paper-with-me

홈 › Papers

Marking anything: application of point cloud in extracting video target features

2023-06-13 · Xiangchun Xu

Extracting retrievable features from video is of great significance for structured video database construction, video copyright protection and fake video rumor refutation. Inspired by point cloud data processing, this paper proposes a method for marking anything (MA) in the video, which can extract the contour features of any target in the video and convert it into a feature vector with a length of 256 that can be retrieved. The algorithm uses YOLO-v8 algorithm, multi-object tracking algorithm and PointNet++ to extract contour of the video detection target to form spatial point cloud data. Then extract the point cloud feature vector and use it as the retrievable feature of the video detection target. In order to verify the effectiveness and robustness of contour feature, some datasets are crawled from Dou Yin and Kinetics-700 dataset as experimental data. For Dou Yin's homogenized videos, the proposed contour features achieve retrieval accuracy higher than 97% in Top1 return mode. For videos from Kinetics 700, the contour feature also showed good robustness for partial clip mode video tracing.

📄 PDF Abstract BibTeX arXiv:2306.07559

Code (0)

등록된 구현이 없습니다.

Tasks

Multi-Object TrackingObject TrackingRetrieval

Methods 이 논문이 사용한 방법론

CLIP Contrastive Language-Image Pre-training (CLIP), consisting of a simplified version of ConVIRT trained from scratch, is an efficient method of image representation learning…

Similar Papers 제목 키워드 기반

Language-Driven 6-DoF Grasp Detection Using Negative Prompt Guidance

2024-07-18 · Toan Nguyen, Minh Nhat Vu, Baoru Huang, An Vuong 외

6-DoF grasp detection has been a fundamental and challenging problem in robotic vision. While previous works have focused on ensuring grasp stability, they often do not consider human intention conveyed through natural l…

Benchmarking

PrintAnything: Learning an Intermediate Representation for 3D printing G-code Generation

2026-07-30 · Sangmin Hong, Daniel Sungho Jung, Heewon Kim, Kyoung Mu Lee arxiv

Point clouds are one of the most fundamental and widely used 3D representations, serving as the most basic geometric representation of 3D shapes. Nevertheless, most existing 3D printing pipelines require a watertight mes…

Code GenerationPoint Clouds

VFMM3D: Releasing the Potential of Image by Vision Foundation Model for Monocular 3D Object Detection

2024-04-15 · Bonan Ding, Jin Xie, Jing Nie, Jiale Cao 외

Due to its cost-effectiveness and widespread availability, monocular 3D object detection, which relies solely on a single camera during inference, holds significant importance across various applications, including auton…

3D Object DetectionAutonomous DrivingMonocular 3D Object DetectionObject+2

SAM3D: Segment Anything in 3D Scenes

2023-06-06 · Yunhan Yang, Xiaoyang Wu, Tong He, Hengshuang Zhao 외

In this work, we propose SAM3D, a novel framework that is able to predict masks in 3D point clouds by leveraging the Segment-Anything Model (SAM) in RGB images without further training or finetuning. For a point cloud of…

Segmentation

Point-SAM: Promptable 3D Segmentation Model for Point Clouds

2024-06-25 · Yuchen Zhou, Jiayuan Gu, Tung Yen Chiang, Fanbo Xiang 외

The development of 2D foundation models for image segmentation has been significantly advanced by the Segment Anything Model (SAM). However, achieving similar success in 3D models remains a challenge due to issues such a…

Image SegmentationSegmentationSemantic Segmentation