Optimizing queries over video via lightweight keypoint-based object detection

J Dong, J Yuan, L Li, X Zhong, W Liu - Proceedings of the 2020 …, 2020 - dl.acm.org
Recent advancements in convolutional neural networks based object detection have
enabled analyzing the mounting video data with high accuracy. However, inference speed is …

Feature aggregated queries for transformer-based video object detectors

Y Cui - Proceedings of the IEEE/CVF Conference on …, 2023 - openaccess.thecvf.com
Video object detection needs to solve feature degradation situations that rarely happen in
the image domain. One solution is to use the temporal information and fuse the features from …

Faq: Feature aggregated queries for transformer-based video object detectors

Y Cui, L Yang - arXiv preprint arXiv:2303.08319, 2023 - arxiv.org
Video object detection needs to solve feature degradation situations that rarely happen in
the image domain. One solution is to use the temporal information and fuse the features from …

Queryprop: Object query propagation for high-performance video object detection

F He, N Gao, J Jia, X Zhao, K Huang - Proceedings of the AAAI …, 2022 - ojs.aaai.org
Video object detection has been an important yet challenging topic in computer vision.
Traditional methods mainly focus on designing the image-level or box-level feature …

Video object detection via object-level temporal aggregation

CH Yao, C Fang, X Shen, Y Wan, MH Yang - Computer Vision–ECCV …, 2020 - Springer
While single-image object detectors can be naively applied to videos in a frame-by-frame
fashion, the prediction is often temporally inconsistent. Moreover, the computation can be …

[PDF][PDF] Ensembling Object Detectors for Effective Video Query Processing

D Chao, N Koudas, X Yu, Y Chen - 2025 - openproceedings.org
Object detection is the foundation of video query processing systems, which have been the
subject of active research in recent years. Compared to the use of a single model, model …

Pack and detect: Fast object detection in videos using region-of-interest packing

AR Kumar, B Ravindran, A Raghunathan - Proceedings of the ACM …, 2019 - dl.acm.org
Object detection in videos is an important task in computer vision for various applications
such as object tracking, video summarization and video search. Although great progress has …

Video object detection using motion context and feature aggregation

J Kim, J Koh, JW Choi - 2020 International Conference on …, 2020 - ieeexplore.ieee.org
The deep learning technique has recently led to significant improvement in object-detection
accuracy. Numerous object detection schemes have been designed to process each frame …

Temporal early exits for efficient video object detection

A Sabet, J Hare, B Al-Hashimi, GV Merrett - arXiv preprint arXiv …, 2021 - arxiv.org
Transferring image-based object detectors to the domain of video remains challenging
under resource constraints. Previous efforts utilised optical flow to allow unchanged features …

Context matters: Refining object detection in video with recurrent neural networks

S Tripathi, ZC Lipton, S Belongie, T Nguyen - arXiv preprint arXiv …, 2016 - arxiv.org
Given the vast amounts of video available online, and recent breakthroughs in object
detection with static images, object detection in video offers a promising new frontier …