357Z

Authors: Hao Luo, Wenxuan Xie, Xinggang Wang, Wenjun Zeng

Published: 2018-11-13T14:44:10.000Z

## Abstract

State-of-the-art object detectors and trackers are developing fast. Trackers are in general more efficient than detectors but bear the risk of drifting. A question is hence raised -- how to improve the accuracy of video object detection/tracking by utilizing the existing detectors and trackers within a given time budget? A baseline is frame skipping -- detecting every N-th frames and tracking for the frames in between. This baseline, however, is suboptimal since the detection frequency should depend on the tracking quality. To this end, we propose a scheduler network, which determines to detect or track at a certain frame, as a generalization of Siamese trackers. Although being light-weight and simple in structure, the scheduler network is more effective than the frame skipping baselines and flow-based approaches, as validated on ImageNet VID dataset in video object detection/tracking.

## 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/1811.05340>)

[PDF](<https://arxiv.org/pdf/1811.05340.pdf>)