For a comprehensive evaluation of face matchers, three recognition tasks are performed under standard, masked and unbiased settings, respectively.
The current research on this problem mainly focuses on designing an efficient Fully-connected layer (FC) to reduce GPU memory consumption caused by a large number of identities.
There are second phase of the challenge till October 1, 2021 and on-going leaderboard.
In this paper, we contribute a new million-scale face benchmark containing noisy 4M identities/260M faces (WebFace260M) and cleaned 2M identities/42M faces (WebFace42M) training data, as well as an elaborately designed time-constrained evaluation protocol.
Ranked #1 on Face Verification on IJB-C (training dataset metric)
In this paper, we propose a Semi-Global Shape-aware Network (SGSNet) considering both feature similarity and proximity for preserving object shapes when modeling long-range dependencies.
Particularly, we introduce an additional loss to encode the differences in the feature and semantic distributions within feature maps between the baseline model and the pruned one.
Deep neural networks (DNNs) have achieved great success in a wide range of computer vision areas, but the applications to mobile devices is limited due to their high storage and computational cost.
On NTU RGB-D, Action Machine achieves the state-of-the-art performance with top-1 accuracies of 97. 2% and 94. 3% on cross-view and cross-subject respectively.
Ranked #1 on Action Recognition on UTD-MHAD
Real-time motion detection in non-stationary scenes is a difficult task due to dynamic background, changing foreground appearance and limited computational resource.
Obtained by moving object detection, the foreground mask result is unshaped and can not be directly used in most subsequent processes.
Real-time moving object detection in unconstrained scenes is a difficult task due to dynamic background, changing foreground appearance and limited computational resource.
From the frame/clip-level feature learning to the video-level representation building, deep learning methods in action recognition have developed rapidly in recent years.
For the two-stream style methods in action recognition, fusing the two streams' predictions is always by the weighted averaging scheme.