2018 IEEE International Conference on Multimedia and Expo (ICME)最新文献_第2页

Schmidt: Image Augmentation for Black-Box Adversarial Attack Schmidt:黑盒对抗性攻击的图像增强

2018 IEEE International Conference on Multimedia and Expo (ICME) Pub Date : 2018-07-01 DOI: 10.1109/ICME.2018.8486449

Yucheng Shi, Yahong Han

引用次数: 7

Multi-Grained Deep Feature Learning for Pedestrian Detection 用于行人检测的多粒度深度特征学习

2018 IEEE International Conference on Multimedia and Expo (ICME) Pub Date : 2018-07-01 DOI: 10.1109/ICME.2018.8486498

Chunze Lin, Jiwen Lu, Jie Zhou

{"title":"Multi-Grained Deep Feature Learning for Pedestrian Detection","authors":"Chunze Lin, Jiwen Lu, Jie Zhou","doi":"10.1109/ICME.2018.8486498","DOIUrl":"https://doi.org/10.1109/ICME.2018.8486498","url":null,"abstract":"In this paper, we address the challenging problem of detecting pedestrians who are heavily occluded or far from camera. Unlike most existing pedestrian detection methods which only use coarse-resolution feature maps with fixed receptive field, our approach exploits multi-grained deep features to make the detector more robust to visible parts of occluded pedestrians and small-size targets. Specifically, we jointly train a scale-aware network and a human parsing network in a semi-supervised manner with only bounding box annotation. We carefully design the scale-aware network to predict pedestrians of particular scales using most appropriate feature maps, by matching their receptive field with the target sizes. The human parsing network generates a fine-grained attentional map which helps guide the detector to focus on the visible parts of occluded pedestrians and small-size instances. Both networks are computed in parallel and form an unified single stage pedestrian detector, which assures a great trade-off between accuracy and speed. Experiments on two challenging benchmarks, Caltech and KITTI, demonstrate the effectiveness of our proposed approach, which in addition, executes 2× faster than competitive methods.","PeriodicalId":426613,"journal":{"name":"2018 IEEE International Conference on Multimedia and Expo (ICME)","volume":"34 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116511465","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: 6

Adaptive Layerwise Quantization for Deep Neural Network Compression 深度神经网络压缩的自适应分层量化

2018 IEEE International Conference on Multimedia and Expo (ICME) Pub Date : 2018-07-01 DOI: 10.1109/ICME.2018.8486500

Xiaotian Zhu, Wen-gang Zhou, Houqiang Li

引用次数: 38

FI-CAP: Robust Framework to Benchmark Head Pose Estimation in Challenging Environments FI-CAP:在具有挑战性的环境中对基准头部姿态估计的鲁棒框架

2018 IEEE International Conference on Multimedia and Expo (ICME) Pub Date : 2018-07-01 DOI: 10.1109/ICME.2018.8486490

S. Jha, C. Busso

{"title":"FI-CAP: Robust Framework to Benchmark Head Pose Estimation in Challenging Environments","authors":"S. Jha, C. Busso","doi":"10.1109/ICME.2018.8486490","DOIUrl":"https://doi.org/10.1109/ICME.2018.8486490","url":null,"abstract":"Head pose estimation is challenging in a naturalistic environment. To effectively train machine-learning algorithms, we need datasets with reliable ground truth labels from diverse environments. We present Fi-Cap, a helmet with fiducial markers designed for head pose estimation. The relative position and orientation of the tags from a reference camera can be automatically obtained from a subset of the tags. Placed at the back of the head, it provides a reference system without interfering with sensors that record frontal face. We quantify the performance of the Fi-Cap by (1) rendering the 3D model of the design, evaluating its accuracy under various rotation, image resolution and illumination conditions, and (2) comparing the predicted head pose with the location of the projected beam of a laser mounted on glasses worn by the subjects in controlled experiments conducted in our laboratory. Fi-Cap provides ideal benchmark information to evaluate automatic algorithms and alternative sensors for head pose estimation in a variety of challenging environments, including our target application for advanced driver assistance systems (ADAS).","PeriodicalId":426613,"journal":{"name":"2018 IEEE International Conference on Multimedia and Expo (ICME)","volume":"16 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125624070","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: 7

Multi-Path Feature Fusion Network for Saliency Detection 显著性检测的多路径特征融合网络

2018 IEEE International Conference on Multimedia and Expo (ICME) Pub Date : 2018-07-01 DOI: 10.1109/ICME.2018.8486571

Hengliang Zhu, Xin Tan, Zhiwen Shao, Yangyang Hao, Lizhuang Ma

引用次数: 2

Deep Learning Based Identity Verification in Renaissance Portraits 文艺复兴时期肖像中基于深度学习的身份验证

2018 IEEE International Conference on Multimedia and Expo (ICME) Pub Date : 2018-07-01 DOI: 10.1109/ICME.2018.8486605

Akash Gupta, Niluthpol Chowdhury Mithun, C. Rudolph, A. Roy-Chowdhury

{"title":"Deep Learning Based Identity Verification in Renaissance Portraits","authors":"Akash Gupta, Niluthpol Chowdhury Mithun, C. Rudolph, A. Roy-Chowdhury","doi":"10.1109/ICME.2018.8486605","DOIUrl":"https://doi.org/10.1109/ICME.2018.8486605","url":null,"abstract":"The identity of subjects in many portraits has been a matter of debate for art historians that relied upon subjective analysis of facial features to resolve ambiguity in sitter identity. Developing automated face verification technique has thus garnered interest to provide a quantitative way to reinforce the decision arrived at by the art historians. However, most existing works often fail to resolve ambiguities concerning the identity of the subjects due to significant variation in artistic styles and the limited availability and authenticity of art images. To these ends, we explore the use of deep Siamese Convolutional Neural Networks (CNN) to provide a measure of similarity between a pair of portraits. To mitigate limited training data issue, we employ CNN based style-transfer technique that creates several new images by recasting an art style to other images, keeping original image content unchanged. The resulting system thereby learns features which are discriminative and invariant to changes in artistic styles. Our approach shows significant improvement over baselines and state-of-the-art methods on several examples which are identified by art historians as being very challenging and controversial.","PeriodicalId":426613,"journal":{"name":"2018 IEEE International Conference on Multimedia and Expo (ICME)","volume":"50 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127896092","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: 4

Depth Restoration with Normal-Guided Multiresolution Superpixel 用法线引导的多分辨率超像素深度恢复

2018 IEEE International Conference on Multimedia and Expo (ICME) Pub Date : 2018-07-01 DOI: 10.1109/ICME.2018.8486583

Jinghui Qian, Jie Guo, Jingui Pan

引用次数: 0

Personalized Sequential Check-in Prediction: Beyond Geographical and Temporal Contexts 个性化顺序登记预测:超越地理和时间背景

2018 IEEE International Conference on Multimedia and Expo (ICME) Pub Date : 2018-07-01 DOI: 10.1109/ICME.2018.8486476

Shenglin Zhao, Xixian Chen, Irwin King, Michael R. Lyu

引用次数: 6

Hybrid Noise for LIC-Based Pencil Hatching Simulation 基于lic的铅笔孵化仿真的混合噪声

2018 IEEE International Conference on Multimedia and Expo (ICME) Pub Date : 2018-07-01 DOI: 10.1109/ICME.2018.8486527

Qunye Kong, Y. Sheng, Guixu Zhang

引用次数: 8

Temporal Attentive Network for Action Recognition 动作识别的时间注意网络

2018 IEEE International Conference on Multimedia and Expo (ICME) Pub Date : 2018-07-01 DOI: 10.1109/ICME.2018.8486452

Yemin Shi, Yonghong Tian, Tiejun Huang, Yaowei Wang

{"title":"Temporal Attentive Network for Action Recognition","authors":"Yemin Shi, Yonghong Tian, Tiejun Huang, Yaowei Wang","doi":"10.1109/ICME.2018.8486452","DOIUrl":"https://doi.org/10.1109/ICME.2018.8486452","url":null,"abstract":"In action recognition, one of the most important challenges is to jointly utilize the texture and motion information as well as capturing the long-term dependence of various common and action-specific postures. Motivated by this fact, this paper proposes Temporal Attentive Network (TAN) for action recognition. The key idea in TAN is that not all postures, each of which represented by a small collection of consecutive frames, contribute equally to the successful recognition of an action. As a result, TAN incorporates two separate spatial and temporal streams into one network. Information in the two streams is partially shared so that discriminative spatiotemporal features can be extracted to characterize various postures in an action. Moreover, a temporal attention mechanism is introduced in the form of Long-Short Term Memory (LSTM) network. With this mechanism, features from the action-specific postures can be emphasized, while common postures shared by many different actions will be ignored to some extent. By jointly using such spatial and temporal information as well as attentive cues in a single network, TAN achieves impressive performance on two public datasets, HMDB51 and UCF101, with accuracy scores of 72.5% and 94.1 %, respectively.","PeriodicalId":426613,"journal":{"name":"2018 IEEE International Conference on Multimedia and Expo (ICME)","volume":"236 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"132908375","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: 5