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

arXiv: https://arxiv.org/abs/1812.02619 · HTML: https://mlsanity.com/paper/1812.02619/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 6 Dec 2018.

## Built on by (most cited first, 2 of 2)

- [Motion-Grounded Video Reasoning: Understanding and Perceiving Motion at Pixel Level](https://mlsanity.com/paper/2411.09921/) (2024)
- [On Occlusions in Video Action Detection: Benchmark Datasets And Training Recipes](https://mlsanity.com/paper/2410.19553/) (2024)

## Abstract (arXiv)

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.