Temporal Convolutional Network with Complementary Inner Bag Loss for Weakly Supervised Anomaly Detection

Zhang, Jiangong; Qing, Laiyun; Miao, Jun

doi:10.1109/icip.2019.8803657

Cited by 129 publications

(66 citation statements)

References 13 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Table 3 shows the results obtained by using KTH, UCF11, and KISA Datasets. [28] R3D RGB 76.67 Zhang et al [29] C3D RGB 78.66 Kamoona et al [30] C3D RGB 79.49 GCN-Annmaly [31] C3D RGB 81.08 MIST [32] C3D RGB 81.40 MlST [32] I3D RGB 82.30 Wu et al [33] I3D RGB 82.44 Tian et al [34] C3D RGB 83.28 Tian et al [34] I3D RGB 84.03 Recently, Convolutional 3D (C3D), I3D, and Residual 3D (R3D) methods are mainly used for action recognition algorithms. In Table 3, I3D and C3D showed high performance in the public dataset.…”

Section: Resultsmentioning

confidence: 99%

Real-Time Surveillance System for Analyzing Abnormal Behavior of Pedestrians

Kim¹,

Kim²,

Mok³

et al. 2021

Applied Sciences

View full text Add to dashboard Cite

In spite of excellent performance of deep learning-based computer vision algorithms, they are not suitable for real-time surveillance to detect abnormal behavior because of very high computational complexity. In this paper, we propose a real-time surveillance system for abnormal behavior analysis in a closed-circuit television (CCTV) environment by constructing an algorithm and system optimized for a CCTV environment. The proposed method combines pedestrian detection and tracking to extract pedestrian information in real-time, and detects abnormal behaviors such as intrusion, loitering, fall-down, and violence. To analyze an abnormal behavior, it first determines intrusion/loitering through the coordinates of an object and then determines fall-down/violence based on the behavior pattern of the object. The performance of the proposed method is evaluated using an intelligent CCTV data set distributed by Korea Internet and Security Agency (KISA).

show abstract

Section: Resultsmentioning

confidence: 99%

Real-Time Surveillance System for Analyzing Abnormal Behavior of Pedestrians

Kim¹,

Kim²,

Mok³

et al. 2021

Applied Sciences

View full text Add to dashboard Cite

show abstract

“…For the authors knowledge, UCF-Crime and The Web datasets are the most well known and referenced by the scientific community for this context [28,29], due to its diversity and size, being this the reason for its selection for training and testing the proposal here included. GBA is also included, as it comprises indoor anomalous scenes from standard in the wild environments [36], of high interest in security applications.…”

Section: Methodsmentioning

confidence: 99%

“…In this work, outer bag loss, associated with the difference in score between abnormal and normal bags, is formulated to push apart the anomalous and normal bags from each other. The above-stated work has been extended to include inner bag loss in [29] as intra-difference between scores within a bag should be as low as possible.…”

Section: Related Workmentioning

confidence: 99%

See 1 more Smart Citation

Semi-Supervised Anomaly Detection in Video-Surveillance Scenes in the Wild

Sarker

Losada

Marrón

et al. 2021

Sensors

View full text Add to dashboard Cite

Surveillance cameras are being installed in many primary daily living places to maintain public safety. In this video-surveillance context, anomalies occur only for a very short time, and very occasionally. Hence, manual monitoring of such anomalies may be exhaustive and monotonous, resulting in a decrease in reliability and speed in emergency situations due to monitor tiredness. Within this framework, the importance of automatic detection of anomalies is clear, and, therefore, an important amount of research works have been made lately in this topic. According to these earlier studies, supervised approaches perform better than unsupervised ones. However, supervised approaches demand manual annotation, making dependent the system reliability of the different situations used in the training (something difficult to set in anomaly context). In this work, it is proposed an approach for anomaly detection in video-surveillance scenes based on a weakly supervised learning algorithm. Spatio-temporal features are extracted from each surveillance video using a temporal convolutional 3D neural network (T-C3D). Then, a novel ranking loss function increases the distance between the classification scores of anomalous and normal videos, reducing the number of false negatives. The proposal has been evaluated and compared against state-of-art approaches, obtaining competitive performance without fine-tuning, which also validates its generalization capability. In this paper, the proposal design and reliability is presented and analyzed, as well as the aforementioned quantitative and qualitative evaluation in-the-wild scenarios, demonstrating its high sensitivity in anomaly detection in all of them.

show abstract

“…It is suited for the detection or localization of anomalous events especially in the absence of precise label information in the training data. Zhong et al employs a weakly supervised anomaly detection using MIL with inner bag loss (IBL) of both positive and negative bags [17]. Dictionary of sparse codes in conjunction with MIL is also made use of to train anomalous labeled bags containing unlabeled sub-events instances [38].…”

Section: Related Workmentioning

confidence: 99%