Related papers: Hierarchical Context Embedding for Region-based Ob…

Attribute recognition is a crucial but challenging task due to viewpoint changes, illumination variations and appearance diversities, etc. Most of previous work only consider the attribute-level feature embedding, which might perform poorly…

Jointly integrating aspect ratio and context has been extensively studied and shown performance improvement in traditional object detection systems such as the DPMs. It, however, has been largely ignored in deep neural network based…

Remote sensing image scene classification remains a challenging task, primarily due to the complex spatial structures and multi-scale characteristics of ground objects. Although CNN-based methods excel at extracting local inductive biases,…

Scene graph generation aims to produce structured representations for images, which requires to understand the relations between objects. Due to the continuous nature of deep neural networks, the prediction of scene graphs is divided into…

Transformer-based detectors have advanced small-object detection, but they often remain inefficient and vulnerable to background-induced query noise, which motivates deep decoders to refine low-quality queries. We present HELP…

Spatial contexts, such as the backgrounds and surroundings, are considered critical in Human-Object Interaction (HOI) recognition, especially when the instance-centric foreground is blurred or occluded. Recent advancements in HOI detectors…

Global context information is vital in visual understanding problems, especially in pixel-level semantic segmentation. The mainstream methods adopt the self-attention mechanism to model global context information. However, pixels belonging…

Despite advances in object detection, aerial imagery remains a challenging domain, as models often fail to generalize across variations in spatial resolution, scene composition, and semantic label coverage. Differences in geographic…

Scene labeling is the problem of assigning an object label to each pixel. It unifies the image segmentation and object recognition problems. The importance of using contextual information in scene labeling frameworks has been widely…

Object categories inherently form a hierarchy with different levels of concept abstraction, especially for fine-grained categories. For example, birds (Aves) can be categorized according to a four-level hierarchy of order, family, genus,…

Current Transformer-based methods for small object detection continue emerging, yet they have still exhibited significant shortcomings. This paper introduces HeatMap Position Embedding (HMPE), a novel Transformer Optimization technique that…

Object detection is one of the most active areas in computer vision, which has made significant improvement in recent years. Current state-of-the-art object detection methods mostly adhere to the framework of regions with convolutional…

Recent progress on salient object detection mainly aims at exploiting how to effectively integrate convolutional side-output features in convolutional neural networks (CNN). Based on this, most of the existing state-of-the-art saliency…

Reasoning about images/objects and their hierarchical interactions is a key concept for the next generation of computer vision approaches. Here we present a new framework to deal with it through a visual hierarchical context-based…

The task of instance segmentation in remote sensing images, aiming at performing per-pixel labeling of objects at instance level, is of great importance for various civil applications. Despite previous successes, most existing instance…

Object recognition in the presence of background clutter and distractors is a central problem both in neuroscience and in machine learning. However, the performance level of the models that are inspired by cortical mechanisms, including…

Interpretable-by-design models are gaining traction in computer vision because they provide faithful explanations for their predictions. In image classification, these models typically recover human-interpretable concepts from an image and…

Modern deep neural networks remain challenging to interpret due to the opacity of their latent representations, impeding model understanding, debugging, and debiasing. Concept Embedding Models (CEMs) address this by mapping inputs to…

Recognizing objects from simultaneously sensed photometric (RGB) and depth channels is a fundamental yet practical problem in many machine vision applications such as robot grasping and autonomous driving. In this paper, we address this…

Human-Object Interaction (HOI) detection aims to simultaneously localize human-object pairs and recognize their interactions. While recent two-stage approaches have made significant progress, they still face challenges due to incomplete…