Video classification and retrieval through spatio-temporal Radon features

Sasithradevi, A.; Roomi, S. Mohamed Mansoor

doi:10.1016/j.patcog.2019.107099

Cited by 19 publications

(5 citation statements)

References 15 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…As discussed earlier, the authors designed STIP-based techniques to improve the robustness in the continuous images and reduce feature extraction time. For visual feature extraction, rather than using the typical process of face detection, landmark points extraction, head-pose motion detection, the authors proposed the STIP detection-based techniques to develop robustness and decrease the time for feature extraction only the driver's inside the video [16,32]. The proposed STIP for tracking the driver's movements is designed in which the filtering method is used to extract the STIPs from the input videos for noise removal.…”

Section: Methodsmentioning

confidence: 99%

See 1 more Smart Citation

ADMT: Advanced Driver’s Movement Tracking System Using Spatio-Temporal Interest Points and Maneuver Anticipation Using Deep Neural Networks

et al. 2021

View full text Add to dashboard Cite

Assistive driving is a complex engineering problem and is influenced by several factors such as the sporadic nature of the quality of the environment, the response of the driver, and the standard of the roads on which the vehicle is being driven. The authors track the driver's anticipation based on his head movements using Spatio-Temporal Interest Point (STIP) extraction and enhance the anticipation of action accuracy well before using the RNN-LSTM framework. This research tries to tackle a fundamental problem of lane change assistance by developing a novel model called Advanced Driver's Movement Tracking (ADMT). ADMT uses customized convolution-based deep learning networks by using Recurrent Convolutional Neural Network (RCNN). STIP with eye gaze extraction and RCNN performed in ADMT on brain4cars dataset for driver movement tracking. Its performance is compared with the traditional machine learning and deep learning models, namely Support Vector Machines (SVM), Hidden Markov Model (HMM), Convolutional Neural Networks (CNN), Recurrent Neural Networks (RNN), Long Short-Term Memory (LSTM) and provided an increment of almost 12% in the prediction accuracy and 44% in the anticipation time. ADMT systems outperformed all of the models in terms of both the accuracy of the system and the previously mentioned time of anticipation that is discussed at length in the paper. Thus it assists the driver with additional anticipation time to access the typical reaction time for better preparedness to respond to undesired future behavior. The driver is then assured of a safe and assisted driving experience with the proposed system. INDEX TERMS RCNN; advanced driver movement tracking system, spatio-temporal interest points, eye gaze tracking, deep neural networks.

show abstract

Section: Methodsmentioning

confidence: 99%

“…However, Spatio-temporal action recognition has problems like tracking the action in a video, object or action localization [32]. Action localization becomes more challenging with the temporal dimension [33].…”

Section: Spatio-temporal Action Recognitionmentioning

confidence: 99%

ADMT: Advanced Driver’s Movement Tracking System Using Spatio-Temporal Interest Points and Maneuver Anticipation Using Deep Neural Networks

et al. 2021

View full text Add to dashboard Cite

show abstract

“…[10] proposed to leverage pupillary response to estimate video taggings. [26] proposed to use the users' multiple physiological responses for video emotion tagging while [22] suggested to extract spatio-temporal Radon features from the video for the tagging task. [35] proposed to integrate the user behavior and content information for the task.…”

Section: Related Workmentioning

confidence: 99%

Multimodal Feature Fusion for Video Advertisements Tagging Via Stacking Ensemble

Zhou,

Liang,

Lin

et al. 2021

Preprint

View full text Add to dashboard Cite

Automated tagging of video advertisements has been a critical yet challenging problem, and it has drawn increasing interests in last years as its applications seem to be evident in many fields. Despite sustainable efforts have been made, the tagging task is still suffered from several challenges, such as, efficiently feature fusion approach is desirable, but under-explored in previous studies. In this paper, we present our approach for Multimodal Video Ads Tagging in the 2021 Tencent Advertising Algorithm Competition. Specifically, we propose a novel multi-modal feature fusion framework, with the goal to combine complementary information from multiple modalities. This framework introduces stacking-based ensembling approach to reduce the influence of varying levels of noise and conflicts between different modalities. Thus, our framework can boost the performance of the tagging task, compared to previous methods. To empirically investigate the effectiveness and robustness of the proposed framework, we conduct extensive experiments on the challenge datasets. The obtained results suggest that our framework can significantly outperform related approaches and our method ranks as the 1𝑠𝑡 place on the final leaderboard, with a Global Average Precision (GAP) of 82.63%. To better promote the research in this field, we will release our code in the final version. CCS CONCEPTS• Computing methodologies → Machine learning approaches; Knowledge representation and reasoning.

show abstract

“…Automated surveillance is a major problem and concern of computer vision experts, where deep models have achieved tremendously precise results in many computer vision problems, ranging from object detection to complex multiple activities prediction and perception. The achievements of computer vision techniques are mainly due to the excessive demand of automated video analytic methods for enormous applications such as video indexing and retrieval, video summarization [91], action and activity recognition [14], and video classification [65]. In video classification domain, action and activity recognition has received significant attention in research community due to its applications to medical healthcare, security, sports and entertainment, among many others.…”

Section: Introductionmentioning

confidence: 99%

An overview of violence detection techniques: current challenges and future directions

et al. 2022

View full text Add to dashboard Cite

The Big Video Data generated in today's smart cities has raised concerns from its purposeful usage perspective, where surveillance cameras, among many others are the most prominent resources to contribute to the huge volumes of data, making its automated analysis a difficult task in terms of computation and preciseness. Violence Detection (VD), broadly plunging under Action and Activity recognition domain, is used to analyze Big Video data for anomalous actions incurred due to humans. The VD literature is traditionally based on manually engineered features, though advancements to deep learning based standalone models are developed for

show abstract

Video classification and retrieval through spatio-temporal Radon features

Cited by 19 publications

References 15 publications

ADMT: Advanced Driver’s Movement Tracking System Using Spatio-Temporal Interest Points and Maneuver Anticipation Using Deep Neural Networks

ADMT: Advanced Driver’s Movement Tracking System Using Spatio-Temporal Interest Points and Maneuver Anticipation Using Deep Neural Networks

Multimodal Feature Fusion for Video Advertisements Tagging Via Stacking Ensemble

An overview of violence detection techniques: current challenges and future directions

Contact Info

Product

Resources

About