Search Results for author:
Found 13 papers, 7 papers with code
Self-Supervised Robustifying Guidance for Monocular 3D Face Reconstruction
On the three variations of the test dataset of CelebA: rational occlusions, delusional occlusions, and noisy face images, our method outperforms the current state-of-the-art method by large margins (e. g., for the shape-based 3D vertex errors, a reduction from 0. 146 to 0. 048 for rational occlusions, from 0. 292 to 0. 061 for delusional occlusions and from 0. 269 to 0. 053 for the noise in the face images), demonstrating the effectiveness of the proposed approach.
Learned Smartphone ISP on Mobile NPUs with Deep Learning, Mobile AI 2021 Challenge: Report
As the quality of mobile cameras starts to play a crucial role in modern smartphones, more and more attention is now being paid to ISP algorithms used to improve various perceptual aspects of mobile photos.
Network Space Search for Pareto-Efficient Spaces
We propose an NSS method to directly search for efficient-aware network spaces automatically, reducing the manual effort and immense cost in discovering satisfactory ones.
Action Segmentation with Mixed Temporal Domain Adaptation
The main progress for action segmentation comes from densely-annotated data for fully-supervised learning.
Ranked #6 on
Action Segmentation
on Breakfast
Action Segmentation with Joint Self-Supervised Temporal Domain Adaptation
Despite the recent progress of fully-supervised action segmentation techniques, the performance is still not fully satisfactory.
Ranked #6 on
Action Segmentation
on GTEA
Interpretable Self-Attention Temporal Reasoning for Driving Behavior Understanding
Performing driving behaviors based on causal reasoning is essential to ensure driving safety.
Traffic Sign Detection under Challenging Conditions: A Deeper Look Into Performance Variations and Spectral Characteristics
We investigate the effect of challenging conditions through spectral analysis and show that challenging conditions can lead to distinct magnitude spectrum characteristics.
Temporal Attentive Alignment for Large-Scale Video Domain Adaptation
Finally, we propose Temporal Attentive Adversarial Adaptation Network (TA3N), which explicitly attends to the temporal dynamics using domain discrepancy for more effective domain alignment, achieving state-of-the-art performance on four video DA datasets (e. g. 7. 9% accuracy gain over "Source only" from 73. 9% to 81. 8% on "HMDB --> UCF", and 10. 3% gain on "Kinetics --> Gameplay").
Ranked #1 on
Domain Adaptation
on UCF --> HMDB (full)
Image Captioning with Integrated Bottom-Up and Multi-level Residual Top-Down Attention for Game Scene Understanding
However, little work has been done for game image captioning which has some unique characteristics and requirements.
Temporal Attentive Alignment for Video Domain Adaptation
Finally, we propose Temporal Attentive Adversarial Adaptation Network (TA3N), which explicitly attends to the temporal dynamics using domain discrepancy for more effective domain alignment, achieving state-of-the-art performance on three video DA datasets.
Ranked #1 on
Domain Adaptation
on UCF-to-Olympic
Challenging Environments for Traffic Sign Detection: Reliability Assessment under Inclement Conditions
Experimental results show that benchmarked algorithms are highly sensitive to tested challenging conditions, which result in an average performance drop of 0. 17 in terms of precision and a performance drop of 0. 28 in recall under severe conditions.
TS-LSTM and Temporal-Inception: Exploiting Spatiotemporal Dynamics for Activity Recognition
We demonstrate that using both RNNs (using LSTMs) and Temporal-ConvNets on spatiotemporal feature matrices are able to exploit spatiotemporal dynamics to improve the overall performance.
Ranked #50 on
Action Recognition
on UCF101
Depth and Skeleton Associated Action Recognition without Online Accessible RGB-D Cameras
Our approach aims to enhance action recognition in RGB videos by leveraging the extra database.
