2015 IEEE International Conference on Computer Vision (ICCV)最新文献_第7页

Category-Blind Human Action Recognition: A Practical Recognition System 类别盲人类动作识别:一种实用的识别系统

2015 IEEE International Conference on Computer Vision (ICCV) Pub Date : 2015-12-07 DOI: 10.1109/ICCV.2015.505

Wenbo Li, Longyin Wen, M. Chuah, Siwei Lyu

{"title":"Category-Blind Human Action Recognition: A Practical Recognition System","authors":"Wenbo Li, Longyin Wen, M. Chuah, Siwei Lyu","doi":"10.1109/ICCV.2015.505","DOIUrl":"https://doi.org/10.1109/ICCV.2015.505","url":null,"abstract":"Existing human action recognition systems for 3D sequences obtained from the depth camera are designed to cope with only one action category, either single-person action or two-person interaction, and are difficult to be extended to scenarios where both action categories co-exist. In this paper, we propose the category-blind human recognition method (CHARM) which can recognize a human action without making assumptions of the action category. In our CHARM approach, we represent a human action (either a single-person action or a two-person interaction) class using a co-occurrence of motion primitives. Subsequently, we classify an action instance based on matching its motion primitive co-occurrence patterns to each class representation. The matching task is formulated as maximum clique problems. We conduct extensive evaluations of CHARM using three datasets for single-person actions, two-person interactions, and their mixtures. Experimental results show that CHARM performs favorably when compared with several state-of-the-art single-person action and two-person interaction based methods without making explicit assumptions of action category.","PeriodicalId":6633,"journal":{"name":"2015 IEEE International Conference on Computer Vision (ICCV)","volume":"15 1","pages":"4444-4452"},"PeriodicalIF":0.0,"publicationDate":"2015-12-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"88804091","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: 67

Multi-View Complementary Hash Tables for Nearest Neighbor Search 多视图互补哈希表的最近邻搜索

2015 IEEE International Conference on Computer Vision (ICCV) Pub Date : 2015-12-07 DOI: 10.1109/ICCV.2015.132

Xianglong Liu, Lei Huang, Cheng Deng, Jiwen Lu, B. Lang

{"title":"Multi-View Complementary Hash Tables for Nearest Neighbor Search","authors":"Xianglong Liu, Lei Huang, Cheng Deng, Jiwen Lu, B. Lang","doi":"10.1109/ICCV.2015.132","DOIUrl":"https://doi.org/10.1109/ICCV.2015.132","url":null,"abstract":"Recent years have witnessed the success of hashing techniques in fast nearest neighbor search. In practice many applications (eg., visual search, object detection, image matching, etc.) have enjoyed the benefits of complementary hash tables and information fusion over multiple views. However, most of prior research mainly focused on compact hash code cleaning, and rare work studies how to build multiple complementary hash tables, much less to adaptively integrate information stemming from multiple views. In this paper we first present a novel multi-view complementary hash table method that learns complementarity hash tables from the data with multiple views. For single multi-view table, using exemplar based feature fusion, we approximate the inherent data similarities with a low-rank matrix, and learn discriminative hash functions in an efficient way. To build complementary tables and meanwhile maintain scalable training and fast out-of-sample extension, an exemplar reweighting scheme is introduced to update the induced low-rank similarity in the sequential table construction framework, which indeed brings mutual benefits between tables by placing greater importance on exemplars shared by mis-separated neighbors. Extensive experiments on three large-scale image datasets demonstrate that the proposed method significantly outperforms various naive solutions and state-of-the-art multi-table methods.","PeriodicalId":6633,"journal":{"name":"2015 IEEE International Conference on Computer Vision (ICCV)","volume":"120 1","pages":"1107-1115"},"PeriodicalIF":0.0,"publicationDate":"2015-12-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"77405825","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: 52

Fine-Grained Change Detection of Misaligned Scenes with Varied Illuminations 不同光照条件下不对齐场景的细粒度变化检测

2015 IEEE International Conference on Computer Vision (ICCV) Pub Date : 2015-12-07 DOI: 10.1109/ICCV.2015.149

Wei Feng, Fei-Peng Tian, Qian Zhang, N. Zhang, Liang Wan, Ji-zhou Sun

{"title":"Fine-Grained Change Detection of Misaligned Scenes with Varied Illuminations","authors":"Wei Feng, Fei-Peng Tian, Qian Zhang, N. Zhang, Liang Wan, Ji-zhou Sun","doi":"10.1109/ICCV.2015.149","DOIUrl":"https://doi.org/10.1109/ICCV.2015.149","url":null,"abstract":"Detecting fine-grained subtle changes among a scene is critically important in practice. Previous change detection methods, focusing on detecting large-scale significant changes, cannot do this well. This paper proposes a feasible end-to-end approach to this challenging problem. We start from active camera relocation that quickly relocates camera to nearly the same pose and position of the last time observation. To guarantee detection sensitivity and accuracy of minute changes, in an observation, we capture a group of images under multiple illuminations, which need only to be roughly aligned to the last time lighting conditions. Given two times observations, we formulate fine-grained change detection as a joint optimization problem of three related factors, i.e., normal-aware lighting difference, camera geometry correction flow, and real scene change mask. We solve the three factors in a coarse-to-fine manner and achieve reliable change decision by rank minimization. We build three real-world datasets to benchmark fine-grained change detection of misaligned scenes under varied multiple lighting conditions. Extensive experiments show the superior performance of our approach over state-of-the-art change detection methods and its ability to distinguish real scene changes from false ones caused by lighting variations.","PeriodicalId":6633,"journal":{"name":"2015 IEEE International Conference on Computer Vision (ICCV)","volume":"20 1","pages":"1260-1268"},"PeriodicalIF":0.0,"publicationDate":"2015-12-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"86937170","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: 32

Multiple Granularity Descriptors for Fine-Grained Categorization 用于细粒度分类的多粒度描述符

2015 IEEE International Conference on Computer Vision (ICCV) Pub Date : 2015-12-07 DOI: 10.1109/ICCV.2015.276

Dequan Wang, Zhiqiang Shen, Jie Shao, Wei Zhang, X. Xue, Zeyu Zhang

{"title":"Multiple Granularity Descriptors for Fine-Grained Categorization","authors":"Dequan Wang, Zhiqiang Shen, Jie Shao, Wei Zhang, X. Xue, Zeyu Zhang","doi":"10.1109/ICCV.2015.276","DOIUrl":"https://doi.org/10.1109/ICCV.2015.276","url":null,"abstract":"Fine-grained categorization, which aims to distinguish subordinate-level categories such as bird species or dog breeds, is an extremely challenging task. This is due to two main issues: how to localize discriminative regions for recognition and how to learn sophisticated features for representation. Neither of them is easy to handle if there is insufficient labeled data. We leverage the fact that a subordinate-level object already has other labels in its ontology tree. These \"free\" labels can be used to train a series of CNN-based classifiers, each specialized at one grain level. The internal representations of these networks have different region of interests, allowing the construction of multi-grained descriptors that encode informative and discriminative features covering all the grain levels. Our multiple granularity framework can be learned with the weakest supervision, requiring only image-level label and avoiding the use of labor-intensive bounding box or part annotations. Experimental results on three challenging fine-grained image datasets demonstrate that our approach outperforms state-of-the-art algorithms, including those requiring strong labels.","PeriodicalId":6633,"journal":{"name":"2015 IEEE International Conference on Computer Vision (ICCV)","volume":"58 1","pages":"2399-2406"},"PeriodicalIF":0.0,"publicationDate":"2015-12-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"85619473","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: 199

Automatic Thumbnail Generation Based on Visual Representativeness and Foreground Recognizability 基于视觉代表性和前景可识别性的缩略图自动生成

2015 IEEE International Conference on Computer Vision (ICCV) Pub Date : 2015-12-07 DOI: 10.1109/ICCV.2015.37

Jingwei Huang, Huarong Chen, Bin Wang, Stephen Lin

引用次数: 20

Rolling Shutter Super-Resolution 超分辨率卷帘式快门

2015 IEEE International Conference on Computer Vision (ICCV) Pub Date : 2015-12-07 DOI: 10.1109/ICCV.2015.71

Abhijith Punnappurath, Vijay Rengarajan, A. Rajagopalan

引用次数: 13

HICO: A Benchmark for Recognizing Human-Object Interactions in Images HICO:识别图像中人与物交互的基准

2015 IEEE International Conference on Computer Vision (ICCV) Pub Date : 2015-12-07 DOI: 10.1109/ICCV.2015.122

Yu-Wei Chao, Zhan Wang, Yugeng He, Jiaxuan Wang, Jia Deng

引用次数: 258

Where to Buy It: Matching Street Clothing Photos in Online Shops 哪里可以买到:网上商店的街头服装照片

2015 IEEE International Conference on Computer Vision (ICCV) Pub Date : 2015-12-07 DOI: 10.1109/ICCV.2015.382

M. Kiapour, Xufeng Han, S. Lazebnik, A. Berg, Tamara L. Berg

引用次数: 428

Model-Based Tracking at 300Hz Using Raw Time-of-Flight Observations 使用原始飞行时间观测的300Hz基于模型的跟踪

2015 IEEE International Conference on Computer Vision (ICCV) Pub Date : 2015-12-07 DOI: 10.1109/ICCV.2015.408

Jan Stühmer, Sebastian Nowozin, A. Fitzgibbon, R. Szeliski, Travis Perry, S. Acharya, D. Cremers, J. Shotton

{"title":"Model-Based Tracking at 300Hz Using Raw Time-of-Flight Observations","authors":"Jan Stühmer, Sebastian Nowozin, A. Fitzgibbon, R. Szeliski, Travis Perry, S. Acharya, D. Cremers, J. Shotton","doi":"10.1109/ICCV.2015.408","DOIUrl":"https://doi.org/10.1109/ICCV.2015.408","url":null,"abstract":"Consumer depth cameras have dramatically improved our ability to track rigid, articulated, and deformable 3D objects in real-time. However, depth cameras have a limited temporal resolution (frame-rate) that restricts the accuracy and robustness of tracking, especially for fast or unpredictable motion. In this paper, we show how to perform model-based object tracking which allows to reconstruct the object's depth at an order of magnitude higher frame-rate through simple modifications to an off-the-shelf depth camera. We focus on phase-based time-of-flight (ToF) sensing, which reconstructs each low frame-rate depth image from a set of short exposure 'raw' infrared captures. These raw captures are taken in quick succession near the beginning of each depth frame, and differ in the modulation of their active illumination. We make two contributions. First, we detail how to perform model-based tracking against these raw captures. Second, we show that by reprogramming the camera to space the raw captures uniformly in time, we obtain a 10x higher frame-rate, and thereby improve the ability to track fast-moving objects.","PeriodicalId":6633,"journal":{"name":"2015 IEEE International Conference on Computer Vision (ICCV)","volume":"40 1","pages":"3577-3585"},"PeriodicalIF":0.0,"publicationDate":"2015-12-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"88220051","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: 20

You are Here: Mimicking the Human Thinking Process in Reading Floor-Plans 你在这里:模仿人类阅读平面图的思维过程

2015 IEEE International Conference on Computer Vision (ICCV) Pub Date : 2015-12-07 DOI: 10.1109/ICCV.2015.255

Hang Chu, Dong Ki Kim, Tsuhan Chen

引用次数: 21