# Tube-CNN: Modeling temporal evolution of appearance for object detection in video

Source: [Tube-CNN: Modeling temporal evolution of appearance for object detection in video](<https://www.sota2.com/research/paper/68fa65301e209131cea08b73>)

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

Data updated: 2025-10-25T21:20:52.699Z

Authors: Tuan-Hung Vu, Anton Osokin, Ivan Laptev

Published: 2018-12-06T15:48:54.000Z

## Abstract

Object detection in video is crucial for many applications. Compared to images, video provides additional cues which can help to disambiguate the detection problem. Our goal in this paper is to learn discriminative models for the temporal evolution of object appearance and to use such models for object detection. To model temporal evolution, we introduce space-time tubes corresponding to temporal sequences of bounding boxes. We propose two CNN architectures for generating and classifying tubes, respectively. Our tube proposal network (TPN) first generates a large number of spatio-temporal tube proposals maximizing object recall. The Tube-CNN then implements a tube-level object detector in the video. Our method improves state of the art on two large-scale datasets for object detection in video: HollywoodHeads and ImageNet VID. Tube models show particular advantages in difficult dynamic scenes.

## 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/1812.02619>)

[PDF](<https://arxiv.org/pdf/1812.02619.pdf>)