Related papers: Predicting Human Interaction via Relative Attentio…

We address the challenging task of anticipating human-object interaction in first person videos. Most existing methods ignore how the camera wearer interacts with the objects, or simply consider body motion as a separate modality. In…

Human activity recognition in videos has been widely studied and has recently gained significant advances with deep learning approaches; however, it remains a challenging task. In this paper, we propose a novel framework that simultaneously…

Objects are entities we act upon, where the functionality of an object is determined by how we interact with it. In this work we propose a Dual Attention Network model which reasons about human-object interactions. The dual-attentional…

We propose a novel attention model that can accurately attends to target objects of various scales and shapes in images. The model is trained to gradually suppress irrelevant regions in an input image via a progressive attentive process…

Human-object interaction detection is an important and relatively new class of visual relationship detection tasks, essential for deeper scene understanding. Most existing approaches decompose the problem into object localization and…

Despite the notable progress made in action recognition tasks, not much work has been done in action recognition specifically for human-robot interaction. In this paper, we deeply explore the characteristics of the action recognition task…

User interests are usually dynamic in the real world, which poses both theoretical and practical challenges for learning accurate preferences from rich behavior data. Among existing user behavior modeling solutions, attention networks are…

This paper proposes joint attention estimation in a single image. Different from related work in which only the gaze-related attributes of people are independently employed, (I) their locations and actions are also employed as contextual…

Robots that navigate through human crowds need to be able to plan safe, efficient, and human predictable trajectories. This is a particularly challenging problem as it requires the robot to predict future human trajectories within a crowd…

Deep neural networks, including recurrent networks, have been successfully applied to human activity recognition. Unfortunately, the final representation learned by recurrent networks might encode some noise (irrelevant signal components,…

Human motion prediction aims to forecast future human poses given a historical motion. Whether based on recurrent or feed-forward neural networks, existing learning based methods fail to model the observation that human motion tends to…

3D hand-object pose estimation is the key to the success of many computer vision applications. The main focus of this task is to effectively model the interaction between the hand and an object. To this end, existing works either rely on…

Close human-robot cooperation is a key enabler for new developments in advanced manufacturing and assistive applications. Close cooperation require robots that can predict human actions and intent, and understand human non-verbal cues.…

Reasoning human object interactions is a core problem in human-centric scene understanding and detecting such relations poses a unique challenge to vision systems due to large variations in human-object configurations, multiple co-occurring…

We address the challenging task of human reaction generation, which aims to generate a corresponding reaction based on an input action. Most of the existing works do not focus on generating and predicting the reaction and cannot generate…

Human motion prediction aims to forecast future human poses given a past motion. Whether based on recurrent or feed-forward neural networks, existing methods fail to model the observation that human motion tends to repeat itself, even for…

Students often drift in and out of focus during class. Effective teachers recognize this and re-engage them when necessary. With the shift to remote learning, teachers have lost the visual feedback needed to adapt to varying student…

Probabilistic models can learn users' preferences from the history of their item adoptions on a social media site, and in turn, recommend new items to users based on learned preferences. However, current models ignore psychological factors…

A visual hard attention model actively selects and observes a sequence of subregions in an image to make a prediction. The majority of hard attention models determine the attention-worthy regions by first analyzing a complete image.…

The attention mechanism provides a sequential prediction framework for learning spatial models with enhanced implicit temporal consistency. In this work, we show a systematic design (from 2D to 3D) for how conventional networks and other…