English
Related papers

Related papers: DFA: Dynamic Feature Aggregation for Efficient Vid…

200 papers

Dataset distillation aims to synthesize compact yet informative datasets that allow models trained on them to achieve performance comparable to training on the full dataset. While this approach has shown promising results for image data,…

Computer Vision and Pattern Recognition · Computer Science 2025-12-17 Zhenghao Zhao , Haoxuan Wang , Kai Wang , Yuzhang Shang , Yuan Hong , Yan Yan

Current video object detection (VOD) models often encounter issues with over-aggregation due to redundant aggregation strategies, which perform feature aggregation on every frame. This results in suboptimal performance and increased…

Computer Vision and Pattern Recognition · Computer Science 2023-08-23 Bingqing Zhang , Sen Wang , Yifan Liu , Brano Kusy , Xue Li , Jiajun Liu

State-of-the-art video object detection methods maintain a memory structure, either a sliding window or a memory queue, to enhance the current frame using attention mechanisms. However, we argue that these memory structures are not…

Computer Vision and Pattern Recognition · Computer Science 2024-02-02 Guanxiong Sun , Yang Hua , Guosheng Hu , Neil Robertson

Since the wide employment of deep learning frameworks in video salient object detection, the accuracy of the recent approaches has made stunning progress. These approaches mainly adopt the sequential modules, based on optical flow or…

Computer Vision and Pattern Recognition · Computer Science 2021-03-18 Yi Tang , Yuanman Li , Wenbin Zou

The 2D object detection in clean images has been a well studied topic, but its vulnerability against adversarial attack is still worrying. Existing work has improved robustness of object detectors by adversarial training, at the same time,…

Computer Vision and Pattern Recognition · Computer Science 2021-08-27 Weipeng Xu , Hongcheng Huang , Shaoyou Pan

Object detection has achieved promising performance on clean datasets, but how to achieve better tradeoff between the adversarial robustness and clean precision is still under-explored. Adversarial training is the mainstream method to…

Computer Vision and Pattern Recognition · Computer Science 2022-10-20 Weipeng Xu , Pengzhi Chu , Renhao Xie , Xiongziyan Xiao , Hongcheng Huang

This paper aims to learn a compact representation of a video for video face recognition task. We make the following contributions: first, we propose a meta attention-based aggregation scheme which adaptively and fine-grained weighs the…

Computer Vision and Pattern Recognition · Computer Science 2019-09-13 Zhaoxiang Liu , Huan Hu , Jinqiang Bai , Shaohua Li , Shiguo Lian

Significant progress has been made in Video Object Segmentation (VOS), the video object tracking task in its finest level. While the VOS task can be naturally decoupled into image semantic segmentation and video object tracking,…

Computer Vision and Pattern Recognition · Computer Science 2020-07-14 Xuhua Huang , Jiarui Xu , Yu-Wing Tai , Chi-Keung Tang

A significant amount of redundancy exists between consecutive frames of a video. Object detectors typically produce detections for one image at a time, without any capabilities for taking advantage of this redundancy. Meanwhile, many…

Computer Vision and Pattern Recognition · Computer Science 2021-09-16 Hughes Perreault , Guillaume-Alexandre Bilodeau , Nicolas Saunier , Maguelonne Héritier

Video-based person recognition is challenging due to persons being blocked and blurred, and the variation of shooting angle. Previous research always focused on person recognition on still images, ignoring similarity and continuity between…

Computer Vision and Pattern Recognition · Computer Science 2021-01-01 Fangtao Li , Wenzhe Wang , Zihe Liu , Haoran Wang , Chenghao Yan , Bin Wu

Knowledge distillation has become increasingly important in model compression. It boosts the performance of a miniaturized student network with the supervision of the output distribution and feature maps from a sophisticated teacher…

Machine Learning · Computer Science 2020-08-04 Yushuo Guan , Pengyu Zhao , Bingxuan Wang , Yuanxing Zhang , Cong Yao , Kaigui Bian , Jian Tang

The primary challenge in Video Object Detection (VOD) is effectively exploiting temporal information to enhance object representations. Traditional strategies, such as aggregating region proposals, often suffer from feature variance due to…

Computer Vision and Pattern Recognition · Computer Science 2024-12-09 Khurram Azeem Hashmi , Talha Uddin Sheikh , Didier Stricker , Muhammad Zeshan Afzal

LiDAR-based sparse 3D object detection plays a crucial role in autonomous driving applications due to its computational efficiency advantages. Existing methods either use the features of a single central voxel as an object proxy, or treat…

Computer Vision and Pattern Recognition · Computer Science 2024-06-18 Lin Liu , Ziying Song , Qiming Xia , Feiyang Jia , Caiyan Jia , Lei Yang , Hongyu Pan

Input aggregation is a simple technique used by state-of-the-art LiDAR 3D object detectors to improve detection. However, increasing aggregation is known to have diminishing returns and even performance degradation, due to objects…

Computer Vision and Pattern Recognition · Computer Science 2024-11-21 Chengjie Huang , Vahdat Abdelzad , Sean Sedwards , Krzysztof Czarnecki

Recent works on salient object detection have made use of multi-scale features in a way such that high-level features and low-level features can collaborate in locating salient objects. Many of the previous methods have achieved great…

Computer Vision and Pattern Recognition · Computer Science 2022-11-15 Xiaogang Liu Shuang Song

This paper aims to accelerate video stream processing, such as object detection and semantic segmentation, by leveraging the temporal redundancies that exist between video frames. Instead of propagating and warping features using motion…

Computer Vision and Pattern Recognition · Computer Science 2022-03-21 Amirhossein Habibian , Haitam Ben Yahia , Davide Abati , Efstratios Gavves , Fatih Porikli

Point clouds and RGB images are two general perceptional sources in autonomous driving. The former can provide accurate localization of objects, and the latter is denser and richer in semantic information. Recently, AutoAlign presents a…

Computer Vision and Pattern Recognition · Computer Science 2022-07-22 Zehui Chen , Zhenyu Li , Shiquan Zhang , Liangji Fang , Qinhong Jiang , Feng Zhao

Optical flow, which expresses pixel displacement, is widely used in many computer vision tasks to provide pixel-level motion information. However, with the remarkable progress of the convolutional neural network, recent state-of-the-art…

Computer Vision and Pattern Recognition · Computer Science 2021-11-11 Ruibing Jin , Guosheng Lin , Changyun Wen , Jianliang Wang , Fayao Liu

Transferring image-based object detectors to the domain of videos remains a challenging problem. Previous efforts mostly exploit optical flow to propagate features across frames, aiming to achieve a good trade-off between accuracy and…

Computer Vision and Pattern Recognition · Computer Science 2019-08-19 Chaoxu Guo , Bin Fan , Jie Gu , Qian Zhang , Shiming Xiang , Veronique Prinet , Chunhong Pan

Video objection detection is a challenging task because isolated video frames may encounter appearance deterioration, which introduces great confusion for detection. One of the popular solutions is to exploit the temporal information and…

Computer Vision and Pattern Recognition · Computer Science 2021-08-13 Yiming Cui , Liqi Yan , Zhiwen Cao , Dongfang Liu