Shoplifting poses a significant challenge for shop owners as well as other stakeholders, including law enforcement agencies. In recent years, the task of shoplifting detection has gained the interest of researchers due to video surveillance generating vast quantities of data that cannot be processed in real-time by human staff. In previous studies, different datasets and methods have been developed for the task of shoplifting detection. However, there is a lack of a large benchmark dataset containing different behaviors of shoplifting and standard methods for the task of shoplifting detection. To overcome this limitation, in this study, a large benchmark dataset has been developed, having 900 instances with 450 cases of shoplifting and 450 of non-shoplifting with manual annotation based on five different ways of shoplifting. Moreover, a method for the detection of shoplifting is proposed for evaluating the developed dataset. The dataset is also evaluated with methods as baseline methods, including 2D CNN and 3D CNN. Our proposed method, which is a combination of Inception V3 and BILSTM, outperforms all baseline methods with 81 % accuracy. The developed dataset will be publicly available to foster in various areas related to human activity recognition. These areas encompass the development of systems for detecting behaviors such as robbery, identifying human movements, enhancing safety measures, and detecting instances of theft.
19 November 2018 in Journal of the Association for Information Science and Technology
Text reuse is becoming a serious issue in many fields and research shows that it is much harder to detect when it occurs across languages. The recent rise in multi‐lingual content on the Web has increased cross‐language text reuse to an unprecedented scale. Although researchers have proposed methods to detect it, one major drawback is the unavailability of large‐scale gold standard evaluation resources built on real cases. To overcome this problem, we propose a cross‐language sentence/passage level text reuse corpus for the English‐Urdu language pair. The Cross‐Language English‐Urdu Corpus (CLEU) has source text in English whereas the derived text is in Urdu. It contains in total 3,235 sentence/passage pairs manually tagged into three categories that is near copy, paraphrased copy, and independently written. Further, as a second contribution, we evaluate the Translation plus Mono‐lingual Analysis method using three sets of experiments on the proposed dataset to highlight its usefulness. Evaluation results (f1=0.732 binary, f1=0.552 ternary classification) indicate that it is harder to detect cross‐language real cases of text reuse, especially when the language pairs have unrelated scripts. The corpus is a useful benchmark resource for the future development and assessment of cross‐language text reuse detection systems for the English‐Urdu language pair.
Paraphrase detection systems uncover the relationship between two text fragments and classify them as paraphrased when they convey the same idea; otherwise non-paraphrased. Previously, the researchers have mainly focused on developing resources for the English language for paraphrase detection. There have been very few efforts for paraphrase detection in South Asian languages. However, no research has been conducted on sentence-level paraphrase detection in Urdu, a low-resourced language. It is mainly due to the unavailability of the corpora that focus on the sentence level. The available related studies on the Urdu language only focus on text reuse detection tasks at the passage and document levels. Therefore, this study aims to develop a large-scale manually annotated benchmark Urdu paraphrase detection corpus at the sentence level, based on real cases from journalism. The proposed Urdu Sentential Paraphrases (USP) corpus contains 4,900 sentences (2,941 paraphrased and 1,959 non-paraphrased), manually collected from the Urdu newspapers. Moreover, several techniques were proposed, developed, and compared as a secondary contribution, including Word Embedding (WE), Sentence Transformers (ST), and feature-fusion techniques. N-gram is treated as the baseline technique for our research. The experimental results indicate that our proposed feature-fusion technique is the most suitable for the Urdu paraphrase detection task. Furthermore, the performance increases when features of the proposed (ST) and baseline (N-gram) are combined for the classification task. In addition, The proposed techniques have also been applied to the UPPC corpus to check their performance at the document level. The best result we obtained using the feature fusion technique ( F1 = 0.855). Our corpus is available and free to download for research purposes.