scholarly journals ISLF: Interest Shift and Latent Factors Combination Model for Session-based Recommendation

2019 ◽  
Author(s):  
Jing Song ◽  
Hong Shen ◽  
Zijing Ou ◽  
Junyi Zhang ◽  
Teng Xiao ◽  
...  
Keyword(s):  
User Behavior ◽  
State Of The Art ◽  
Experimental Results ◽  
Challenging Problem ◽  
Short Term ◽  
Latent Factors ◽  
Combination Model ◽  
Benchmark Datasets ◽  
Novel Model

Session-based recommendation is a challenging problem due to the inherent uncertainty of user behavior and the limited historical click information. Latent factors and the complex dependencies within the user’s current session have an important impact on the user's main intention, but the existing methods do not explicitly consider this point. In this paper, we propose a novel model, Interest Shift and Latent Factors Combination Model (ISLF), which can capture the user's main intention by taking into account the user’s interest shift (i.e. long-term and short-term interest) and latent factors simultaneously. In addition, we experimentally give an explicit explanation of this combination in our ISLF. Our experimental results on three benchmark datasets show that our model achieves state-of-the-art performance on all test datasets.

scholarly journals LCF: A Local Context Focus Mechanism for Aspect-Based Sentiment Classification

2019 ◽  
Vol 9 (16) ◽  
pp. 3389 ◽  
Author(s):  
Biqing Zeng ◽  
Heng Yang ◽  
Ruyang Xu ◽  
Wu Zhou ◽  
Xuli Han
Keyword(s):  
State Of The Art ◽  
Sentiment Classification ◽  
Experimental Results ◽  
Local Context ◽  
Baseline Model ◽  
Global Context ◽  
Benchmark Datasets ◽  
Art Performance ◽  
Context Features

Aspect-based sentiment classification (ABSC) aims to predict sentiment polarities of different aspects within sentences or documents. Many previous studies have been conducted to solve this problem, but previous works fail to notice the correlation between the aspect’s sentiment polarity and the local context. In this paper, a Local Context Focus (LCF) mechanism is proposed for aspect-based sentiment classification based on Multi-head Self-Attention (MHSA). This mechanism is called LCF design, and utilizes the Context features Dynamic Mask (CDM) and Context Features Dynamic Weighted (CDW) layers to pay more attention to the local context words. Moreover, a BERT-shared layer is adopted to LCF design to capture internal long-term dependencies of local context and global context. Experiments are conducted on three common ABSC datasets: the laptop and restaurant datasets of SemEval-2014 and the ACL twitter dataset. Experimental results demonstrate that the LCF baseline model achieves considerable performance. In addition, we conduct ablation experiments to prove the significance and effectiveness of LCF design. Especially, by incorporating with BERT-shared layer, the LCF-BERT model refreshes state-of-the-art performance on all three benchmark datasets.

scholarly journals A Multilayer CARU Framework to Obtain Probability Distribution for Paragraph-Based Sentiment Analysis

2021 ◽  
Vol 11 (23) ◽  
pp. 11344
Author(s):  
Wei Ke ◽  
Ka-Hou Chan
Keyword(s):  
Probability Distribution ◽  
Information Extraction ◽  
Sentiment Analysis ◽  
State Of The Art ◽  
Final Analysis ◽  
The State ◽  
Experimental Results ◽  
Content Adaptive

Paragraph-based datasets are hard to analyze by a simple RNN, because a long sequence always contains lengthy problems of long-term dependencies. In this work, we propose a Multilayer Content-Adaptive Recurrent Unit (CARU) network for paragraph information extraction. In addition, we present a type of CNN-based model as an extractor to explore and capture useful features in the hidden state, which represent the content of the entire paragraph. In particular, we introduce the Chebyshev pooling to connect to the end of the CNN-based extractor instead of using the maximum pooling. This can project the features into a probability distribution so as to provide an interpretable evaluation for the final analysis. Experimental results demonstrate the superiority of the proposed approach, being compared to the state-of-the-art models.

scholarly journals Learning Long- and Short-Term User Literal-Preference with Multimodal Hierarchical Transformer Network for Personalized Image Caption

2020 ◽  
Vol 34 (05) ◽  
pp. 9571-9578 ◽  
Author(s):  
Wei Zhang ◽  
Yue Ying ◽  
Pan Lu ◽  
Hongyuan Zha
Keyword(s):  
State Of The Art ◽  
Natural Extension ◽  
Target Image ◽  
Short Term ◽  
Image Representations ◽  
High Level ◽  
Image Descriptions ◽  
Shed Light ◽  
Image Caption

Personalized image caption, a natural extension of the standard image caption task, requires to generate brief image descriptions tailored for users' writing style and traits, and is more practical to meet users' real demands. Only a few recent studies shed light on this crucial task and learn static user representations to capture their long-term literal-preference. However, it is insufficient to achieve satisfactory performance due to the intrinsic existence of not only long-term user literal-preference, but also short-term literal-preference which is associated with users' recent states. To bridge this gap, we develop a novel multimodal hierarchical transformer network (MHTN) for personalized image caption in this paper. It learns short-term user literal-preference based on users' recent captions through a short-term user encoder at the low level. And at the high level, the multimodal encoder integrates target image representations with short-term literal-preference, as well as long-term literal-preference learned from user IDs. These two encoders enjoy the advantages of the powerful transformer networks. Extensive experiments on two real datasets show the effectiveness of considering two types of user literal-preference simultaneously and better performance over the state-of-the-art models.

scholarly journals Learning from Interventions Using Hierarchical Policies for Safe Learning

2020 ◽  
Vol 34 (06) ◽  
pp. 10352-10360
Author(s):  
Jing Bi ◽  
Vikas Dhiman ◽  
Tianyou Xiao ◽  
Chenliang Xu
Keyword(s):  
Reaction Time ◽  
State Of The Art ◽  
The State ◽  
Policy Framework ◽  
Asymptotic Performance ◽  
Short Term ◽  
Learning From Demonstrations ◽  
Hierarchical Levels ◽  
Long Term Behavior

Learning from Demonstrations (LfD) via Behavior Cloning (BC) works well on multiple complex tasks. However, a limitation of the typical LfD approach is that it requires expert demonstrations for all scenarios, including those in which the algorithm is already well-trained. The recently proposed Learning from Interventions (LfI) overcomes this limitation by using an expert overseer. The expert overseer only intervenes when it suspects that an unsafe action is about to be taken. Although LfI significantly improves over LfD, the state-of-the-art LfI fails to account for delay caused by the expert's reaction time and only learns short-term behavior. We address these limitations by 1) interpolating the expert's interventions back in time, and 2) by splitting the policy into two hierarchical levels, one that generates sub-goals for the future and another that generates actions to reach those desired sub-goals. This sub-goal prediction forces the algorithm to learn long-term behavior while also being robust to the expert's reaction time. Our experiments show that LfI using sub-goals in a hierarchical policy framework trains faster and achieves better asymptotic performance than typical LfD.

scholarly journals Long-term target tracking combined with re-detection

2020 ◽  
Author(s):  
Juanjuan Wang ◽  
HaoRan Yang ◽  
Ning Xu ◽  
Chengqin Wu ◽  
ZengShun Zhao ◽  
...  
Keyword(s):  
Correlation Energy ◽  
State Of The Art ◽  
Tracking Algorithm ◽  
Correlation Filters ◽  
Short Term ◽  
Tracking Method ◽  
Tracking Tasks ◽  
Svm Model ◽  
Confidence Degree

Abstract The long-term visual tracking undergoes more challenges and is closer to realistic applications than short-term tracking. However, the performances of most existing methods have been limited in the long-term tracking tasks. In this work, we present a reliable yet simple long-term tracking method, which extends the state-of-the-art Learning Adaptive Discriminative Correlation Filters (LADCF) tracking algorithm with a re-detection component based on the SVM model. The LADCF tracking algorithm localizes the target in each frame and the re-detector is able to efficiently re-detect the target in the whole image when the tracking fails. We further introduce a robust confidence degree evaluation criterion that combines the maximum response criterion and the average peak-to correlation energy (APCE) to judge the confidence level of the predicted target. When the confidence degree is generally high, the SVM is updated accordingly. If the confidence drops sharply, the SVM re-detects the target. We perform extensive experiments on the OTB-2015 and UAV123 datasets. The experimental results demonstrate the effectiveness of our algorithm in long-term tracking.

scholarly journals Neural Architecture Search for a Highly Efficient Network with Random Skip Connections

2020 ◽  
Vol 10 (11) ◽  
pp. 3712
Author(s):  
Dongjing Shan ◽  
Xiongwei Zhang ◽  
Wenhua Shi ◽  
Li Li
Keyword(s):  
State Of The Art ◽  
Cell Structure ◽  
Frequency Discrimination ◽  
Search Space ◽  
Short Term ◽  
Cell Parameters ◽  
Neural Architecture ◽  
Proposed Model ◽  
Initialization Scheme

Regarding the sequence learning of neural networks, there exists a problem of how to capture long-term dependencies and alleviate the gradient vanishing phenomenon. To manage this problem, we proposed a neural network with random connections via a scheme of a neural architecture search. First, a dense network was designed and trained to construct a search space, and then another network was generated by random sampling in the space, whose skip connections could transmit information directly over multiple periods and capture long-term dependencies more efficiently. Moreover, we devised a novel cell structure that required less memory and computational power than the structures of long short-term memories (LSTMs), and finally, we performed a special initialization scheme on the cell parameters, which could permit unhindered gradient propagation on the time axis at the beginning of training. In the experiments, we evaluated four sequential tasks: adding, copying, frequency discrimination, and image classification; we also adopted several state-of-the-art methods for comparison. The experimental results demonstrated that our proposed model achieved the best performance.

scholarly journals Consistent Video Style Transfer via Compound Regularization

2020 ◽  
Vol 34 (07) ◽  
pp. 12233-12240
Author(s):  
Wenjing Wang ◽  
Jizheng Xu ◽  
Li Zhang ◽  
Yue Wang ◽  
Jiaying Liu
Keyword(s):  
State Of The Art ◽  
Video Data ◽  
Experimental Results ◽  
Temporal Consistency ◽  
Challenging Problem ◽  
Style Transfer ◽  
Single Frame ◽  
Optical Flows ◽  
Training Strategies ◽  
Art Style

Recently, neural style transfer has drawn many attentions and significant progresses have been made, especially for image style transfer. However, flexible and consistent style transfer for videos remains a challenging problem. Existing training strategies, either using a significant amount of video data with optical flows or introducing single-frame regularizers, have limited performance on real videos. In this paper, we propose a novel interpretation of temporal consistency, based on which we analyze the drawbacks of existing training strategies; and then derive a new compound regularization. Experimental results show that the proposed regularization can better balance the spatial and temporal performance, which supports our modeling. Combining with the new cost formula, we design a zero-shot video style transfer framework. Moreover, for better feature migration, we introduce a new module to dynamically adjust inter-channel distributions. Quantitative and qualitative results demonstrate the superiority of our method over other state-of-the-art style transfer methods. Our project is publicly available at: https://daooshee.github.io/CompoundVST/.

Robust Inland Waterway Ship Tracking via Hybrid TLD and Kalman Filter

2014 ◽  
Vol 1037 ◽  
pp. 373-377 ◽  
Author(s):  
Teng Fei ◽  
Liu Qing ◽  
Lin Zhu ◽  
Jing Li
Keyword(s):  
Kalman Filter ◽  
Visual Tracking ◽  
State Of The Art ◽  
Experimental Results ◽  
Closed Circuit ◽  
Video Sequences ◽  
Inland Waterway ◽  
Cluttered Background ◽  
Full Occlusion

In this paper, we mainly address the problem of tracking a single ship in inland waterway CCTV (Closed-Circuit Television) video sequences. Although state-of-the-art performance has been demonstrated in TLD (Tracking-Learning-Detection) visual tracking, it is still challenging to perform long-term robust ship tracking due to factors such as cluttered background, scale change, partial or full occlusion and so forth. In this work, we focus on tracking a single ship when it suffers occlusion. To accomplish this goal, an effective Kalman filter is adopted to construct a novel online model to adapt to the rapid ship appearance change caused by occlusion. Experimental results on numerous inland waterway CCTV video sequences demonstrate that the proposed algorithm outperforms the original one.

scholarly journals Finding Action Tubes with a Sparse-to-Dense Framework

2020 ◽  
Vol 34 (07) ◽  
pp. 11466-11473
Author(s):  
Yuxi Li ◽  
Weiyao Lin ◽  
Tao Wang ◽  
John See ◽  
Rui Qian ◽  
...  
Keyword(s):  
Dynamic Feature ◽  
Video Streams ◽  
Short Term ◽  
Key Characteristics ◽  
Benchmark Datasets ◽  
Tube Output ◽  
Spatio Temporal ◽  
First Time ◽  
Temporal Action

The task of spatial-temporal action detection has attracted increasing researchers. Existing dominant methods solve this problem by relying on short-term information and dense serial-wise detection on each individual frames or clips. Despite their effectiveness, these methods showed inadequate use of long-term information and are prone to inefficiency. In this paper, we propose for the first time, an efficient framework that generates action tube proposals from video streams with a single forward pass in a sparse-to-dense manner. There are two key characteristics in this framework: (1) Both long-term and short-term sampled information are explicitly utilized in our spatio-temporal network, (2) A new dynamic feature sampling module (DTS) is designed to effectively approximate the tube output while keeping the system tractable. We evaluate the efficacy of our model on the UCF101-24, JHMDB-21 and UCFSports benchmark datasets, achieving promising results that are competitive to state-of-the-art methods. The proposed sparse-to-dense strategy rendered our framework about 7.6 times more efficient than the nearest competitor.

Sign in / Sign up

Export Citation Format

Share Document