Related papers: From Lifestyle Vlogs to Everyday Interactions
Visual relationships capture a wide variety of interactions between pairs of objects in images (e.g. "man riding bicycle" and "man pushing bicycle"). Consequently, the set of possible relationships is extremely large and it is difficult to…
Around-device interaction promises to extend the input space of mobile and wearable devices beyond the common but restricted touchscreen. So far, most around-device interaction approaches rely on instrumenting the device or the environment…
Latent actions serve as an intermediate representation that enables consistent modeling of vision-language-action (VLA) models across heterogeneous datasets. However, approaches to supervising VLAs with latent actions are fragmented and…
We design a new approach that allows robot learning of new activities from unlabeled human example videos. Given videos of humans executing the same activity from a human's viewpoint (i.e., first-person videos), our objective is to make the…
Events are fundamental for understanding how people experience their lives. It is challenging, however, to automatically record all events in daily life. An understanding of multimedia signals allows recognizing events of daily living and…
Despite advances in hand-object interaction modeling, generating realistic dexterous manipulation data for robotic hands remains a challenge. Retargeting methods often suffer from low accuracy and fail to account for hand-object…
We address the problem of accurate capture of interactive behaviors between two people in daily scenarios. Most previous works either only consider one person or solely focus on conversational gestures of two people, assuming the body…
Now that everyone can easily record videos, the quantity of which is continuously increasing, research on methods for improved video retrieval is important in the contemporary world. In cases where target videos are to be identified within…
Progress in embodied intelligence increasingly depends on scalable data infrastructure. While vision and language have scaled with internet corpora, learning physical interaction remains constrained by the lack of large, diverse, and richly…
Predicting human interaction is challenging as the on-going activity has to be inferred based on a partially observed video. Essentially, a good algorithm should effectively model the mutual influence between the two interacting subjects.…
We introduce and we analyze a new dataset which resembles the input to biological vision systems much more than most previously published ones. Our analysis leaded to several important conclusions. First, it is possible to disambiguate over…
Given their importance in shaping social networks and determining how information or diseases propagate in a population, human interactions are the subject of many data collection efforts. To this aim, different methods are commonly used,…
The use of visual analytics tools has gained popularity in various domains, helping users discover meaningful information from complex and large data sets. Users often face difficulty in disseminating the knowledge discovered without clear…
Learning action models from real-world human-centric interaction datasets is important towards building general-purpose intelligent assistants with efficiency. However, most existing datasets only offer specialist interaction category and…
This work focuses on anticipating long-term human actions, particularly using short video segments, which can speed up editing workflows through improved suggestions while fostering creativity by suggesting narratives. To this end, we imbue…
While the shortage of explicit action data limits Vision-Language-Action (VLA) models, human action videos offer a scalable yet unlabeled data source. A critical challenge in utilizing large-scale human video datasets lies in transforming…
Interactions are patterns between several attributes in data that cannot be inferred from any subset of these attributes. While mutual information is a well-established approach to evaluating the interactions between two attributes, we…
Understanding social interactions from egocentric views is crucial for many applications, ranging from assistive robotics to AR/VR. Key to reasoning about interactions is to understand the body pose and motion of the interaction partner…
The visual analytics community has proposed several user modeling algorithms to capture and analyze users' interaction behavior in order to assist users in data exploration and insight generation. For example, some can detect exploration…
Learning how humans manipulate objects requires machines to acquire knowledge from two perspectives: one for understanding object affordances and the other for learning human's interactions based on the affordances. Even though these two…