paper-with-me

홈 › Papers

Rethinking Temporal Object Detection from Robotic Perspectives

2019-12-22 · Xingyu Chen, Zhengxing Wu, Junzhi Yu, Li Wen

Video object detection (VID) has been vigorously studied for years but almost all literature adopts a static accuracy-based evaluation, i.e., average precision (AP). From a robotic perspective, the importance of recall continuity and localization stability is equal to that of accuracy, but the AP is insufficient to reflect detectors' performance across time. In this paper, non-reference assessments are proposed for continuity and stability based on object tracklets. These temporal evaluations can serve as supplements to static AP. Further, we develop an online tracklet refinement for improving detectors' temporal performance through short tracklet suppression, fragment filling, and temporal location fusion. In addition, we propose a small-overlap suppression to extend VID methods to single object tracking (SOT) task so that a flexible SOT-by-detection framework is then formed. Extensive experiments are conducted on ImageNet VID dataset and real-world robotic tasks, where the superiority of our proposed approaches are validated and verified. Codes will be publicly available.

📄 PDF Abstract BibTeX arXiv:1912.10406

Code (0)

등록된 구현이 없습니다.

Tasks

Multi-Object TrackingObjectobject-detectionObject DetectionObject TrackingVideo Object Detection

Similar Papers 제목 키워드 기반

3D-MAN: 3D Multi-frame Attention Network for Object Detection

2021-03-30 · CVPR 2021 1 · Zetong Yang, Yin Zhou, Zhifeng Chen, Jiquan Ngiam

3D object detection is an important module in autonomous driving and robotics. However, many existing methods focus on using single frames to perform 3D detection, and do not fully utilize information from multiple frame…

3D Object DetectionAutonomous Drivingobject-detectionObject Detection

TransPillars: Coarse-to-Fine Aggregation for Multi-Frame 3D Object Detection

2022-08-04 · Zhipeng Luo, Gongjie Zhang, Changqing Zhou, Tianrui Liu 외

3D object detection using point clouds has attracted increasing attention due to its wide applications in autonomous driving and robotics. However, most existing studies focus on single point cloud frames without harness…

3D Object DetectionAutonomous DrivingObjectobject-detection+2

Rethinking Progression of Memory State in Robotic Manipulation: An Object-Centric Perspective

2025-11-14 · Nhat Chung, Taisei Hanyu, Toan Nguyen, Huy Le 외 arxiv

As embodied agents operate in increasingly complex environments, the ability to perceive, track, and reason about individual object instances over time becomes essential, especially in tasks requiring sequenced interacti…

Object Tracking

DetZero: Rethinking Offboard 3D Object Detection with Long-term Sequential Point Clouds

2023-06-09 · ICCV 2023 1 · Tao Ma, Xuemeng Yang, Hongbin Zhou, Xin Li 외

Existing offboard 3D detectors always follow a modular pipeline design to take advantage of unlimited sequential point clouds. We have found that the full potential of offboard 3D detectors is not explored mainly due to …

3D Multi-Object Tracking3D Object DetectionObjectobject-detection+1

Rethinking the Defocus Blur Detection Problem and A Real-Time Deep DBD Model

2020-08-01 · ECCV 2020 8 · Ning Zhang, Junchi Yan

Defocus blur detection (DBD) is a classical low level vision task. It has recently attracted attention focusing on designing complex convolutional neural networks (CNN) which make full use of both low level features and …

Data AugmentationDefocus Blur Detection