Search Results for author:
Found 14 papers, 3 papers with code
Counterfactual Reasoning Using Predicted Latent Personality Dimensions for Optimizing Persuasion Outcome
In this paper, we present a novel approach that tracks a user's latent personality dimensions (LPDs) during ongoing persuasion conversation and generates tailored counterfactual utterances based on these LPDs to optimize the overall persuasion outcome.
Anchor-aware Deep Metric Learning for Audio-visual Retrieval
However, the model training fails to fully explore the space due to the scarcity of training data points, resulting in an incomplete representation of the overall positive and negative distributions.
Two-Stage Triplet Loss Training with Curriculum Augmentation for Audio-Visual Retrieval
We propose a two-stage training paradigm that guides the model's learning process from semi-hard to hard triplets.
Topic-switch adapted Japanese Dialogue System based on PLATO-2
Furthermore, our proposed topic-switch algorithm achieves an average score of 1. 767 and outperforms PLATO-JDS by 0. 267, indicating its effectiveness in improving the user experience of our system.
Do I Have Your Attention: A Large Scale Engagement Prediction Dataset and Baselines
The experiments show the usefulness of the proposed dataset.
Complete Cross-triplet Loss in Label Space for Audio-visual Cross-modal Retrieval
In this paper, to reduce the interference of hard negative samples in representation learning, we propose a new AV-CMR model to optimize semantic features by directly predicting labels and then measuring the intrinsic correlation between audio-visual data using complete cross-triple loss.
Compositionality-Aware Graph2Seq Learning
It is expected that the compositionality in a graph can be associated to the compositionality in the output sequence in many graph2seq tasks.
Multi-Level Attention Pooling for Graph Neural Networks: Unifying Graph Representations with Multiple Localities
It has an attention pooling layer for each message passing step and computes the final graph representation by unifying the layer-wise graph representations.
Detecting Unknown Behaviors by Pre-defined Behaviours: An Bayesian Non-parametric Approach
An automatic mouse behavior recognition system can considerably reduce the workload of experimenters and facilitate the analysis process.
A Hierarchical Mixture Density Network
One of the complicated relationships among three correlated variables could be a two-layer hierarchical many-to-many mapping.
Towards Generation of Visual Attention Map for Source Code
Program comprehension is a dominant process in software development and maintenance.
Skip-connection and batch-normalization improve data separation ability
The ResNet and the batch-normalization (BN) achieved high performance even when only a few labeled data are available.
Application of SsVGMM to medical data-classification with novelty detection
There is a considerable demand to apply classification in medical analysis.
Efficient learning with robust gradient descent
Minimizing the empirical risk is a popular training strategy, but for learning tasks where the data may be noisy or heavy-tailed, one may require many observations in order to generalize well.
