|TREND||DATASET||BEST METHOD||PAPER TITLE||PAPER||CODE||COMPARE|
We propose the Asynchronous Interaction Aggregation network (AIA) that leverages different interactions to boost action detection.
While observing complex events with multiple actors, humans do not assess each actor separately, but infer from the context.
In this paper, we introduce the concept of learning latent super-events from activity videos, and present how it benefits activity detection in continuous videos.
Ranked #2 on Action Detection on Multi-THUMOS
We propose an Efficient Activity Detection System, Argus, for Extended Video Analysis in the surveillance scenario.
Diffusions effectively interact two aspects of information, i. e., localized and holistic, for more powerful way of representation learning.
Ranked #1 on Action Classification on Kinetics-600
We introduce a new convolutional layer named the Temporal Gaussian Mixture (TGM) layer and present how it can be used to efficiently capture longer-term temporal information in continuous activity videos.
Ranked #1 on Action Detection on Multi-THUMOS
Each branch produces a set of action anchor layers by applying deconvolution to the feature maps of the main stream.
Ranked #2 on Temporal Action Localization on THUMOS’14