{"title":"Session details: Deep-2 (Recognition)","authors":"Qin Jin","doi":"10.1145/3286931","DOIUrl":"https://doi.org/10.1145/3286931","url":null,"abstract":"","PeriodicalId":339857,"journal":{"name":"Proceedings of the 26th ACM international conference on Multimedia","volume":"53 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-10-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124744106","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
By offering a natural way for information seeking, multimodal dialogue systems are attracting increasing attention in several domains such as retail, travel etc. However, most existing dialogue systems are limited to textual modality, which cannot be easily extended to capture the rich semantics in visual modality such as product images. For example, in fashion domain, the visual appearance of clothes and matching styles play a crucial role in understanding the user's intention. Without considering these, the dialogue agent may fail to generate desirable responses for users. In this paper, we present a Knowledge-aware Multimodal Dialogue (KMD) model to address the limitation of text-based dialogue systems. It gives special consideration to the semantics and domain knowledge revealed in visual content, and is featured with three key components. First, we build a taxonomy-based learning module to capture the fine-grained semantics in images the category and attributes of a product). Second, we propose an end-to-end neural conversational model to generate responses based on the conversation history, visual semantics, and domain knowledge. Lastly, to avoid inconsistent dialogues, we adopt a deep reinforcement learning method which accounts for future rewards to optimize the neural conversational model. We perform extensive evaluation on a multi-turn task-oriented dialogue dataset in fashion domain. Experiment results show that our method significantly outperforms state-of-the-art methods, demonstrating the efficacy of modeling visual modality and domain knowledge for dialogue systems.
{"title":"Knowledge-aware Multimodal Dialogue Systems","authors":"Lizi Liao, Yunshan Ma, Xiangnan He, Richang Hong, Tat-Seng Chua","doi":"10.1145/3240508.3240605","DOIUrl":"https://doi.org/10.1145/3240508.3240605","url":null,"abstract":"By offering a natural way for information seeking, multimodal dialogue systems are attracting increasing attention in several domains such as retail, travel etc. However, most existing dialogue systems are limited to textual modality, which cannot be easily extended to capture the rich semantics in visual modality such as product images. For example, in fashion domain, the visual appearance of clothes and matching styles play a crucial role in understanding the user's intention. Without considering these, the dialogue agent may fail to generate desirable responses for users. In this paper, we present a Knowledge-aware Multimodal Dialogue (KMD) model to address the limitation of text-based dialogue systems. It gives special consideration to the semantics and domain knowledge revealed in visual content, and is featured with three key components. First, we build a taxonomy-based learning module to capture the fine-grained semantics in images the category and attributes of a product). Second, we propose an end-to-end neural conversational model to generate responses based on the conversation history, visual semantics, and domain knowledge. Lastly, to avoid inconsistent dialogues, we adopt a deep reinforcement learning method which accounts for future rewards to optimize the neural conversational model. We perform extensive evaluation on a multi-turn task-oriented dialogue dataset in fashion domain. Experiment results show that our method significantly outperforms state-of-the-art methods, demonstrating the efficacy of modeling visual modality and domain knowledge for dialogue systems.","PeriodicalId":339857,"journal":{"name":"Proceedings of the 26th ACM international conference on Multimedia","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-10-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130673813","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
{"title":"Session details: Open Source Software Competition","authors":"Min-Chun Hu","doi":"10.1145/3286934","DOIUrl":"https://doi.org/10.1145/3286934","url":null,"abstract":"","PeriodicalId":339857,"journal":{"name":"Proceedings of the 26th ACM international conference on Multimedia","volume":"104 6 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-10-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123388071","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
As attribute leaning brings mid-level semantic properties for objects, it can benefit many traditional learning problems in multimedia and computer vision communities. When facing the huge number of attributes, it is extremely challenging to automatically design a generalizable neural network for other attribute learning tasks. Even for a specific attribute domain, the exploration of the neural network architecture is always optimized by a combination of heuristics and grid search, from which there is a large space of possible choices to be searched. In this paper, Generalizable Attribute Learning Model (GALM) is proposed to automatically design the neural networks for generalizable attribute learning. The main novelty of GALM is that it fully exploits the Multi-Task Learning and Reinforcement Learning to speed up the search procedure. With the help of parameter sharing, GALM is able to transfer the pre-searched architecture to different attribute domains. In experiments, we comprehensively evaluate GALM on 251 attributes from three domains: animals, objects, and scenes. Extensive experimental results demonstrate that GALM significantly outperforms the state-of-the-art attribute learning approaches and previous neural architecture search methods on two generalizable attribute learning scenarios.
{"title":"Learning to Transfer: Generalizable Attribute Learning with Multitask Neural Model Search","authors":"Zhi-Qi Cheng, Xiao Wu, Siyu Huang, Jun-Xiu Li, Alexander Hauptmann, Qiang Peng","doi":"10.1145/3240508.3240518","DOIUrl":"https://doi.org/10.1145/3240508.3240518","url":null,"abstract":"As attribute leaning brings mid-level semantic properties for objects, it can benefit many traditional learning problems in multimedia and computer vision communities. When facing the huge number of attributes, it is extremely challenging to automatically design a generalizable neural network for other attribute learning tasks. Even for a specific attribute domain, the exploration of the neural network architecture is always optimized by a combination of heuristics and grid search, from which there is a large space of possible choices to be searched. In this paper, Generalizable Attribute Learning Model (GALM) is proposed to automatically design the neural networks for generalizable attribute learning. The main novelty of GALM is that it fully exploits the Multi-Task Learning and Reinforcement Learning to speed up the search procedure. With the help of parameter sharing, GALM is able to transfer the pre-searched architecture to different attribute domains. In experiments, we comprehensively evaluate GALM on 251 attributes from three domains: animals, objects, and scenes. Extensive experimental results demonstrate that GALM significantly outperforms the state-of-the-art attribute learning approaches and previous neural architecture search methods on two generalizable attribute learning scenarios.","PeriodicalId":339857,"journal":{"name":"Proceedings of the 26th ACM international conference on Multimedia","volume":"143 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-10-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121636877","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Junbo Wang, Wei Wang, Yan Huang, Liang Wang, T. Tan
Translating videos into natural language sentences has drawn much attention recently. The framework of combining visual attention with Long Short-Term Memory (LSTM) based text decoder has achieved much progress. However, the vision-language translation still remains unsolved due to the semantic gap and misalignment between video content and described semantic concept. In this paper, we propose a Hierarchical Memory Model (HMM) - a novel deep video captioning architecture which unifies a textual memory, a visual memory and an attribute memory in a hierarchical way. These memories can guide attention for efficient video representation extraction and semantic attribute selection in addition to modelling the long-term dependency for video sequence and sentences, respectively. Compared with traditional vision-based text decoder, the proposed attribute-based text decoder can largely reduce the semantic discrepancy between video and sentence. To prove the effectiveness of the proposed model, we perform extensive experiments on two public benchmark datasets: MSVD and MSR-VTT. Experiments show that our model not only can discover appropriate video representation and semantic attributes but also can achieve comparable or superior performances than state-of-the-art methods on these datasets.
{"title":"Hierarchical Memory Modelling for Video Captioning","authors":"Junbo Wang, Wei Wang, Yan Huang, Liang Wang, T. Tan","doi":"10.1145/3240508.3240538","DOIUrl":"https://doi.org/10.1145/3240508.3240538","url":null,"abstract":"Translating videos into natural language sentences has drawn much attention recently. The framework of combining visual attention with Long Short-Term Memory (LSTM) based text decoder has achieved much progress. However, the vision-language translation still remains unsolved due to the semantic gap and misalignment between video content and described semantic concept. In this paper, we propose a Hierarchical Memory Model (HMM) - a novel deep video captioning architecture which unifies a textual memory, a visual memory and an attribute memory in a hierarchical way. These memories can guide attention for efficient video representation extraction and semantic attribute selection in addition to modelling the long-term dependency for video sequence and sentences, respectively. Compared with traditional vision-based text decoder, the proposed attribute-based text decoder can largely reduce the semantic discrepancy between video and sentence. To prove the effectiveness of the proposed model, we perform extensive experiments on two public benchmark datasets: MSVD and MSR-VTT. Experiments show that our model not only can discover appropriate video representation and semantic attributes but also can achieve comparable or superior performances than state-of-the-art methods on these datasets.","PeriodicalId":339857,"journal":{"name":"Proceedings of the 26th ACM international conference on Multimedia","volume":"8 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-10-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121662598","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
{"title":"Session details: Keynote 1","authors":"Susanne CJ Boll","doi":"10.1145/3286916","DOIUrl":"https://doi.org/10.1145/3286916","url":null,"abstract":"","PeriodicalId":339857,"journal":{"name":"Proceedings of the 26th ACM international conference on Multimedia","volume":"26 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-10-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121720138","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Ziqian Chen, Shiqi Wang, D. Wu, Tiejun Huang, Ling-yu Duan
With the advances of artificial intelligence, recent years have witnessed a gradual transition from the big data to the big knowledge. Based on the knowledge-powered deep learning models, the big data such as the vast text, images and videos can be efficiently analyzed. As such, in addition to data, the communication of knowledge implied in the deep learning models is also strongly desired. As a specific example regarding the concept of knowledge creation and communication in the context of Knowledge Centric Networking (KCN), we investigate the deep learning model compression and demonstrate its promise use through a set of experiments. In particular, towards future KCN, we introduce efficient transmission of deep learning models in terms of both single model compression and multiple model prediction. The necessity, importance and open problems regarding the standardization of deep learning models, which enables the interoperability with the standardized compact model representation bitstream syntax, are also discussed.
{"title":"From Data to Knowledge: Deep Learning Model Compression, Transmission and Communication","authors":"Ziqian Chen, Shiqi Wang, D. Wu, Tiejun Huang, Ling-yu Duan","doi":"10.1145/3240508.3240654","DOIUrl":"https://doi.org/10.1145/3240508.3240654","url":null,"abstract":"With the advances of artificial intelligence, recent years have witnessed a gradual transition from the big data to the big knowledge. Based on the knowledge-powered deep learning models, the big data such as the vast text, images and videos can be efficiently analyzed. As such, in addition to data, the communication of knowledge implied in the deep learning models is also strongly desired. As a specific example regarding the concept of knowledge creation and communication in the context of Knowledge Centric Networking (KCN), we investigate the deep learning model compression and demonstrate its promise use through a set of experiments. In particular, towards future KCN, we introduce efficient transmission of deep learning models in terms of both single model compression and multiple model prediction. The necessity, importance and open problems regarding the standardization of deep learning models, which enables the interoperability with the standardized compact model representation bitstream syntax, are also discussed.","PeriodicalId":339857,"journal":{"name":"Proceedings of the 26th ACM international conference on Multimedia","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-10-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121765034","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Due to the advances in deep reinforcement learning and the demand of large training data, virtual-to-real learning has gained lots of attention from computer vision community recently. As state-of-the-art 3D engines can generate photo-realistic images suitable for training deep neural networks, researchers have been gradually applied 3D virtual environment to learn different tasks including autonomous driving, collision avoidance, and image segmentation, to name a few. Although there are already many open-source simulation environments readily available, most of them either provide small scenes or have limited interactions with objects in the environment. To facilitate visual recognition learning, we present a new Virtual Environment for Visual Deep Learning (VIVID), which offers large-scale diversified indoor and outdoor scenes. Moreover, VIVID leverages the advanced human skeleton system, which enables us to simulate numerous complex human actions. VIVID has a wide range of applications and can be used for learning indoor navigation, action recognition, event detection, etc. We also release several deep learning examples in Python to demonstrate the capabilities and advantages of our system.
{"title":"VIVID","authors":"Kuan-Ting Lai, Chia-Chih Lin, Chun-Yao Kang, Mei-Enn Liao, Ming-Syan Chen","doi":"10.1145/3240508.3243653","DOIUrl":"https://doi.org/10.1145/3240508.3243653","url":null,"abstract":"Due to the advances in deep reinforcement learning and the demand of large training data, virtual-to-real learning has gained lots of attention from computer vision community recently. As state-of-the-art 3D engines can generate photo-realistic images suitable for training deep neural networks, researchers have been gradually applied 3D virtual environment to learn different tasks including autonomous driving, collision avoidance, and image segmentation, to name a few. Although there are already many open-source simulation environments readily available, most of them either provide small scenes or have limited interactions with objects in the environment. To facilitate visual recognition learning, we present a new Virtual Environment for Visual Deep Learning (VIVID), which offers large-scale diversified indoor and outdoor scenes. Moreover, VIVID leverages the advanced human skeleton system, which enables us to simulate numerous complex human actions. VIVID has a wide range of applications and can be used for learning indoor navigation, action recognition, event detection, etc. We also release several deep learning examples in Python to demonstrate the capabilities and advantages of our system.","PeriodicalId":339857,"journal":{"name":"Proceedings of the 26th ACM international conference on Multimedia","volume":"407 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-10-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115855053","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Most multi-scale detectors face a challenge of small-size false positives due to the inadequacy of low-level features, which have small receptive field sizes and weak semantic capabilities. This paper demonstrates independent predictions from different feature layers on the same region is beneficial for reducing false positives. We propose a novel light-weight previewer block, which previews the objectness probability for the potential regression region of each prior box, using the stronger features with larger receptive fields and more contextual information for better predictions. This previewer block is generic and can be easily implemented in multi-scale detectors, such as SSD, RFBNet and MS-CNN. Extensive experiments are conducted on PASCAL VOC and KITTI pedestrian benchmark to show the superiority of the proposed method.
{"title":"Previewer for Multi-Scale Object Detector","authors":"Zhihang Fu, Zhongming Jin, Guo-Jun Qi, Chen Shen, Rongxin Jiang, Yao-wu Chen, Xiansheng Hua","doi":"10.1145/3240508.3240544","DOIUrl":"https://doi.org/10.1145/3240508.3240544","url":null,"abstract":"Most multi-scale detectors face a challenge of small-size false positives due to the inadequacy of low-level features, which have small receptive field sizes and weak semantic capabilities. This paper demonstrates independent predictions from different feature layers on the same region is beneficial for reducing false positives. We propose a novel light-weight previewer block, which previews the objectness probability for the potential regression region of each prior box, using the stronger features with larger receptive fields and more contextual information for better predictions. This previewer block is generic and can be easily implemented in multi-scale detectors, such as SSD, RFBNet and MS-CNN. Extensive experiments are conducted on PASCAL VOC and KITTI pedestrian benchmark to show the superiority of the proposed method.","PeriodicalId":339857,"journal":{"name":"Proceedings of the 26th ACM international conference on Multimedia","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-10-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130257195","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Yangyang Guo, Zhiyong Cheng, Liqiang Nie, Xin-Shun Xu, M. Kankanhalli
The visual preference of users for products has been largely ignored by the existing product search methods. In this work, we propose a multi-modal personalized product search method, which aims to search products which not only are relevant to the submitted textual query, but also match the user preferences from both textual and visual modalities. To achieve the goal, we first leverage the also_view and buy_after_viewing products to construct the visual and textual latent spaces, which are expected to preserve the visual similarity and semantic similarity of products, respectively. We then propose a translation-based search model (TranSearch ) to 1) learn a multi-modal latent space based on the pre-trained visual and textual latent spaces; and 2) map the users, queries and products into this space for direct matching. The TranSearch model is trained based on a comparative learning strategy, such that the multi-modal latent space is oriented to personalized ranking in the training stage. Experiments have been conducted on real-world datasets to validate the effectiveness of our method. The results demonstrate that our method outperforms the state-of-the-art method by a large margin.
{"title":"Multi-modal Preference Modeling for Product Search","authors":"Yangyang Guo, Zhiyong Cheng, Liqiang Nie, Xin-Shun Xu, M. Kankanhalli","doi":"10.1145/3240508.3240541","DOIUrl":"https://doi.org/10.1145/3240508.3240541","url":null,"abstract":"The visual preference of users for products has been largely ignored by the existing product search methods. In this work, we propose a multi-modal personalized product search method, which aims to search products which not only are relevant to the submitted textual query, but also match the user preferences from both textual and visual modalities. To achieve the goal, we first leverage the also_view and buy_after_viewing products to construct the visual and textual latent spaces, which are expected to preserve the visual similarity and semantic similarity of products, respectively. We then propose a translation-based search model (TranSearch ) to 1) learn a multi-modal latent space based on the pre-trained visual and textual latent spaces; and 2) map the users, queries and products into this space for direct matching. The TranSearch model is trained based on a comparative learning strategy, such that the multi-modal latent space is oriented to personalized ranking in the training stage. Experiments have been conducted on real-world datasets to validate the effectiveness of our method. The results demonstrate that our method outperforms the state-of-the-art method by a large margin.","PeriodicalId":339857,"journal":{"name":"Proceedings of the 26th ACM international conference on Multimedia","volume":"130 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-10-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"134070877","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
京公网安备 11010802042870号
京ICP备2023020795号-1
扫码关注我们
求助内容：
应助结果提醒方式：