Provid: Progressive and multimodal vehicle reidentification for large-scale urban surveillance

X Liu, W Liu, T Mei, H Ma - IEEE Transactions on Multimedia, 2017 - ieeexplore.ieee.org
Compared with person reidentification, which has attracted concentrated attention, vehicle
reidentification is an important yet frontier problem in video surveillance and has been …

Unidentified video objects: A benchmark for dense, open-world segmentation

W Wang, M Feiszli, H Wang… - Proceedings of the IEEE …, 2021 - openaccess.thecvf.com
Current state-of-the-art object detection and segmentation methods work well under the
closed-world assumption. This closed-world setting assumes that the list of object categories …

Capdet: Unifying dense captioning and open-world detection pretraining

Y Long, Y Wen, J Han, H Xu, P Ren… - Proceedings of the …, 2023 - openaccess.thecvf.com
Benefiting from large-scale vision-language pre-training on image-text pairs, open-world
detection methods have shown superior generalization ability under the zero-shot or few …

Spatio-temporal person retrieval via natural language queries

M Yamaguchi, K Saito, Y Ushiku… - Proceedings of the …, 2017 - openaccess.thecvf.com
In this paper, we address the problem of spatio-temporal person retrieval from videos using
a natural language query, in which we output a tube (ie, a sequence of bounding boxes) …

Learning attentional recurrent neural network for visual tracking

Q Wang, C Yuan, J Wang… - IEEE Transactions on …, 2018 - ieeexplore.ieee.org
Existing visual tracking methods face many challenges: 1) the changed size and number of
targets over time, occlusion in discrete frames, and mis-identification for crossing targets …

Video big data retrieval over media cloud: A context-aware online learning approach

Y Feng, P Zhou, J Xu, S Ji, D Wu - IEEE transactions on …, 2018 - ieeexplore.ieee.org
Online video sharing (eg, via YouTube or YouKu) has emerged as one of the most important
services in the current Internet, where billions of videos on the cloud are awaiting …

[PDF][PDF] Semantic based video retrieval system: survey

ME Abdulmunem, E Hato - Iraqi Journal of Science, 2018 - iasj.net
In this review paper a number of studies and researches are surveyed, in order to assist the
upcoming researchers, to know about the techniques available in the field of semantic …

Weakly supervised easy-to-hard learning for object detection in image sequences

H Yu, D Guo, Z Yan, L Fu, J Simmons, CP Przybyla… - Neurocomputing, 2020 - Elsevier
Object detection is an important research problem in computer vision. Convolutional Neural
Networks (CNN) based deep learning models could be used for this problem, but it would …

Pixel-level and robust vibration source sensing in high-frame-rate video analysis

M Jiang, T Aoyama, T Takaki, I Ishii - Sensors, 2016 - mdpi.com
We investigate the effect of appearance variations on the detectability of vibration feature
extraction with pixel-level digital filters for high-frame-rate videos. In particular, we consider …

Large‐scale video retrieval via deep local convolutional features

C Zhang, B Hu, Y Suo, Z Zou, Y Ji - Advances in Multimedia, 2020 - Wiley Online Library
In this paper, we study the challenge of image‐to‐video retrieval, which uses the query
image to search relevant frames from a large collection of videos. A novel framework based …