Related papers: Going Deeper into First-Person Activity Recognitio…
Achieving robust multi-person 2D body landmark localization and pose estimation is essential for human behavior and interaction understanding as encountered for instance in HRI settings. Accurate methods have been proposed recently, but…
In this paper, we introduce Coarse-Fine Networks, a two-stream architecture which benefits from different abstractions of temporal resolution to learn better video representations for long-term motion. Traditional Video models process…
Human recognition of the actions of other humans is very efficient and is based on patterns of movements. Our theoretical starting point is that the dynamics of the joint movements is important to action categorization. On the basis of this…
Generally, social network analysis has often focused on the topology of the network without considering the characteristics of individuals involved in them. Less attention is given to study the behavior of individuals, considering they are…
Recently, pose-based action recognition has gained more and more attention due to the better performance compared with traditional appearance-based methods. However, there still exist two problems to be further solved. First, existing…
Video activity Recognition has recently gained a lot of momentum with the release of massive Kinetics (400 and 600) data. Architectures such as I3D and C3D networks have shown state-of-the-art performances for activity recognition. The one…
The increasing popularity of egocentric cameras has generated growing interest in studying multi-camera interactions in shared environments. Although large-scale datasets such as Ego4D and Ego-Exo4D have propelled egocentric vision…
Two-stream networks have been very successful for solving the problem of action detection. However, prior work using two-stream networks train both streams separately, which prevents the network from exploiting regularities between the two…
In this paper, we present a deep coupled framework to address the problem of matching sketch image against a gallery of mugshots. Face sketches have the essential in- formation about the spatial topology and geometric details of faces while…
Human activities recognition is an important task for an intelligent robot, especially in the field of human-robot collaboration, it requires not only the label of sub-activities but also the temporal structure of the activity. In order to…
Natural interaction with virtual objects in AR/VR environments makes for a smooth user experience. Gestures are a natural extension from real world to augmented space to achieve these interactions. Finding discriminating spatio-temporal…
First-person (wearable) camera continually captures unscripted interactions of the camera user with objects, people, and scenes reflecting his personal and relational tendencies. One of the preferences of people is their interaction with…
Given a video captured from a first person perspective and the environment context of where the video is recorded, can we recognize what the person is doing and identify where the action occurs in the 3D space? We address this challenging…
Hand detection is essential for many hand related tasks, e.g. parsing hand pose, understanding gesture, which are extremely useful for robotics and human-computer interaction. However, hand detection in uncontrolled environments is…
Person-person mutual action recognition (also referred to as interaction recognition) is an important research branch of human activity analysis. Current solutions in the field -- mainly dominated by CNNs, GCNs and LSTMs -- often consist of…
Actionness was introduced to quantify the likelihood of containing a generic action instance at a specific location. Accurate and efficient estimation of actionness is important in video analysis and may benefit other relevant tasks such as…
A collection of approaches based on graph convolutional networks have proven success in skeleton-based action recognition by exploring neighborhood information and dense dependencies between intra-frame joints. However, these approaches…
Improved dense trajectories (iDT) have shown great performance in action recognition, and their combination with the two-stream approach has achieved state-of-the-art performance. It is, however, difficult for iDT to completely remove…
Egocentric action anticipation is the task of predicting the future actions a camera wearer will likely perform based on past video observations. While in a real-world system it is fundamental to output such predictions before the action…
This paper proposes a two-stream flow-guided convolutional attention networks for action recognition in videos. The central idea is that optical flows, when properly compensated for the camera motion, can be used to guide attention to the…