• Publications
  • Influence
EL-GAN: Embedding Loss Driven Generative Adversarial Networks for Lane Detection
TLDR
This work proposes EL-GAN: a GAN framework to mitigate the discussed problem using an embedding loss, and uses the TuSimple lane marking challenge to demonstrate that with this proposed framework it is viable to overcome the inherent anomalies of posing it as a semantic segmentation problem.
Multi-view 3D Human Pose Estimation in Complex Environment
TLDR
This work introduces a framework for unconstrained 3D human upper body pose estimation from multiple camera views in complex environment and demonstrates that this approach outperforms the state-of-the-art in experiments with large and challenging real-world data from an outdoor setting.
I Bet You Are Wrong: Gambling Adversarial Networks for Structured Semantic Segmentation
TLDR
This paper rethink adversarial training for semantic segmentation and proposes to reformulate the fake/real discrimination framework with a correct/incorrect training objective, replacing the discriminator with a "gambler" network that learns to spot and distribute its budget in areas where the predictions are clearly wrong.
Multi-view 3D human pose estimation combining single-frame recovery, temporal integration and model adaptation
TLDR
This work presents a system for the estimation of unconstrained 3D human upper body movement from multiple cameras that outperforms the state of the art in experiments with large and challenging real world data from an outdoor setting.
Multi-view 3D human pose estimation combining single-frame recovery, temporal integration and model adaptation
TLDR
This work presents a system for the estimation of unconstrained 3D human upper body movement from multiple cameras that outperforms the state of the art in experiments with large and challenging real world data from an outdoor setting.
VATLD: A Visual Analytics System to Assess, Understand and Improve Traffic Light Detection
TLDR
This work proposes a visual analytics system, VATLD, equipped with a disentangled representation learning and semantic adversarial learning, to assess, understand, and improve the accuracy and robustness of traffic light detectors in autonomous driving applications.
Single-Frame 3D Human Pose Recovery from Multiple Views
TLDR
It is demonstrated that the proposed clustering approach greatly outperforms state-of-the-art bottom-up clustering in parameter space and present a detailed experimental evaluation of the complete system on a large data set.
Optimization of MFNs for signal-based phrase break prediction
TLDR
A neural network based method for signal-based phrase break prediction and tested this method across two different speech databases, finding that phrase break recognition rates vary from 79% up to 97%.
Evolutionary optimization of an adaptive prosody model
TLDR
A novel evolutionary approach is surveyed to optimize the model structure itself and to improve the predicted prosodic contours of the syllable-based, adaptive prosody model IGM to help develop resource-saving prosody modules.
...
1
2
...