Related papers: Mining Conditional Part Semantics with Occluded Ex…

This paper is on human pose estimation using Convolutional Neural Networks. Our main contribution is a CNN cascaded architecture specifically designed for learning part relationships and spatial context, and robustly inferring pose even for…

As the intermediate level task connecting image captioning and object detection, visual relationship detection started to catch researchers' attention because of its descriptive power and clear structure. It detects the objects and captures…

Action recognition is a critical task for social robots to meaningfully engage with their environment. 3D human skeleton-based action recognition is an attractive research area in recent years. Although, the existing approaches are good at…

Recent graph convolutional neural networks (GCNs) have shown high performance in the field of human action recognition by using human skeleton poses. However, it fails to detect human-object interaction cases successfully due to the lack of…

Occluded person re-identification (Re-ID) in images captured by multiple cameras is challenging because the target person is occluded by pedestrians or objects, especially in crowded scenes. In addition to the processes performed during…

The task of Human-Object Interaction (HOI) detection is to detect humans and their interactions with surrounding objects, where transformer-based methods show dominant advances currently. However, these methods ignore the relationship among…

Semantic segmentation and instance level segmentation made substantial progress in recent years due to the emergence of deep neural networks (DNNs). A number of deep architectures with Convolution Neural Networks (CNNs) were proposed that…

The scarcity of labeled action data poses a considerable challenge for developing machine learning algorithms for robotic object manipulation. It is expensive and often infeasible for a robot to interact with many objects. Conversely,…

Human skeletons and RGB sequences are both widely-adopted input modalities for human action recognition. However, skeletons lack appearance features and color data suffer large amount of irrelevant depiction. To address this, we introduce…

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…

Comprehensive visual understanding requires detection frameworks that can effectively learn and utilize object interactions while analyzing objects individually. This is the main objective in Human-Object Interaction (HOI) detection task.…

Semantic segmentation is one of the core tasks in the field of computer vision, and its goal is to accurately classify each pixel in an image. The traditional Unet model achieves efficient feature extraction and fusion through an…

We propose a framework for the completely unsupervised learning of latent object properties from their interactions: the perception-prediction network (PPN). Consisting of a perception module that extracts representations of latent object…

In this work, we introduce a novel weakly supervised object detection (WSOD) paradigm to detect objects belonging to rare classes that have not many examples using transferable knowledge from human-object interactions (HOI). While WSOD…

In the scenario of one/multi-shot learning, conventional end-to-end learning strategies without sufficient supervision are usually not powerful enough to learn correct patterns from noisy signals. Thus, given a CNN pre-trained for object…

Occluded person re-identification is one of the challenging areas of computer vision, which faces problems such as inefficient feature representation and low recognition accuracy. Convolutional neural network pays more attention to the…

The interactions between human and objects are important for recognizing object-centric actions. Existing methods usually adopt a two-stage pipeline, where object proposals are first detected using a pretrained detector, and then are fed to…

For object detection, how to address the contradictory requirement between feature map resolution and receptive field on high-resolution inputs still remains an open question. In this paper, to tackle this issue, we build a novel…

Sensor-based human activity recognition is a key technology for many human-centered intelligent applications. However, this research is still in its infancy and faces many unresolved challenges. To address these, we propose a comprehensive…

Amodal recognition is the ability of the system to detect occluded objects. Most SOTA Visual Recognition systems lack the ability to perform amodal recognition. Few studies have achieved amodal recognition through passive prediction or…