前不久CVPR的结果出来了,首先恭喜我一个已经毕业工作的师弟中了一篇文章。完整的文章列表已经在CVPR的主页上公布了(链接),今天把其中一些感兴趣的整理一下,虽然论文下载的链接大部分还都没出来,不过可以follow最新动态。等下载链接出来的时候一一补上。
由于没有下载链接,所以只能通过题目和作者估计一下论文的内容。难免有偏差,等看了论文以后再修正。
(papers on web 已经收录了部分文章的下载链接,大家可以过去下载。传送门)
显著性
Saliency Aggregation: A Data-driven Approach Long Mai, Yuzhen Niu, Feng Liu 现在还没有搜到相关的资料,应该是多线索的自适应融合来进行显著性检测的
PISA: Pixelwise Image Saliency by Aggregating Complementary Appearance Contrast Measures with Spatial Priors Keyang Shi, Keze Wang, Jiangbo Lu, Liang Lin 这里的两个线索看起来都不新,应该是集成框架比较好。而且像素级的,估计能达到分割或者matting的效果
Looking Beyond the Image: Unsupervised Learning for Object Saliency and Detection Parthipan Siva, Chris Russell, Tao Xiang, Lourdes Agapito 基于学习的的显著性检测
Learning video saliency from human gaze using candidate selection Dmitry Rudoy, Dan Goldman, Eli Shechtman, Lihi Zelnik-Manor 这是一个做视频显著性的,估计是选择显著的视频目标
Hierarchical Saliency Detection Qiong Yan, Li Xu, Jianping Shi, Jiaya Jia Jiaya Jia的学生也开始做显著性了,多尺度的方法
Saliency Detection via Graph-Based Manifold Ranking Chuan Yang, Lihe Zhang, Huchuan Lu, Ming-Hsuan Yang, Xiang Ruan 这个应该是扩展了那个经典的 graph based saliency,应该是用到了显著性传播的技巧
Salient object detection: a discriminative regional feature integration approach Huaizu Jiang, Jingdong Wang, Zejian Yuan, Yang Wu, Nanning Zheng 一个多特征自适应融合的显著性检测方法
Submodular Salient Region Detection Zhuolin Jiang, Larry Davis 又是大牛下面的文章,提法也很新颖,用了submodular。第一作者今年有3篇CVPR文章
图像分割
Efficient Object Detection and Segmentation for Fine-Grained Recognition Anelia Angelova, Shenghuo Zhu 这个文章的卖点应该在efficient上面,是一个高效的算法。
Image Segmentation by Cascaded Region Allglomeration Zhile Ren, Gregory Shakhnarovich 看标题应该是一种新的区域生长类似的算法,多层模型的应用值得关注。
Analyzing Semantic Segmentation Using Human-Machine Hybrid CRFs Roozbeh Mottaghi, Sanja Fidler, Jian Yao, Raquel Urtasun, Devi Parikh 这个方法应该是把人机交互放到了条件随机场里面,实际上以前很多文章这么做过,很好奇这篇文章用了什么办法。这个研究组中了4篇。
Unsupervised Joint Object Discovery and Segmentation in Internet Images Michael Rubinstein, Armand Joulin, Ce Liu, Johannes Kopf 给予互联网图像的无监督目标检测和分割,应该是用到了海量数据中目标会重复出现这一基本属性。
Weakly-Supervised Bi-Clustering for Image Semantic Segmentation Yang Liu, Jing Liu, Zechao Li, Hanqing Lu 一个二元聚类问题,感觉应该是前景背景分割
Deep Learning Shape Priors for Object Segmentation Fei Chen, Huimin Yu, Roland Hu, Xunxun Zeng 通过deep learning学习形状模型
SCALPEL: Segmentation CAscades with Localized Priors and Efficient Learning David Weiss, Ben Taskar Ben Taskar是宾夕法尼亚大学的教授,他前年还获得了一个美国官方的奖项
Top-down Segmentation of Non-rigid Visual Objects using Derivative-based Search on Sparse Manifolds
Jacinto Nascimento, Gustavo Carneiro 自上而下的分割,是用到了模型学习吗?
Probabilistic Graphlet Cut: Exploiting Spatial Structure Cue for Weakly Supervised Image Segmentation
Luming Zhang, Mingli Song, Zicheng Liu, Xiao Liu, Jiajun Bu, Chun Chen 现在新名词越来越多了,弱监督的分割,效果应该不错。
Graph Transduction Learning with Connectivity Constraints with Application to Multiple Foreground Cosegmentation Tianyang Ma, Longin Jan Latecki 天普大学的,基本每年都能见到他的paper
Towards Fast and Accurate Segmentation Camillo Taylor 这个应该是宾大的CJ Taylor教授,他竟然一个人写了一篇
A Principled Deep Random Field Model for Image Segmentation Pushmeet Kohli, Anton Osokin, Stefanie Jegelka 这个也是大牛的paper
视频处理
Video Object Segmentation through Spatially Accurate and Temporally Dense Extraction of Primary Object Regions Dong Zhang, Omar Javed, Mubarak Shah ORAL 从视频中分割出主要目标的方法。既然是Oral,应该值得好好学习。
Fast Rigid Motion Segmentation via Incrementally-Complex Local Models Fernando Flores-Mangas, Allan Jepson 快速的运动分割,实时性的东西我都比较感兴趣。
Multi-Class Video Co-Segmentation with a Generative Multi-Video Model Wei-Chen Chiu, Mario Fritz 这个难道是将几个视频放一起进行联合分割?
Discriminative Segment Annotation in Weakly Labeled Video Kevin Tang, Rahul Sukthankar, Jay Yagnik,Li Fei-Fei ORAL 视频标注,Li Feifei做这个方向挺长时间了,看看这篇oral文章新的idea
Representing Videos using Mid-level Discriminative Patches Arpit Jain, Abhinav Gupta, Mikel Rodriguez, Larry Davis 新的视频描述方法,应该可以用在视频分割里面
Video Editing with Temporal, Spatial and Appearance Consistency Xiaojie Guo, Xiaochun Cao, Yi Ma Ma yi的paper,关于视频编辑的,里面应该也是主要用到了视频分割的技术。
Ensemble Video Object Cut in Highly Dynamic Scenes Xiaobo Ren, Tony Han, Zhihai He 在高度动态的场景中,时间一致性不好保证,视频分割应该会变得困难。
Hierarchical Video Representation with Trajectory Binary Partition Tree Guillem Palou, Philippe Salembier 看题目挺有意思,轨迹的二分树
Adherent Raindrop Detection and Removal in Video Shaodi You, Rei Kawakami, Robby Tan, Katsushi Ikeuchi 来自日本的一篇有趣的paper,视频中的雨点检测与消除
跟踪
Tracking Sports Players with Context-Conditioned Motion Models Jingchen Liu, Peter Carr, Robert Collins, Yanxi Liu ORAL Bob Collins的paper,使用运动模型进行运动员跟踪的。
Multi-target Tracking by Lagrangian Relaxation to Min-Cost Network Flow Asad Butt, Robert Collins ORAL 看来Collins教授已经称霸tracking领域了,直接两篇oral
Physically Plausible 3D Scene Tracking: The Single Actor Hypothesis Nikolaos Kyriazis, Antonis Argyros ORAL 关于3D场景跟踪的,一篇oral
Structure Preserving Object Tracking Lu Zhang, Laurens van der Maaten ORAL 保持结构的跟踪,不知道具体指的是哪方面的结构,骨架吗?
Harry Potter's Marauder's Map: Localizing and Tracking Multiple Persons-of-Interest by Nonnegative Discretization Shoou-I Yu, Yi Yang, Alexander Hauptmann 都扯上哈利波特了,看看吧
Detection- and Trajectory-Level Exclusion in Multiple Object Tracking Anton Andriyenko, Stefan Roth, Konrad Schindler 这个应该是重在利用轨迹进行目标的关联上
Robust Real-Time Tracking of Multiple Objects by Volumetric Mass Densities Horst Possegger, Sabine Sternig, Thomas Mauthner, Peter Roth, Horst Bischof 不知道这个质量密度是什么意思,是不是统计被跟踪的目标形成的volume中概率密度的总和之类
Learning Compact Binary Codes for Visual Tracking Xi Li, Chunhua Shen, Anthony Dick, Anton van den Hengel 题目看起来有意思
Part-based Visual Tracking with Online Latent Structural Learning Rui Yao, Qinfeng Shi, Chunhua Shen, Yanning Zhang, Anton van den Hengel 这个paper是西工大的吧,基于部件的在线跟踪
Self-paced learning for long-term tracking James Supancic III, Deva Ramanan 这个也有点意思,应该是分析长时间跟踪中,模型的更新频率问题。
Joint Multi-Camera Reconstruction and Multi-Object Tracking in a Global Unified Optimization Framework
Martin Hofmann, Daniel Wolf 利用多相机做多目标跟踪和场景重建
Least Soft-thresold Squares Tracking Dong Wang, Huchuan Lu, Ming-Hsuan Yang
Tracking People and Their Objects Tobias Baumgartner, Dennis Mitzel, Bastian Leibe 是要跟踪人和他们携带的物品吗?
Tracking Human Pose by Tracking Symmetric Parts Varun Ramakrishna, Yaser Sheikh, Takeo Kanade Kanade教授的paper,利用对称性来跟踪人。
立体视觉
Accurate Localization of 3D Objects from RGB-D Data using Segmentation Hypotheses Byung-soo Kim, Shili Xu, Silvio Savarese 随着kinect的普及,RGB-D数据越来越受关注了。
Megastereo: Constructing High-Resolution Stereo Panoramas Christian Richardt, Yael Pritch, Henning Zimmer, Alexander Sorkine-Hornung ORAL 创建高分辨率的立体全景图,应该有市场前景
Scene-SIRFS: Intrinsic Scene Properties from a Single RGB-D Image Jonathan Barron, Jitendra Malik ORAL
Perceptual Organization and Recognition of Indoor Scenes from RGBD Images Saurabh Gupta, Pablo Arbelaez, Jitendra Malik ORAL 连着两篇J.Malik教授的Oral,都是关于RGBD图像的,看来他们现在对这个方面很感兴趣
A New Perspective on Uncalibrated Photometric Stereo Thoma Papadhimitri, Paolo Favaro 不用标定的,应该适合于手持设备。
In Defense of 3D-Label Stereo Carl Olsson, Johannes Ulen, Yuri Boykov 大牛的paper,关注之
Recovering Stereo Pairs from Anaglyphs Armand Joulin, Sing Bing Kang
Segment-Tree based Cost Aggregation for Stereo Matching Xing Mei, Xun Sun, Weiming Dong, Xiaopeng ZHANG 基于分割树的立体匹配
其他
Integrating Grammar and Segmentation for Human Pose Estimation Brandon Rothrock, Seyoung Park,Song Chun Zhu 做姿态估计的,我自己没做过这方面,不过很想了解一下。
Watching Unlabeled Video Helps Learn New Human Actions from Very Few Labeled Snapshots Chao-Yeh Chen, Kristen Grauman ORAL paper的题目很有意思,美女教授的Oral,关注一下
Context-Aware Modeling and Recognition of Activities in Video Amit Roy-Chowdhury, YINGYING ZHU ORAL 和行为识别有关系的,用到了上下文信息。
Recognize Human Activities from Partially Observed Videos Yu Cao, Daniel Barrett, Andrei Barbu, Siddharth Narayanaswamy, Haonan Yu, Aaron Michaux, Yuewei Lin, Sven Dickinson, Jeffrey Siskind, Song Wang 关注这篇paper主要是因为第一次看到CVPR的论文有这么多作者。(10个作者!)
Large Displacement Optical Flow from Nearest Neighbor Fields Zhuoyuan Chen, Hailin Jin, Zhe Lin, Scott Cohen, Ying Wu wu ying 提了新的LDOF,不知道会不会比Brox的快
Better exploiting motion for better action recognition Mihir Jain, Herve Jegou, Patrick Bouthemy 名字起的有吸引力,关注一下
Motionlets: Mid-Level 3D Parts for Human Motion Recognition LiMin Wang, Qiao Yu, Xiaoou Tang 中层的3D部件
Motion Estimation for Self-Driving Cars With a Generalized Camera Gim Hee Lee, Friedrich Fraundorfer,marc pollefeys 基于无人驾驶汽车的视觉运动估计,这个我很感兴趣。
Deformable Spatial Pyramid Matching for Fast Dense Correspondences Jaechul Kim, Ce Liu, Fei Sha,Kristen Grauman 稠密匹配的,Ce Liu 和 Grauman合作的
Pose from Flow and Flow from Pose Katerina Fragkiadaki, Han Hu, jianbo shi 以前一起合作过的,Jianbo Shi老师的学生
Correlation Filters for Improved Object Alignment Vishnu Naresh Boddeti, Takeo Kanade, Vijayakumar Bhagavatula Kanade教授的paper,目标对齐
Articulated Pose Estimation using Discriminative Armlet Classifiers Georgia Gkioxari, Pablo Arbelaez, Lubomir Bourdev, Jitendra Malik