Filters








13,151 Hits in 4.0 sec

Object Detection in Video with Spatiotemporal Sampling Networks [article]

Gedas Bertasius, Lorenzo Torresani, Jianbo Shi
2018 arXiv   pre-print
We propose a Spatiotemporal Sampling Network (STSN) that uses deformable convolutions across time for object detection in videos.  ...  Our STSN performs object detection in a video frame by learning to spatially sample features from the adjacent frames.  ...  Spatiotemporal Sampling Network Our goal is to design a network architecture that incorporates temporal information for object detection in video.  ... 
arXiv:1803.05549v2 fatcat:vn6admrzn5akvdzgci4gxu4nxq

Object Detection in Video with Spatiotemporal Sampling Networks [chapter]

Gedas Bertasius, Lorenzo Torresani, Jianbo Shi
2018 Lecture Notes in Computer Science  
We propose a Spatiotemporal Sampling Network (STSN) that uses deformable convolutions across time for object detection in videos.  ...  Our STSN performs object detection in a video frame by learning to spatially sample features from the adjacent frames.  ...  Spatiotemporal Sampling Network Our goal is to design a network architecture that incorporates temporal information for object detection in video.  ... 
doi:10.1007/978-3-030-01258-8_21 fatcat:zgwtfbunevh2jlhczscryrytsi

Semi-supervised 3D Object Detection via Temporal Graph Neural Networks [article]

Jianren Wang, Haiming Gang, Siddarth Ancha, Yi-Ting Chen, David Held
2022 arXiv   pre-print
We learn to perform this temporal reasoning with a graph neural network, where edges represent the relationship between candidate detections in different time frames.  ...  3D object detection plays an important role in autonomous driving and other robotics applications.  ...  We propose a novel framework for semi-supervised 3D object detection by leveraging the rich spatiotemporal information in 3D point cloud videos. 2.  ... 
arXiv:2202.00182v1 fatcat:n7fptukzh5aabhvsrhtaj4ufle

Video Saliency Detection by 3D Convolutional Neural Networks [chapter]

Guanqun Ding, Yuming Fang
2018 Communications in Computer and Information Science  
In this paper, we present a novel and effective approach for salient object detection for video sequences based on 3D convolutional neural networks.  ...  First, we design a 3D convolutional network (Conv3DNet) with the input as three video frame to learn the spatiotemporal features for video sequences.  ...  Conclusion In this paper, a novel salient object detection approach with 3D convolutional neural networks is proposed to effectively learn semantic and spatiotemporal features for video sequences.  ... 
doi:10.1007/978-981-10-8108-8_23 fatcat:s447mvmueze73hqw6mbh7s5jky

Weakly Supervised Salient Object Detection with Spatiotemporal Cascade Neural Networks

Yi Tang, Wenbin Zou, Zhi Jin, Yuhuan Chen, Yang Hua, Xia Li
2018 IEEE transactions on circuits and systems for video technology (Print)  
However, the salient object detection in videos by using traditional handcrafted features or deep learning features is not fully investigated, probably due to the lack of sufficient manually labeled video  ...  Furthermore, we propose a spatiotemporal cascade neural network (SCNN) architecture for saliency modeling, in which two fully convolutional networks are cascaded to evaluate visual saliency from both spatial  ...  CONCLUSION In this paper, we propose a novel SCNN for salient object detection in a video.  ... 
doi:10.1109/tcsvt.2018.2859773 fatcat:l2m646l5m5a6bo4f2dgevffwlm

Spatiotemporal Multi-Task Network for Human Activity Understanding

Yao Liu, Jianqiang Huang, Chang Zhou, Deng Cai, Xian-Sheng Hua
2017 Proceedings of the on Thematic Workshops of ACM Multimedia 2017 - Thematic Workshops '17  
To tackle these problems, we propose a spatiotemporal, multi-task, 3D deep convolutional neural network to detect (including temporally localize and recognition) actions in untrimmed videos.  ...  Meanwhile, in order to better utilize the rich motion information in videos, we introduce a novel video representation, interlaced images, as an additional network input stream.  ...  For object detection in still images, the couvolutional neural networks provide better features compare with traditional hand-craft features, and achieve impressive performance.  ... 
doi:10.1145/3126686.3126705 dblp:conf/mm/LiuHZCH17 fatcat:vauwsk6ndbd7fhxhel3swqf4fq

Cross Complementary Fusion Network for Video Salient Object Detection

Ziyang Wang, Junxia Li, Zefeng Pan
2020 IEEE Access  
for video salient object detection. 2) Visual Comparison 3) Runtime Comparison We compare our video saliency detection network with optical flow based methods and all methods in runtime cost respectively  ...  ViSal is the first dataset designed for video object detection task and contains 17 video sequences with obvious objects.  ...  His current research interests include static image saliency detection and video saliency detection.  ... 
doi:10.1109/access.2020.3036533 fatcat:34wvxqukvvaa3lsl2prao4gaay

Video Salient Object Detection via Spatiotemporal Attention Neural Networks

Yi Tang, Wenbin Zou, Yang Hua, Zhi Jin, Xia Li
2019 Neurocomputing  
Conclusion In this paper, we propose a novel spatiotemporal attention neural network for video salient objects detection.  ...  attention neural network for video salient objects detection.  ... 
doi:10.1016/j.neucom.2019.09.064 fatcat:hmmvekkitbhz7ludfmy2fc6k34

Learning Future Object Prediction with a Spatiotemporal Detection Transformer [article]

Adam Tonderski, Joakim Johnander, Christoffer Petersson, Kalle Åström
2022 arXiv   pre-print
We explore future object prediction -- a challenging problem where all objects visible in a future video frame are to be predicted.  ...  We extend existing detection transformers in two ways to capture the scene dynamics.  ...  Duke et al . [11] experiments with spatiotemporal self-attention for video object segmentation (VOS), and propose to use local attention to reduce computational cost in long videos.  ... 
arXiv:2204.10321v1 fatcat:35bkglo3xvf6lkdochxr3idkuq

Deep Vehicle Detection in Satellite Video [article]

Roman Pflugfelder and Axel Weissenfeld and Julian Wagner
2022 arXiv   pre-print
This work presents a deep learning approach for vehicle detection in satellite video.  ...  A new spatiotemporal model of a compact 3 × 3 convolutional, neural network is proposed which neglects pooling layers and uses leaky ReLUs.  ...  for tiny object detection.  ... 
arXiv:2204.06828v2 fatcat:kz3zesrf6bbfvhx6rlivt3dwge

Video Salient Object Detection via Fully Convolutional Networks

Wenguan Wang, Jianbing Shen, Ling Shao
2018 IEEE Transactions on Image Processing  
This paper proposes a deep learning model to efficiently detect salient regions in videos.  ...  It addresses two important issues: (1) deep video saliency model training with the absence of sufficiently large and pixel-wise annotated video data, and (2) fast video saliency training and detection.  ...  In this work, we aim at detecting saliency object regions in videos.  ... 
doi:10.1109/tip.2017.2754941 pmid:28945593 fatcat:v644yvm4qjag5l5ri5lq7ztwee

Spatiotemporal representation learning for video anomaly detection

Zhaoyan Li, Yaoshun Li, Zhisheng Gao
2020 IEEE Access  
INDEX TERMS Spatiotemporal representation learning, anomaly detection, 3D convolutional neural network, mixed Gaussian model.  ...  Video-based anomalous human behavior detection is widely studied in many fields such as security, medical care, education, and energy.  ...  In video anomaly detection, behaviors that differ from the majority of behaviors in the scene are treated as anomalies, reflected as unusual object shapes, poses, and motions.  ... 
doi:10.1109/access.2020.2970497 fatcat:tlaxd6pxxngczkvzm3sz3aqcvu

LiDAR-based Online 3D Video Object Detection with Graph-based Message Passing and Spatiotemporal Transformer Attention [article]

Junbo Yin, Jianbing Shen, Chenye Guan, Dingfu Zhou, Ruigang Yang
2020 arXiv   pre-print
Existing LiDAR-based 3D object detectors usually focus on the single-frame detection, while ignoring the spatiotemporal information in consecutive point cloud frames.  ...  In this paper, we propose an end-to-end online 3D video object detector that operates on point cloud sequences.  ...  Conclusion This paper proposed a new 3D video object detector for exploring the spatiotemporal information in point cloud video.  ... 
arXiv:2004.01389v1 fatcat:i46zosrmynabrl66egkeqnrr64

Single-Object Tracking Algorithm Based on Two-Step Spatiotemporal Deep Feature Fusion in a Complex Surveillance Scenario

Yanyan Chen, Rui Sheng, Yi-Zhang Jiang
2021 Mathematical Problems in Engineering  
In this paper, an effective single-object tracking algorithm based on two-step spatiotemporal feature fusion is proposed, which combines deep learning detection with the kernelized correlation filtering  ...  In addition, the improved KCF algorithm is adopted to track and calculate the temporal information correlation of gradient features between video frames, so as to reduce the probability of missing detection  ...  Mathematical Problems in Engineering Object Detection and Tracking for Spatiotemporal Fusion.  ... 
doi:10.1155/2021/6653954 fatcat:6tkewtczybg2zljxxngdpla7su

Learning Video Salient Object Detection Progressively from Unlabeled Videos [article]

Binwei Xu, Haoran Liang, Wentian Ni, Weihua Gong, Ronghua Liang, Peng Chen
2022 arXiv   pre-print
Recent deep learning-based video salient object detection (VSOD) has achieved some breakthrough, but these methods rely on expensive annotated videos with pixel-wise annotations, weak annotations, or part  ...  salient objects in sequence without utilizing any video annotation.  ...  Compared with locating salient objects in images, detecting salient objects in videos is different. Temporal information can be a critical cue for identifying the salient objects in videos.  ... 
arXiv:2204.02008v1 fatcat:p6g6hkg3vveupmo3tzdikzxezi
« Previous Showing results 1 — 15 out of 13,151 results