Related papers: SQLNet: Scale-Modulated Query and Localization Net…

Handling class imbalance remains a central challenge in machine learning, particularly in pattern recognition tasks where identifying rare but critical anomalies is of paramount importance. Traditional generative models often decouple data…

We propose a novel architecture for object classification, called Self-Attention Capsule Networks (SACN). SACN is the first model that incorporates the Self-Attention mechanism as an integral layer within the Capsule Network (CapsNet).…

Contextual information is vital in visual understanding problems, such as semantic segmentation and object detection. We propose a Criss-Cross Network (CCNet) for obtaining full-image contextual information in a very effective and efficient…

The main obstacle to weakly supervised semantic image segmentation is the difficulty of obtaining pixel-level information from coarse image-level annotations. Most methods based on image-level annotations use localization maps obtained from…

Salient instance segmentation is a new challenging task that received widespread attention in the saliency detection area. The new generation of saliency detection provides a strong theoretical and technical basis for video surveillance.…

Traditional change detection methods based on convolutional neural networks (CNNs) face the challenges of speckle noise and deformation sensitivity for synthetic aperture radar images. To mitigate these issues, we proposed a Multiscale…

Scene coordinates regression (SCR), i.e., predicting 3D coordinates for every pixel of a given image, has recently shown promising potential. However, existing methods remain limited to small scenes memorized during training, and thus…

Standard convolutional neural networks(CNNs) require consistent image resolutions in both training and testing phase. However, in practice, testing with smaller image sizes is necessary for fast inference. We show that trivially evaluating…

Object counting is a fundamental task in computer vision, with broad applicability in many real-world scenarios. Fully-supervised counting methods require costly point-level annotations per object. Few weakly-supervised methods leverage…

Self-attention mechanism recently achieves impressive advancement in Natural Language Processing (NLP) and Image Processing domains. And its permutation invariance property makes it ideally suitable for point cloud processing. Inspired by…

We aim to localize objects in images using image-level supervision only. Previous approaches to this problem mainly focus on discriminative object regions and often fail to locate precise object boundaries. We address this problem by…

Class-agnostic object counting aims to count object instances of an arbitrary class at test time. It is challenging but also enables many potential applications. Current methods require human-annotated exemplars as inputs which are often…

The spread of deepfakes poses significant security concerns, demanding reliable detection methods. However, diverse generation techniques and class imbalance in datasets create challenges. We propose CAE-Net, a Convolution- and…

Temporal action localization is a challenging computer vision problem with numerous real-world applications. Most existing methods require laborious frame-level supervision to train action localization models. In this work, we propose a…

Recent Semi-Supervised Object Detection (SS-OD) methods are mainly based on self-training, i.e., generating hard pseudo-labels by a teacher model on unlabeled data as supervisory signals. Although they achieved certain success, the limited…

The audio-visual event localization task requires identifying concurrent visual and auditory events from unconstrained videos within a network model, locating them, and classifying their category. The efficient extraction and integration of…

We formulate counting as a sequential decision problem and present a novel crowd counting model solvable by deep reinforcement learning. In contrast to existing counting models that directly output count values, we divide one-step…

We propose Sym-Net, a novel framework for Few-Shot Segmentation (FSS) that addresses the critical issue of intra-class variation by jointly learning both query and support prototypes in a symmetrical manner. Unlike previous methods that…

One of the key challenges of performing label prediction over a data stream concerns with the emergence of instances belonging to unobserved class labels over time. Previously, this problem has been addressed by detecting such instances and…

Class-agnostic counting (CAC) aims to estimate the number of objects in images without being restricted to predefined categories. However, while current exemplar-based CAC methods offer flexibility at inference time, they still rely heavily…