Related papers: SPAN: Spatial Pyramid Attention Network forImage M…

In the face of scarcity in detailed training annotations, the ability to perform object localization tasks in real-time with weak-supervision is very valuable. However, the computational cost of generating and evaluating region proposals is…

Recognition of human actions and associated interactions with objects and the environment is an important problem in computer vision due to its potential applications in a variety of domains. The most versatile methods can generalize to…

Attentive Neural Process (ANP) improves the fitting ability of Neural Process (NP) and improves its prediction accuracy, but the higher time complexity of the model imposes a limitation on the length of the input sequence. Inspired by…

This paper studies introducing viewpoint invariant feature representations in existing action recognition architecture. Despite significant progress in action recognition, efficiently handling geometric variations in large-scale datasets…

Deep convolutional neural networks (DCNNs) have achieved great success in monocular depth estimation (MDE). However, few existing works take the contributions for MDE of different levels feature maps into account, leading to inaccurate…

In image segmentation, there is often more than one plausible solution for a given input. In medical imaging, for example, experts will often disagree about the exact location of object boundaries. Estimating this inherent uncertainty and…

Recently, attentional arbitrary style transfer methods have been proposed to achieve fine-grained results, which manipulates the point-wise similarity between content and style features for stylization. However, the attention mechanism…

State space models (SSMs) have recently emerged as an alternative to transformers due to their unique ability of modeling global relationships in text with linear complexity. However, their success in vision tasks has been limited due to…

We propose a scalable, provably accurate method for localizing an unknown number of multiple axis-aligned anomalous patches in spatial data under a general class of spatial dependence. Motivated by the practical need to detect localized…

Superpixels have become very popular in many computer vision applications. Nevertheless, they remain underexploited since the superpixel decomposition may produce irregular and non stable segmentation results due to the dependency to the…

Detecting persons using a 2D LiDAR is a challenging task due to the low information content of 2D range data. To alleviate the problem caused by the sparsity of the LiDAR points, current state-of-the-art methods fuse multiple previous scans…

In this paper, we propose Double Supervised Network with Attention Mechanism (DSAN), a novel end-to-end trainable framework for scene text recognition. It incorporates one text attention module during feature extraction which enforces the…

Hyperspectral unmixing is a critical yet challenging task in hyperspectral image interpretation. Recently, great efforts have been made to solve the hyperspectral unmixing task via deep autoencoders. However, existing networks mainly focus…

Recent algorithms for image manipulation detection almost exclusively use deep network models. These approaches require either dense pixelwise groundtruth masks, camera ids, or image metadata to train the networks. On one hand, constructing…

Gradient clipping is widely used to stabilize deep network training, but its formulation as a hard, fixed threshold limits flexibility and ignores gradient distribution dynamics. We propose SPAMP (Statistical Per-layer Adaptive Modulation…

High-quality image inpainting requires filling missing regions in a damaged image with plausible content. Existing works either fill the regions by copying image patches or generating semantically-coherent patches from region context, while…

We propose spatially-adaptive normalization, a simple but effective layer for synthesizing photorealistic images given an input semantic layout. Previous methods directly feed the semantic layout as input to the deep network, which is then…

Salient object detection has achieved great improvement by using the Fully Convolution Network (FCN). However, the FCN-based U-shape architecture may cause the dilution problem in the high-level semantic information during the up-sample…

Vehicle re-identification (re-ID) focuses on matching images of the same vehicle across different cameras. It is fundamentally challenging because differences between vehicles are sometimes subtle. While several studies incorporate…

To accelerate deep CNN models, this paper proposes a novel spatially adaptive framework that can dynamically generate pixel-wise sparsity according to the input image. The sparse scheme is pixel-wise refined, regional adaptive under a…