Search Results for author:
Found 14 papers, 0 papers with code
Information-Maximizing Sampling to Promote Tracking-by-Detection
We introduced the idea of most informative sampling, in which the sampler attempts to select samples that trouble the classifier of a discriminative tracker.
Efficient Diverse Ensemble for Discriminative Co-Tracking
To remove this redundancy and have an effective ensemble learning, it is critical for the committee to include consistent hypotheses that differ from one-another, covering the version space with minimum overlaps.
Active Collaborative Ensemble Tracking
However, by updating all of the ensemble using a shared set of samples and their final labels, such diversity is lost or reduced to the diversity provided by the underlying features or internal classifiers' dynamics.
Efficient Version-Space Reduction for Visual Tracking
To cope with variations of the target shape and appearance, the classifier is updated online with different samples of the target and the background.
Efficient Asymmetric Co-Tracking using Uncertainty Sampling
We also introduce a budgeting mechanism which prevents the unbounded growth in the number of examples in the first detector to maintain its rapid response.
Automatic Speech Recognition Errors as a Predictor of L2 Listening Difficulties
To improve the choice of words in this system, and explore a better method to detect speech challenges, ASR errors were investigated as a model of the L2 listener, hypothesizing that some of these errors are similar to those of language learners{'} when transcribing the videos.
Automatic Speech Recognition
Automatic Speech Recognition (ASR)
+2
Long and Short Memory Balancing in Visual Co-Tracking using Q-Learning
Employing one or more additional classifiers to break the self-learning loop in tracing-by-detection has gained considerable attention.
AnimGAN: A Spatiotemporally-Conditioned Generative Adversarial Network for Character Animation
We proposed a spatiotemporally-conditioned GAN that generates a sequence that is similar to a given sequence in terms of semantics and spatiotemporal dynamics.
Adversarial Semi-Supervised Multi-Domain Tracking
Neural networks for multi-domain learning empowers an effective combination of information from different domains by sharing and co-learning the parameters.
Leveraging Tacit Information Embedded in CNN Layers for Visual Tracking
Different layers in CNNs provide not only different levels of abstraction for describing the objects in the input but also encode various implicit information about them.
Q-Learning Scheduler for Multi-Task Learning through the use of Histogram of Task Uncertainty
Simultaneous training of a multi-task learning network on different domains or tasks is not always straightforward.
Q-Learning Scheduler for Multi Task Learning Through the use of Histogram of Task Uncertainty
Simultaneous training of a multi-task learning network on different domains or tasks is not always straightforward.
Uncertainty Regularized Multi-Task Learning
By sharing parameters and providing task-independent shared features, multi-task deep neural networks are considered one of the most interesting ways for parallel learning from different tasks and domains.
