A Unified Personalized Video Recommendation via Dynamic Recurrent Neural Networks

Gao, Junyu; Zhang, Tianzhu; Xu, Changsheng

doi:10.1145/3123266.3123433

Cited by 56 publications

(29 citation statements)

References 49 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…With the rapid development of deep learning technology, many efforts have been devoted to obtaining personalized user interests in the field of recommendation [12,17,19,21,35,36,38,42,43], especially the combination of recurrent neural networks (RNN) [8,22] and attention mechanisms [4,30], which has made great progress in capturing long-term and short-term user preferences and learning diverse interests. For example, Chen et al [2] proposed a hierarchical attention network at category-level and item-level for long-term and short-term interest modeling in micro-video click-through prediction.…”

Section: Introductionmentioning

confidence: 99%

“…• Multi-scale time effects. Previous methods usually consider that the effect of micro-videos on user interest modeling decreases over time implicitly, which is captured by RNN [8,10,11] or learned from timestamp features [20,30]. However, they ignore the case that the importance of micro-videos decreases over time varies from user to user, that is to say, for different users, 1 https://www.jiguang.cn/reports/43.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

What Aspect Do You Like

Jiang¹,

Wang

Wei³

et al. 2020

Proceedings of the 28th ACM International Conference on Multimedia

View full text Add to dashboard Cite

Online micro-video recommender systems aim to address the information explosion of micro-videos and make the personalized recommendation for users. However, the existing methods still have some limitations in learning representative user interests, since the multi-scale time effects, user interest group modeling, and false positive interactions are not taken into consideration. In view of this, we propose an end-to-end Multi-scale Time-aware user Interest modeling Network (MTIN). In particular, we first present an interest group routing algorithm to generate fine-grained user interest groups based on user's interaction sequence. Afterwards, to explore multi-scale time effects on user interests, we design a time-aware mask network and distill multiple temporal information by several parallel temporal masks. And then an interest mask network is introduced to aggregate fine-grained interest groups and generate the final user interest representation. At last, in the prediction unit, the user representation and micro-video candidates are fed into a deep neural network (DNN) for predictions. To demonstrate the effectiveness of our method, we conduct experiments on two publicly available datasets, and the experimental results demonstrate that our proposed model achieves substantial gains over the state-of-the-art methods.

show abstract

Section: Introductionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

What Aspect Do You Like

Jiang¹,

Wang

Wei³

et al. 2020

Proceedings of the 28th ACM International Conference on Multimedia

View full text Add to dashboard Cite

show abstract

“…Visual target tracking has important applications in areas such as autonomous driving, intelligent security, human computer interaction and robotics [ 1 , 2 , 3 ]. A complete tracking system consists of three components: a search strategy, the feature extraction and an observation model.…”

Section: Introductionmentioning

confidence: 99%

A Visual Tracker Offering More Solutions

Zhao

Mahmoud

Ren

et al. 2020

Sensors

View full text Add to dashboard Cite

Most trackers focus solely on robustness and accuracy. Visual tracking, however, is a long-term problem with a high time limitation. A tracker that is robust, accurate, with long-term sustainability and real-time processing, is of high research value and practical significance. In this paper, we comprehensively consider these requirements in order to propose a new, state-of-the-art tracker with an excellent performance. EfficientNet-B0 is adopted for the first time via neural architecture search technology as the backbone network for the tracking task. This improves the network feature extraction ability and significantly reduces the number of parameters required for the tracker backbone network. In addition, maximal Distance Intersection-over-Union is set as the target estimation method, enhancing network stability and increasing the offline training convergence rate. Channel and spatial dual attention mechanisms are employed in the target classification module to improve the discrimination of the trackers. Furthermore, the conjugate gradient optimization strategy increases the speed of the online learning target classification module. A two-stage search method combined with a screening module is proposed to enable the tracker to cope with sudden target movement and reappearance following a brief disappearance. Our proposed method has an obvious speed advantage compared with pure global searching and achieves an optimal performance on OTB2015, VOT2016, VOT2018-LT, UAV-123 and LaSOT while running at over 50 FPS.

show abstract

“…Song et al [Song et al, 2016] model user temporal behavior by recurrent neural network (RNN) in recommender systems. Similarly, authors in [Gao et al, 2017] design a dynamic RNN to capture user temporal preferences in the video recommendation. Although most of them take efforts to improve recommendation performance, two important factors are neglected.…”

Section: Introductionmentioning

confidence: 99%

DeepAPF: Deep Attentive Probabilistic Factorization for Multi-site Video Recommendation

Yan

Chen

Gao

et al. 2019

Proceedings of the Twenty-Eighth International Joint Conference on Artificial Intelligence

View full text Add to dashboard Cite

Existing web video systems recommend videos according to users' viewing history from its own website. However, since many users watch videos in multiple websites, this approach fails to capture these users' interests across sites. In this paper, we investigate the user viewing behavior in multiple sites based on a large scale real dataset. We find that user interests are comprised of cross-site consistent part and site-specific part with different degrees of the importance. Existing linear matrix factorization recommendation model has limitation in modeling such complicated interactions. Thus, we propose a model of Deep Attentive Probabilistic Factorization (DeepAPF) to exploit deep learning method to approximate such complex user-video interaction. DeepAPF captures both cross-site common interests and site-specific interests with non-uniform importance weights learned by the attentional network. Extensive experiments show that our proposed model outperforms by 17.62%, 7.9% and 8.1% with the comparison of three state-of-the-art baselines. Our study provides insight to integrate user viewing records from multiple sites via the trusted third party, which gains mutual benefits in video recommendation.

show abstract

A Unified Personalized Video Recommendation via Dynamic Recurrent Neural Networks

Cited by 56 publications

References 49 publications

What Aspect Do You Like

What Aspect Do You Like

A Visual Tracker Offering More Solutions

DeepAPF: Deep Attentive Probabilistic Factorization for Multi-site Video Recommendation

Contact Info

Product

Resources

About