In this paper we present our approach to the Track 1 of the 2021 AI City Challenge. The goal of the challenge track is to to analyse footage captured with traffic cameras by counting the number of vehicles performing ...
详细信息
ISBN:
(纸本)9781665448994
In this paper we present our approach to the Track 1 of the 2021 AI City Challenge. The goal of the challenge track is to to analyse footage captured with traffic cameras by counting the number of vehicles performing various pre-defined motions of interest. Our approach is based on the CenterTrack object detection and tracking neural network used in conjunction with a simple IoU-based tracking algorithm. In the public evaluation server our system achieved the S1 score of 0.8449 placing it at the 8th place on the public leaderboard.
Recent research has shown that faces can be obfuscated in large-scale datasets with a minimal performance impact on image classification and downstream tasks like object recognition. In this paper, we investigate the ...
详细信息
ISBN:
(纸本)9781665448994
Recent research has shown that faces can be obfuscated in large-scale datasets with a minimal performance impact on image classification and downstream tasks like object recognition. In this paper, we investigate the role of face obfuscation in video classification datasets and quantify a more significant reduction in performance caused by face blurring. To reduce such performance effects, we propose a generalized distillation approach in which a privacy-preserving action recognition network is trained with privileged information given by face identities. We show, through experiments performed on Kinetics-400, that the proposed approach can fully close the performance gap caused by face anonymization.
During the performance optimization of a computervision system, developers frequently run into platform-level inefficiencies and bottlenecks that can not be addressed by traditional methods. OpenVX is designed to add...
详细信息
ISBN:
(纸本)9781479943098
During the performance optimization of a computervision system, developers frequently run into platform-level inefficiencies and bottlenecks that can not be addressed by traditional methods. OpenVX is designed to address such system-level issues by means of a graph-based computation model. This approach differs from the traditional acceleration of one-off functions, and exposes optimization possibilities that might not be available or obvious with traditional computervision libraries such as OpenCV.
We present an approach to perform supervised action recognition in the dark. In this work, we present our results on the ARID dataset[60]. Most previous works only evaluate performance on large, well illuminated datas...
详细信息
ISBN:
(纸本)9781665448994
We present an approach to perform supervised action recognition in the dark. In this work, we present our results on the ARID dataset[60]. Most previous works only evaluate performance on large, well illuminated datasets like Kinetics and HMDB51. We demonstrate that our work is able to achieve a very low error rate while being trained on a much smaller dataset of dark videos. We also explore a variety of training and inference strategies including domain transfer methodologies and also propose a simple but useful frame selection strategy. Our empirical results demonstrate that we beat previously published baseline models by 11%.
Studies were conducted to optimize the chemical composition of the steel and improve its deoxidation and microalloying in order to reduce the consumption of the scarce SiMgTi alloy and improve the properties of railro...
详细信息
Studies were conducted to optimize the chemical composition of the steel and improve its deoxidation and microalloying in order to reduce the consumption of the scarce SiMgTi alloy and improve the properties of railroad rails. Analysis of the effect of titanium on the rails indicates that it produces a small increase in the tensile strength of non-heat-treated rails, while it has a major negative effect on the impact toughness at content above .016%. The feasibility of reducing the consumption of the SiMgTi alloy by addition of a small amount of ferrotitanium to the ladle. This was found to help stabilize the level of oxidation of the metal and reduce damage to the rails by macrostructural defects.
Building footprints (BFP) provide useful visual context for users of digital maps when navigating in space. This paper proposes a method for extracting and symbolizing building footprints from satellite imagery using ...
详细信息
ISBN:
(数字)9781538661000
ISBN:
(纸本)9781538661000
Building footprints (BFP) provide useful visual context for users of digital maps when navigating in space. This paper proposes a method for extracting and symbolizing building footprints from satellite imagery using a convolutional neural network (CNN). The CNN architecture outputs rotated rectangles, providing a symbolized approximation that works well for small buildings. Experiments are conducted on the four cities in the DeepGlobe Challenge dataset (Las Vegas, Paris, Shanghai, Khartoum). Our method performs best on suburbs consisting of individual houses. These experiments show that either large buildings or buildings without clear delineation produce weaker results in terms of precision and recall.
Adversarial Training (AT) is crucial for obtaining deep neural networks that are robust to adversarial attacks, yet recent works found that it could also make models more vulnerable to privacy attacks. In this work, w...
详细信息
ISBN:
(数字)9781665487399
ISBN:
(纸本)9781665487399
Adversarial Training (AT) is crucial for obtaining deep neural networks that are robust to adversarial attacks, yet recent works found that it could also make models more vulnerable to privacy attacks. In this work, we further reveal this unsettling property of AT by designing a novel privacy attack that is practically applicable to the privacy-sensitive Federated Learning (FL) systems. Using our method, the attacker can exploit AT models in the FL system to accurately reconstruct users' private training images even when the training batch size is large. Code is available at https://***/zjysteven/PrivayAttack_AT_FL.
We present a vision-based method for signer diarization - the task of automatically determining "who signed when?" in a video. This task has similar motivations and applications as speaker diarization but ha...
详细信息
ISBN:
(纸本)9780769549903
We present a vision-based method for signer diarization - the task of automatically determining "who signed when?" in a video. This task has similar motivations and applications as speaker diarization but has received little attention in the literature. In this paper, we motivate the problem and propose a method for solving it. The method is based on the hypothesis that signers make more movements than their interlocutors. Experiments on four videos (a total of 1.4 hours and each consisting of two signers) show the applicability of the method. The best diarization error rate (DER) obtained is 0.16.
We describe an efficient method of improving the performance of vision algorithms operating on video streams by reducing the amount of data captured and transferred from image sensors to analysis servers in a data-awa...
详细信息
ISBN:
(纸本)9781728193601
We describe an efficient method of improving the performance of vision algorithms operating on video streams by reducing the amount of data captured and transferred from image sensors to analysis servers in a data-aware manner. The key concept is to combine guided, highly heterogeneous sampling with an intelligent Scene Cache. This enables the system to adapt to spatial and temporal patterns in the scene, thus reducing redundant data capture and processing. A software prototype of our framework running on a general-purpose embedded processor enables superior object detection accuracy (by 56%) at similar energy consumption (slight improvement of 4%) compared to an H.264 hardware accelerator.
The land cover classification task of the DeepGlohe Challenge presents significant obstacles even to state of the art segmentation models due to a small amount of data, incomplete and sometimes incorrect labeling, and...
详细信息
ISBN:
(数字)9781538661000
ISBN:
(纸本)9781538661000
The land cover classification task of the DeepGlohe Challenge presents significant obstacles even to state of the art segmentation models due to a small amount of data, incomplete and sometimes incorrect labeling, and highly imbalanced classes. In this work, we show an approach based on the U-Net architecture with the Lovcisz-Softmax loss that successfully alleviates these problems: we compare several different convolutional architectures for U-Net encoders.
暂无评论