Filters








9,083 Hits in 6.7 sec

Part Localization using Multi-Proposal Consensus for Fine-Grained Categorization [article]

Kevin J. Shih, Arun Mallya, Saurabh Singh, Derek Hoiem
2015 arXiv   pre-print
We present a simple deep learning framework to simultaneously predict keypoint locations and their respective visibilities and use those to achieve state-of-the-art performance for fine-grained classification  ...  We demonstrate the effectiveness of our accurate keypoint localization and visibility prediction on the fine-grained bird recognition task with and without ground truth bird bounding boxes, and outperform  ...  In addition, we gratefully acknowledge the support of NVIDIA Corporation with the donation of the Tesla K40 GPUs used for this research.  ... 
arXiv:1507.06332v1 fatcat:okkekpyemje4vnnbrkbbm4dfea

Part Localization using Multi-Proposal Consensus for Fine-Grained Categorization

Kevin J. Shih, Arun Mallya, Saurabh Singh, Derek Hoiem
2015 Procedings of the British Machine Vision Conference 2015  
Next, we demonstrate their effectiveness in the fine-grained categorization task by using the predicted keypoints to align head and torso regions, then extracting finetuned AlexNet features from the localized  ...  For effective fine-grained category detection, the keypoint localization methods must have high accuracy, low false positive rates, and low false negative rates.  ...  Next, we demonstrate their effectiveness in the fine-grained categorization task by using the predicted keypoints to align head and torso regions, then extracting finetuned AlexNet features from the localized  ... 
doi:10.5244/c.29.128 dblp:conf/bmvc/ShihMSH15 fatcat:arru5bcehrb5rldrtpuv3yhjqy

Aligned to the Object, not to the Image: A Unified Pose-aligned Representation for Fine-grained Recognition [article]

Pei Guo, Ryan Farrell
2018 arXiv   pre-print
The effectiveness of this paradigm relative to competing methods suggests the critical importance of disentangling pose and appearance for continued progress in fine-grained recognition.  ...  Dramatic appearance variation due to pose constitutes a great challenge in fine-grained recognition, one which recent methods using attention mechanisms or second-order statistics fail to adequately address  ...  Introduction What makes fine-grained visual categorization (FGVC), commonly referred to as fine-grained recognition, different from general visual categorization?  ... 
arXiv:1801.09057v4 fatcat:nwuvizkmebfbrhonnkfwkuhxdy

Classifying Object Manipulation Actions based on Grasp-types and Motion-Constraints [article]

Kartik Gupta, Darius Burschka, Arnav Bhavsar
2018 arXiv   pre-print
Our results justifies the efficacy of grasp attributes for the task of fine-grained and coarse-grained object manipulation action recognition.  ...  We propose to use grasp and motion-constraints information to recognise and understand action intention with different objects.  ...  Grasp attributes We propose to use coarse and fine level categorization of grasp types.  ... 
arXiv:1806.07574v1 fatcat:4vtq63rgxbbkjlr5zbalw2oufe

Towards Scene Understanding with Detailed 3D Object Representations

M. Zeeshan Zia, Michael Stark, Konrad Schindler
2014 International Journal of Computer Vision  
The fine-grained model, in conjunction with the explicit 3D scene model, further allows one to infer part-level occlusions between the modeled objects, as well as occlusions by other, unmodeled scene elements  ...  An object class - in our case cars - is modeled as a deformable 3D wireframe, which enables fine-grained modeling at the level of individual vertices and faces.  ...  , part occlusion estimation, fine-grained categorization, and even ultra-wide baseline matching.  ... 
doi:10.1007/s11263-014-0780-y fatcat:dtpfsces6jbj7lyckysrnlrgxa

Effectiveness of Grasp Attributes and Motion-Constraints for Fine-Grained Recognition of Object Manipulation Actions

Kartik Gupta, Darius Burschka, Arnav Bhavsar
2016 2016 IEEE Conference on Computer Vision and Pattern Recognition Workshops (CVPRW)  
We propose to leverage grasp and motion-constraints information, using a suitable representation, to recognize and understand action intention with different objects.  ...  The evaluation involves a) Different contemporary multi-class classifiers, and binary classifiers with one-vsone multi-class voting scheme, and b) Differential comparisons results based on subsets of attributes  ...  This analysis also helps to demonstrate that different classification frameworks, largely arrive at a consensus with respect to our hypothesis about using grasp and motion-constraints for fine-grained  ... 
doi:10.1109/cvprw.2016.156 dblp:conf/cvpr/GuptaBB16 fatcat:7hjrhcaaunb75ax5tfbnqtz7pu

Label Relation Graphs Enhanced Hierarchical Residual Network for Hierarchical Multi-Granularity Classification [article]

Jingzhou Chen, Peng Wang, Jian Liu, Yuntao Qian
2022 arXiv   pre-print
Experiments on three commonly used datasets demonstrate the effectiveness of our approach compared to the state-of-the-art HMC approaches and fine-grained visual classification (FGVC) methods exploiting  ...  If the observed label is at the leaf level, the combinatorial loss further imposes the multi-class cross-entropy loss to increase the weight of fine-grained classification loss.  ...  HMC with local multi-layer perceptrons (HMC-LMLP) [3] proposed to train a chain of multi-layer perceptron (MLP) networks, each corresponding to a hierarchical level.  ... 
arXiv:2201.03194v2 fatcat:vwnkqsqnhjbqbfqpszeyrwwilu

Synergistic Instance-Level Subspace Alignment for Fine-Grained Sketch-Based Image Retrieval

Ke Li, Kaiyue Pang, Yi-Zhe Song, Timothy M. Hospedales, Tao Xiang, Honggang Zhang
2017 IEEE Transactions on Image Processing  
We study the problem of fine-grained sketch-based image retrieval.  ...  To reduce the sketch-image gap when comparing low-level features, we also (iii) propose a novel method for instance-level domain-alignment, that exploits both subspace and instance-level cues to better  ...  Annotation To annotate our final fine-grained SBIR dataset, we again use crowdsourcing for both fine-grained attributes as well as parts which we will later use for strongly-supervised DPM training.  ... 
doi:10.1109/tip.2017.2745106 pmid:28858796 fatcat:dhp2a73iyvg67kk7yu5z2x6u7m

Effective Domain Knowledge Transfer with Soft Fine-tuning [article]

Zhichen Zhao, Bowen Zhang, Yuning Jiang, Li Xu, Lei Li, Wei-Ying Ma
2019 arXiv   pre-print
Furthermore, we propose a novel and light-weighted method, namely soft fine-tuning.  ...  Convolutional neural networks require numerous data for training.  ...  While in general there is a consensus that large-scale labeled datasets are needed to train CNNs with millions of learnable parameters, for some specific tasks, e.g. fine-grained categorization and infrared  ... 
arXiv:1909.02236v1 fatcat:nivysmbopfa25nsfz2cxa7psta

Multiple Sound Sources Localization from Coarse to Fine [article]

Rui Qian, Di Hu, Heinrich Dinkel, Mengyue Wu, Ning Xu, Weiyao Lin
2020 arXiv   pre-print
We then employ the localization results for sound separation and obtain comparable performance to existing methods.  ...  Code is available at https://github.com/shvdiwnkozbw/Multi-Source-Sound-Localization  ...  We use them for fine-grained feature alignment in next step. Fine-Grained Audiovisual Alignment.  ... 
arXiv:2007.06355v2 fatcat:36e5p5bcqbc6jdorflzkvrdfr4

Super-Fine Attributes with Crowd Prototyping

Daniel Martinho-Corbishley, Mark Nixon, John N. Carter
2018 IEEE Transactions on Pattern Analysis and Machine Intelligence  
Inspired by fine-grained and relative attributes, we introduce super-fine attributes, which now describe multiple, integral concepts of a single trait as multi-dimensional perceptual coordinates.  ...  Crowd prototyping facilitates efficient crowdsourcing of super-fine labels by pre-discovering salient perceptual concepts for prototype matching.  ...  Proposal. We introduce super-fine attributes. Similar to fine-grained and relative attributes, super-fine attributes describe both clear and subtle discriminations between images.  ... 
doi:10.1109/tpami.2018.2836900 pmid:29994759 fatcat:z7cf52y4jrdmnl7fke5yvekshe

Grapy-ML: Graph Pyramid Mutual Learning for Cross-Dataset Human Parsing

Haoyu He, Jing Zhang, Qiming Zhang, Dacheng Tao
2020 PROCEEDINGS OF THE THIRTIETH AAAI CONFERENCE ON ARTIFICIAL INTELLIGENCE AND THE TWENTY-EIGHTH INNOVATIVE APPLICATIONS OF ARTIFICIAL INTELLIGENCE CONFERENCE  
By making use of the multi-granularity labels, Grapy-ML learns a more discriminative feature representation and achieves state-of-the-art performance, which is demonstrated by extensive experiments on  ...  Human parsing, or human body part semantic segmentation, has been an active research topic due to its wide potential applications.  ...  GCN represents using graph convolutions for graph context reasoning in the proposed GPM. GCR represents using self-attention for graph context reasoning in the proposed GPM.  ... 
doi:10.1609/aaai.v34i07.6728 fatcat:juvtu6haingcxgoaabsydtbfaa

A Gated Peripheral-Foveal Convolutional Neural Network for Unified Image Aesthetic Prediction [article]

Xiaodan Zhang, Xinbo Gao, Wen Lu, Lihuo He
2019 arXiv   pre-print
The peripheral vision is used for perceiving the broad spatial scene and selecting the attended regions for the fovea.  ...  Learning fine-grained details is a key issue in image aesthetic assessment.  ...  [18] proposed a multi-patch aggregation network (DMA-Net) to extract local fine-grained features from multiple randomly cropped patches.  ... 
arXiv:1812.07989v2 fatcat:6qvnf6ex6nd4fesdiccndf43jq

Grapy-ML: Graph Pyramid Mutual Learning for Cross-dataset Human Parsing [article]

Haoyu He, Jing Zhang, Qiming Zhang, Dacheng Tao
2019 arXiv   pre-print
By making use of the multi-granularity labels, Grapy-ML learns a more discriminative feature representation and achieves state-of-the-art performance, which is demonstrated by extensive experiments on  ...  Human parsing, or human body part semantic segmentation, has been an active research topic due to its wide potential applications.  ...  GCN represents using graph convolutions for graph context reasoning in the proposed GPM.  ... 
arXiv:1911.12053v1 fatcat:ugfuo5dp35hr7i5lpkrnrhfc6m

Who Likes What? — SplitLBI in Exploring Preferential Diversity of Ratings

Qianqian Xu, Jiechao Xiong, Zhiyong Yang, Xiaochun Cao, Qingming Huang, Yuan Yao
2020 PROCEEDINGS OF THE THIRTIETH AAAI CONFERENCE ON ARTIFICIAL INTELLIGENCE AND THE TWENTY-EIGHTH INNOVATIVE APPLICATIONS OF ARTIFICIAL INTELLIGENCE CONFERENCE  
Such a multi-level model, enables us to simultaneously learn a coarse-grained social preference function together with a fine-grained personalized diversity.  ...  It provides us prediction power for the choices of new users on new alternatives.  ...  Methodology In this section, we systematically introduce the methodology for coarse-to-fine grained preference learning.  ... 
doi:10.1609/aaai.v34i01.5359 fatcat:bz5yhmf3bzahjamc2od75q3ayq
« Previous Showing results 1 — 15 out of 9,083 results