Most existing forecasting systems are memory-based methods, which attemp...
With the exponential growth of video data, there is an urgent need for
a...
The Multiplane Image (MPI), containing a set of fronto-parallel RGBA lay...
Object affordance is an important concept in hand-object interaction,
pr...
In this report, we present our champion solutions to five tracks at Ego4...
Few-shot action recognition aims to recognize novel action classes using...
We consider constrained sampling problems in paid research studies or
cl...
Object affordance is an important concept in human-object interaction,
p...
First-person action recognition is a challenging task in video understan...
The human gaze is a cost-efficient physiological data that reveals human...
The attribution method provides a direction for interpreting opaque neur...
In this paper, we propose a talking face generation method that takes an...
In this report, we describe the technical details of our submission to t...
Visual storytelling is a task of generating relevant and interesting sto...
With today's savvy and empowered customers, sales requires more judgment...
Identifying and visualizing regions that are significant for a given dee...
With the industry trend of shifting from a traditional hierarchical appr...
This paper conducts an empirical investigation to evaluate transfer lear...
Recent advances in computer vision have made it possible to automaticall...
In this work, we address two coupled tasks of gaze prediction and action...
Neural networks have shown great performance in cognitive tasks. When
de...
Object co-segmentation is the task of segmenting the same objects from
m...
Margin enlargement over training data has been an important strategy sin...
We present a new computational model for gaze prediction in egocentric v...