the proceedings contain 781 papers. the topics discussed include: exclusivity-consistency regularized multi-view subspace clustering;borrowing treasures from the wealthy: deep transfer learning through selective joint...
the proceedings contain 781 papers. the topics discussed include: exclusivity-consistency regularized multi-view subspace clustering;borrowing treasures from the wealthy: deep transfer learning through selective joint fine-tuning;the more you know: using knowledge graphs for image classification;dynamic edge-conditioned filters in convolutional neural networks on graphs;convolutional neural network architecture for geometric matching;deep affordance-grounded sensorimotor object recognition;on compressing deep models by low rank and sparse decomposition;unsupervised pixel-level domain adaptation with generative adversarial networks;photo-realistic single image super-resolution using a generative adversarial network;a practical method for fully automatic intrinsic camera calibration using directionally encoded light;elastic shape-from-template with spatially sparse deforming forces;and distinguishing the indistinguishable: exploring structural ambiguities via geodesic context.
the proceedings contain 280 papers. the topics discussed include: the role of synchronic causal conditions in visual knowledge learning;attention-based natural language person retrieval;Singlets: multi-resolution moti...
ISBN:
(纸本)9781538607336
the proceedings contain 280 papers. the topics discussed include: the role of synchronic causal conditions in visual knowledge learning;attention-based natural language person retrieval;Singlets: multi-resolution motion singularities for soccer video abstraction;hockey action recognition via integrated stacked hourglass network;extraction and classification of diving clips from continuous video footage;accurate and efficient 3D human pose estimation algorithm using single depth images for pose analysis in golf;athlete pose estimation by a global-local network;continuous video to simple signals for swimming stroke detection with convolutional neural networks;application of computervision and vector space model for tactical movement classification in badminton;automatic tactical adjustment in real-time: modeling adversary formations with radon-cumulative distribution transform and canonical correlation analysis;infrared variation optimized deep convolutional neural network for robust automatic ground target recognition;an algorithm for parallel reconstruction of jointly sparse tensors with applications to hyperspectral imaging;deep heterogeneous face recognition networks based on cross-modal distillation and an equitable distance metric;face presentation attack with latex masks in multispectral videos;privacy-preserving understanding of human body orientation for smart meetings;and fast, accurate thin-structure obstacle detection for autonomous mobile robots.
We propose the residual expansion (RE) algorithm: a global (or near-global) optimization method for nonconvex least squares problems. Unlike most existing nonconvex optimization techniques, the RE algorithm is not bas...
详细信息
ISBN:
(纸本)9781538604571
We propose the residual expansion (RE) algorithm: a global (or near-global) optimization method for nonconvex least squares problems. Unlike most existing nonconvex optimization techniques, the RE algorithm is not based on either stochastic or multi-point searches;therefore, it can achieve fast global optimization. Moreover, the RE algorithm is easy to implement and successful in highdimensional optimization. the RE algorithm exhibits excellent empirical performance in terms of k-means clustering, point-set registration, optimized product quantization, and blind image deblurring.
In this paper we study the problem of automatically generating polynomial solvers for minimal problems. the main contribution is a new method for finding small elimination templates by making use of the syzygies (i.e....
详细信息
ISBN:
(纸本)9781538604571
In this paper we study the problem of automatically generating polynomial solvers for minimal problems. the main contribution is a new method for finding small elimination templates by making use of the syzygies (i.e. the polynomial relations) that exist between the original equations. Using these syzygies we can essentially parameterize the set of possible elimination templates. We evaluate our method on a wide variety of problems from geometric computervision and show improvement compared to both handcrafted and automatically generated solvers. Furthermore we apply our method on two previously unsolved relative orientation problems.
Hyperspectral imaging is a useful technique for various computervision tasks such as material recognition. However, such technique usually requires an expensive and professional setup and is time-consuming because a ...
详细信息
ISBN:
(纸本)9781538604571
Hyperspectral imaging is a useful technique for various computervision tasks such as material recognition. However, such technique usually requires an expensive and professional setup and is time-consuming because a conventional hyperspectral image consists of a large number of observations. In this paper, we propose a novel technique of one-shot hyperspectral imaging using faced reflectors on which color filters are attached. the key idea is based on the principle that each of multiple reflections on the filters has a different spectrum, which allows us to observe multiple intensities through different spectra. Our technique can be implemented either by a coupled mirror or a kaleidoscope geometry. Experimental results show that our technique is capable of accurately capturing a hyperspectral image by using a coupled mirror setup which is readily available.
Convolutional neural networks (CNNs) have shown great success in computervision, approaching human-level performance when trained for specific tasks via application-specific loss functions. In this paper, we propose ...
详细信息
ISBN:
(纸本)9781538604571
Convolutional neural networks (CNNs) have shown great success in computervision, approaching human-level performance when trained for specific tasks via application-specific loss functions. In this paper, we propose a method for augmenting and training CNNs so that their learned features are compositional. It encourages networks to form representations that disentangle objects from their surroundings and from each other, thereby promoting better generalization. Our method is agnostic to the specific details of the underlying CNN to which it is applied and can in principle be used with any CNN. As we show in our experiments, the learned representations lead to feature activations that are more localized and improve performance over non-compositional baselines in object recognition tasks.
Person recognition methods that use multiple body regions have shown significant improvements over traditional face-based recognition. One of the primary challenges in full-body person recognition is the extreme varia...
详细信息
ISBN:
(纸本)9781538604571
Person recognition methods that use multiple body regions have shown significant improvements over traditional face-based recognition. One of the primary challenges in full-body person recognition is the extreme variation in pose and view point. In this work, (i) we present an approach that tackles pose variations utilizing multiple models that are trained on specific poses, and combined using pose-aware weights during testing. (ii) For learning a person representation, we propose a network that jointly optimizes a single loss over multiple body regions. (iii) Finally, we introduce new benchmarks to evaluate person recognition in diverse scenarios and show significant improvements over previously proposed approaches on all the benchmarks including the photo album setting of PIPA.
this paper presents a general ConvNet architecture for video action recognition based on multiplicative interactions of spacetime features. Our model combines the appearance and motion pathways of a two-stream archite...
详细信息
ISBN:
(纸本)9781538604571
this paper presents a general ConvNet architecture for video action recognition based on multiplicative interactions of spacetime features. Our model combines the appearance and motion pathways of a two-stream architecture by motion gating and is trained end-to-end. We theoretically motivate multiplicative gating functions for residual networks and empirically study their effect on classification accuracy. To capture long-term dependencies we inject identity mapping kernels for learning temporal relationships. Our architecture is fully convolutional in spacetime and able to evaluate a video in a single forward pass. Empirical investigation reveals that our model produces state-of-the-art results on two standard action recognition datasets.
暂无评论