Object Detection from Video Tubelets with Convolutional Neural Networks
arXiv:1604.04053 · doi:10.1109/CVPR.2016.95
Abstract
Deep Convolution Neural Networks (CNNs) have shown impressive performance in various vision tasks such as image classification, object detection and semantic segmentation. For object detection, particularly in still images, the performance has been significantly increased last year thanks to powerful deep networks (e.g. GoogleNet) and detection frameworks (e.g. Regions with CNN features (R-CNN)). The lately introduced ImageNet task on object detection from video (VID) brings the object detection task into the video domain, in which objects' locations at each frame are required to be annotated with bounding boxes. In this work, we introduce a complete framework for the VID task based on still-image object detection and general object tracking. Their relations and contributions in the VID task are thoroughly studied and evaluated. In addition, a temporal convolution network is proposed to incorporate temporal information to regularize the detection results and shows its effectiveness for the task.
arXiv commentAccepted in CVPR 2016 as a Spotlight paper
References in corpus (1)
Cited by in corpus (15)
- GOT-10k: A Large High-Diversity Benchmark for Generic Object Tracking in the Wild
- FairMOT: On the Fairness of Detection and Re-Identification in Multiple Object Tracking
- A Survey of Deep Learning-based Object Detection
- Tracking without bells and whistles
- T-CNN: Tubelets with Convolutional Neural Networks for Object Detection from Videos
- Deep Learning for UAV-based Object Detection and Tracking: A Survey
- A Comprehensive Survey of Scene Graphs: Generation and Application
- Object Detection in Videos with Tubelet Proposal Networks
- Eye in the Sky: Drone-Based Object Tracking and 3D Localization
- YoTube: Searching Action Proposal via Recurrent and Static Regression Networks
- Multi-layered Semantic Representation Network for Multi-label Image Classification
- Towards Balanced Learning for Instance Recognition
- Video Relationship Detection Using Mixture of Experts
- Improving Token-based Object Detection with Video
- Class agnostic moving target detection by color and location prediction of moving area