Proceedings of the 2018 ACM on International Conference on Multimedia Retrieval最新文献_第9页

Scene Text Detection and Tracking in Video with Background Cues 基于背景线索的视频场景文本检测与跟踪

Proceedings of the 2018 ACM on International Conference on Multimedia Retrieval Pub Date : 2018-06-05 DOI: 10.1145/3206025.3206051

Lan Wang, Yang Wang, Susu Shan, Feng Su

引用次数: 28

Temporal Aggregation of Visual Features for Large-Scale Image-to-Video Retrieval 面向大规模图像到视频检索的视觉特征时间聚合

Proceedings of the 2018 ACM on International Conference on Multimedia Retrieval Pub Date : 2018-06-05 DOI: 10.1145/3206025.3206083

Noa García

引用次数: 9

Session details: Oral Session 1: Multimedia Retrieval 会议详情:口头会议1:多媒体检索

Proceedings of the 2018 ACM on International Conference on Multimedia Retrieval Pub Date : 2018-06-05 DOI: 10.1145/3252926

Qi Tan

引用次数: 0

Precise Temporal Action Localization by Evolving Temporal Proposals 演化时间提议的精确时间动作定位

Proceedings of the 2018 ACM on International Conference on Multimedia Retrieval Pub Date : 2018-04-13 DOI: 10.1145/3206025.3206029

Haonan Qiu, Yingbin Zheng, Hao Ye, Yao Lu, Feng Wang, Liang He

{"title":"Precise Temporal Action Localization by Evolving Temporal Proposals","authors":"Haonan Qiu, Yingbin Zheng, Hao Ye, Yao Lu, Feng Wang, Liang He","doi":"10.1145/3206025.3206029","DOIUrl":"https://doi.org/10.1145/3206025.3206029","url":null,"abstract":"Locating actions in long untrimmed videos has been a challenging problem in video content analysis. The performances of existing action localization approaches remain unsatisfactory in precisely determining the beginning and the end of an action. Imitating the human perception procedure with observations and refinements, we propose a novel three-phase action localization framework. Our framework is embedded with an Actionness Network to generate initial proposals through frame-wise similarity grouping, and then a Refinement Network to conduct boundary adjustment on these proposals. Finally, the refined proposals are sent to a Localization Network for further fine-grained location regression. The whole process can be deemed as multi-stage refinement using a novel non-local pyramid feature under various temporal granularities. We evaluate our framework on THUMOS14 benchmark and obtain a significant improvement over the state-of-the-arts approaches. Specifically, the performance gain is remarkable under precise localization with high IoU thresholds. Our proposed framework achieves mAP@IoU=0.5 of 34.2%.","PeriodicalId":224132,"journal":{"name":"Proceedings of the 2018 ACM on International Conference on Multimedia Retrieval","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-04-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130300548","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}

引用次数: 28

Automatic Prediction of Building Age from Photographs 从照片中自动预测建筑物的年龄

Proceedings of the 2018 ACM on International Conference on Multimedia Retrieval Pub Date : 2018-04-06 DOI: 10.1145/3206025.3206060

M. Zeppelzauer, Miroslav Despotovic, Muntaha Sakeena, David Koch, M. Döller

引用次数: 40

A LiDAR Point Cloud Generator: from a Virtual World to Autonomous Driving 激光雷达点云发生器:从虚拟世界到自动驾驶

Proceedings of the 2018 ACM on International Conference on Multimedia Retrieval Pub Date : 2018-03-31 DOI: 10.1145/3206025.3206080

Xiangyu Yue, Bichen Wu, S. Seshia, K. Keutzer, A. Sangiovanni-Vincentelli

{"title":"A LiDAR Point Cloud Generator: from a Virtual World to Autonomous Driving","authors":"Xiangyu Yue, Bichen Wu, S. Seshia, K. Keutzer, A. Sangiovanni-Vincentelli","doi":"10.1145/3206025.3206080","DOIUrl":"https://doi.org/10.1145/3206025.3206080","url":null,"abstract":"3D LiDAR scanners are playing an increasingly important role in autonomous driving as they can generate depth information of the environment. However, creating large 3D LiDAR point cloud datasets with point-level labels requires a significant amount of manual annotation. This jeopardizes the efficient development of supervised deep learning algorithms which are often data-hungry. We present a framework to rapidly create point clouds with accurate point-level labels from a computer game. To our best knowledge, this is the first publication on LiDAR point cloud simulation framework for autonomous driving. The framework supports data collection from both auto-driving scenes and user-configured scenes. Point clouds from auto-driving scenes can be used as training data for deep learning algorithms, while point clouds from user-configured scenes can be used to systematically test the vulnerability of a neural network, and use the falsifying examples to make the neural network more robust through retraining. In addition, the scene images can be captured simultaneously in order for sensor fusion tasks, with a method proposed to do automatic registration between the point clouds and captured scene images. We show a significant improvement in accuracy (+9%) in point cloud segmentation by augmenting the training dataset with the generated synthesized data. Our experiments also show by testing and retraining the network using point clouds from user-configured scenes, the weakness/blind spots of the neural network can be fixed.","PeriodicalId":224132,"journal":{"name":"Proceedings of the 2018 ACM on International Conference on Multimedia Retrieval","volume":"32 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-03-31","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"132328793","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}

引用次数: 168

Transductive Zero-Shot Hashing via Coarse-to-Fine Similarity Mining 基于粗到细相似性挖掘的换能性零次哈希

Proceedings of the 2018 ACM on International Conference on Multimedia Retrieval Pub Date : 2017-11-08 DOI: 10.1145/3206025.3206026

Hanjiang Lai, Yan Pan

{"title":"Transductive Zero-Shot Hashing via Coarse-to-Fine Similarity Mining","authors":"Hanjiang Lai, Yan Pan","doi":"10.1145/3206025.3206026","DOIUrl":"https://doi.org/10.1145/3206025.3206026","url":null,"abstract":"Zero-shot Hashing (ZSH) is to learn hashing models for novel/target classes without training data, which is an important and challenging problem. Most existing ZSH approaches exploit transfer learning via an intermediate shared semantic representations between the seen/source classes and novel/target classes. However, the hash functions learned from the source dataset may show poor performance when directly applied to the target classes due to the dataset bias. In this paper, we study the transductive ZSH, i.e., we have unlabeled data for novel classes. We put forward a simple yet efficient joint learning approach via coarse-to-fine similarity mining which transfers knowledges from source data to target data. It mainly consists of two building blocks in the proposed deep architecture: 1) a shared two-streams network to learn the effective common image representations. The first stream operates on the source data and the second stream operates on the unlabeled data. And 2) a coarse-to-fine module to transfer the similarities of the source data to the target data in a greedy fashion. It begins with a coarse search over the unlabeled data to find the images that most dissimilar to the source data, and then detects the similarities among the found images via the fine module. Extensive evaluation results on several benchmark datasets demonstrate that the proposed hashing method achieves significant improvement over the state-of-the-art methods.","PeriodicalId":224132,"journal":{"name":"Proceedings of the 2018 ACM on International Conference on Multimedia Retrieval","volume":"20 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2017-11-08","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126553175","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}

引用次数: 10

Deep Extreme Multi-label Learning 深度极端多标签学习

Proceedings of the 2018 ACM on International Conference on Multimedia Retrieval Pub Date : 2017-04-12 DOI: 10.1145/3206025.3206030

Wenjie Zhang, Liwei Wang, Junchi Yan, Xiangfeng Wang, H. Zha

引用次数: 95

PatternNet: Visual Pattern Mining with Deep Neural Network PatternNet:基于深度神经网络的视觉模式挖掘

Proceedings of the 2018 ACM on International Conference on Multimedia Retrieval Pub Date : 2017-03-18 DOI: 10.1145/3206025.3206039

Hongzhi Li, Joseph G. Ellis, Lei Zhang, Shih-Fu Chang

{"title":"PatternNet: Visual Pattern Mining with Deep Neural Network","authors":"Hongzhi Li, Joseph G. Ellis, Lei Zhang, Shih-Fu Chang","doi":"10.1145/3206025.3206039","DOIUrl":"https://doi.org/10.1145/3206025.3206039","url":null,"abstract":"Visual patterns represent the discernible regularity in the visual world. They capture the essential nature of visual objects or scenes. Understanding and modeling visual patterns is a fundamental problem in visual recognition that has wide ranging applications. In this paper, we study the problem of visual pattern mining and propose a novel deep neural network architecture called PatternNet for discovering these patterns that are both discriminative and representative. The proposed PatternNet leverages the filters in the last convolution layer of a convolutional neural network to find locally consistent visual patches, and by combining these filters we can effectively discover unique visual patterns. In addition, PatternNet can discover visual patterns efficiently without performing expensive image patch sampling, and this advantage provides an order of magnitude speedup compared to most other approaches. We evaluate the proposed PatternNet subjectively by showing randomly selected visual patterns which are discovered by our method and quantitatively by performing image classification with the identified visual patterns and comparing our performance with the current state-of-the-art. We also directly evaluate the quality of the discovered visual patterns by leveraging the identified patterns as proposed objects in an image and compare with other relevant methods. Our proposed network and procedure, PatterNet, is able to outperform competing methods for the tasks described.","PeriodicalId":224132,"journal":{"name":"Proceedings of the 2018 ACM on International Conference on Multimedia Retrieval","volume":"11 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2017-03-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122012691","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}

引用次数: 33