Related papers: Beyond the Camera: Neural Networks in World Coordi…

Currently, video behavior recognition is one of the most foundational tasks of computer vision. The 2D neural networks of deep learning are built for recognizing pixel-level information such as images with RGB, RGB-D, or optical flow…

Annotating a large number of training images is very time-consuming. In this background, this paper focuses on learning from easy-to-acquire web data and utilizes the learned model for fine-grained image classification in labeled datasets.…

Neural networks outperform kernel methods, sometimes by orders of magnitude, e.g. on staircase functions. This advantage stems from the ability of neural networks to learn features, adapting their hidden representations to better capture…

Convolutional networks are considered shift invariant, but it was demonstrated that their response may vary according to the exact location of the objects. In this paper we will demonstrate that most commonly investigated datasets have a…

We propose novel motion representations for animating articulated objects consisting of distinct parts. In a completely unsupervised manner, our method identifies object parts, tracks them in a driving video, and infers their motions by…

In this paper, we propose Global Context Convolutional Network (GCCN) for visual recognition. GCCN computes global features representing contextual information across image patches. These global contextual features are defined as local…

In this work we present a novel framework that uses deep learning to predict object feature points that are out-of-view in the input image. This system was developed with the application of model-based tracking in mind, particularly in the…

3D Convolutional Neural Network (3D CNN) captures spatial and temporal information on 3D data such as video sequences. However, due to the convolution and pooling mechanism, the information loss seems unavoidable. To improve the visual…

Current methods aggregate multi-level features or introduce edge and skeleton to get more refined saliency maps. However, little attention is paid to how to obtain the complete salient object in cluttered background, where the targets are…

Deep networks have been successfully applied to visual tracking by learning a generic representation offline from numerous training images. However the offline training is time-consuming and the learned generic representation may be less…

We show how to augment any convolutional network with an attention-based global map to achieve non-local reasoning. We replace the final average pooling by an attention-based aggregation layer akin to a single transformer block, that…

Convolutional networks for image classification progressively reduce resolution until the image is represented by tiny feature maps in which the spatial structure of the scene is no longer discernible. Such loss of spatial acuity can limit…

This article trained a network for perceiving three-dimensional motion information of binocular vision target, which can provide real-time three-dimensional coordinate, velocity, and acceleration, and has a basic spatiotemporal perception…

In this paper, we introduce a novel network, called discriminative feature network (DFNet), to address the unsupervised video object segmentation task. To capture the inherent correlation among video frames, we learn discriminative features…

Convolutional Neural Networks (CNNs) are extremely efficient, since they exploit the inherent translation-invariance of natural images. However, translation is just one of a myriad of useful spatial transformations. Can the same efficiency…

We explore total scene capture -- recording, modeling, and rerendering a scene under varying appearance such as season and time of day. Starting from internet photos of a tourist landmark, we apply traditional 3D reconstruction to register…

Robot policy learning benefits from world-action models that capture environment dynamics, but pixel-level prediction entangles dynamics with nuisance factors such as lighting and texture, making learned representations vulnerable to…

Video frame interpolation is a challenging problem because there are different scenarios for each video depending on the variety of foreground and background motion, frame rate, and occlusion. It is therefore difficult for a single network…

Scene parsing is an important and challenging prob- lem in computer vision. It requires labeling each pixel in an image with the category it belongs to. Tradition- ally, it has been approached with hand-engineered features from color…

Standard losses for training deep segmentation networks could be seen as individual classifications of pixels, instead of supervising the global shape of the predicted segmentations. While effective, they require exact knowledge of the…