This paper shows a Min-Max property existing in the connection weights of the convolutional layers in a neural network structure, i.e., the LeNet. Specifically, the Min-Max property means that, during the back propaga...
详细信息
We study the problem of leveraging the syntactic structure of text to enhance pre-trained models such as BERT and RoBERTa. Existing methods utilize syntax of text either in the pre-training stage or in the fine-tuning...
详细信息
In this paper, we propose a defence strategy to improves adversarial robustness incorporating hidden layer representation. The key of this defence strategy aims to compress or filter input’s information including adv...
详细信息
This paper attacks the challenging problem of zero-example video retrieval. In such a retrieval paradigm, an end user searches for unlab.led videos by ad-hoc queries described in natural language text with no visual e...
详细信息
ISBN:
(纸本)9781728132945
This paper attacks the challenging problem of zero-example video retrieval. In such a retrieval paradigm, an end user searches for unlab.led videos by ad-hoc queries described in natural language text with no visual example provided. Given videos as sequences of frames and queries as sequences of words, an effective sequence-to-sequence cross-modal matching is required. The majority of existing methods are concept based, extracting relevant concepts from queries and videos and accordingly establishing associations between the two modalities. In contrast, this paper takes a concept-free approach, proposing a dual deep encoding network that encodes videos and queries into powerful dense representations of their own. Dual encoding is conceptually simple, practically effective and end-to-end. As experiments on three benchmarks, i.e. MSR-VTT, TRECVID 2016 and 2017 Ad-hoc Video Search show, the proposed solution establishes a new state-of-the-art for zero-example video retrieval.
To facilitate the emerging applications in 5G networks, mobile network operators will provide many network functions in terms of control and prediction. Recently, they have recognized the power of machine learning (ML...
详细信息
The ubiquitousness of GPS sensors in smart-phones, vehicles and wearable devices has enabled the collection of massive volumes of trajectory data from tracing moving objects. Consequently, an unprecedented scale of ti...
详细信息
To improve the efficiency of metropolitan shared transportation services (STS), this paper proposes a cooperative scheduling framework to avoid congestion. Two procedures are considered: shared path scheduling and con...
详细信息
Emotion plays an important role in detecting fake news online. When leveraging emotional signals, the existing methods focus on exploiting the emotions of news contents that conveyed by the publishers (i.e., publisher...
详细信息
Most existing lidar odometry estimation strategies are formulated under a standard framework that includes feature selection, and pose estimation through feature matching. In this work, we present a novel pipeline cal...
详细信息
In data Mining, especially when datasets are complex with many features existed. data preparation and analysis may be necessary in implement effective data mining model, especially in classification of high dimensiona...
详细信息
ISBN:
(纸本)9781538680988;9781538680971
In data Mining, especially when datasets are complex with many features existed. data preparation and analysis may be necessary in implement effective data mining model, especially in classification of high dimensional data where not all features are important in the mining process. Hence, feature selection is an essential in data preprocessing. A well known technique in selecting useful attributes is Principle Component Analysis (PCA). The technique assigns a value to each component (feature), so order of importance among components can be apparent. This work presents a new feature selection method. It improves the effectiveness of PCA by means of utilizing the Logistic Function to become Logistic Principle Component Analysis (L-PCA). PCA and L-PCA are compared by means of classifying ten public domain datasets. The result reveals that L-PCA is superior to PCA and able to select crucial features more efficiently.
暂无评论