Search Results for author:
Found 23 papers, 6 papers with code
CI-AVSR: A Cantonese Audio-Visual Speech Dataset for In-car Command Recognition
With the rise of deep learning and intelligent vehicle, the smart assistant has become an essential in-car component to facilitate driving and provide extra functionalities.
Automatic Speech Recognition Datasets in Cantonese: A Survey and New Dataset
We further conduct experiments with Fairseq S2T Transformer, a state-of-the-art ASR model, on the biggest existing dataset, Common Voice zh-HK, and our proposed MDCC, and the results show the effectiveness of our dataset.
Automatic Speech Recognition
Automatic Speech Recognition (ASR)
+2
ASCEND: A Spontaneous Chinese-English Dataset for Code-switching in Multi-turn Conversation
ASCEND (A Spontaneous Chinese-English Dataset) is a high-quality Mandarin Chinese-English code-switching corpus built on spontaneous multi-turn conversational dialogue sources collected in Hong Kong.
Iterative Distillation for Better Uncertainty Estimates in Multitask Emotion Recognition
Iterative distillation over multiple generations significantly improves performance in both emotion recognition and uncertainty estimation.
Learning Hierarchical Integration of Foveal and Peripheral Vision for Vergence Control by Active Efficient Coding
The high resolution fovea can drive precise short range movements.
Self-Calibrating Active Binocular Vision via Active Efficient Coding with Deep Autoencoders
We present a model of the self-calibration of active binocular vision comprising the simultaneous learning of visual representations, vergence, and pursuit eye movements.
AVGCN: Trajectory Prediction using Graph Convolutional Networks Guided by Human Attention
We suggest that introducing an attention mechanism to infer the importance of different neighbors is critical for accurate trajectory prediction in scenes with varying crowd size.
HGCN-GJS: Hierarchical Graph Convolutional Network with Groupwise Joint Sampling for Trajectory Prediction
Fully investigating the social interactions within the crowd is crucial for accurate pedestrian trajectory prediction.
Multitask Emotion Recognition with Incomplete Labels
We use the soft labels and the ground truth to train the student model.
Towards High Performance Low Complexity Calibration in Appearance Based Gaze Estimation
Appearance-based gaze estimation from RGB images provides relatively unconstrained gaze tracking.
Robot Navigation in Crowds by Graph Convolutional Networks with Attention Learned from Human Gaze
Previous work has shown the power of deep reinforcement learning frameworks to train efficient policies.
Offset Calibration for Appearance-Based Gaze Estimation via Gaze Decomposition
To improve estimation, we propose a novel gaze decomposition method and a single gaze point calibration method, motivated by our finding that the inter-subject squared bias exceeds the intra-subject variance for a subject-independent estimator.
Gaze Training by Modulated Dropout Improves Imitation Learning
The basic idea behind behavioral cloning is to have the neural network learn from observing a human expert's behavior.
Appearance-Based Gaze Estimation Using Dilated-Convolutions
Appearance-based gaze estimation has attracted more and more attention because of its wide range of applications.
Coupled Recurrent Network (CRN)
To learn from these heterogenous input sources, existing methods reply on two-stream architectural designs that contain independent, parallel streams of Recurrent Neural Networks (RNNs).
Action Recognition In Videos
Multi-Person Pose Estimation
+2
Multimodal Utterance-level Affect Analysis using Visual, Audio and Text Features
The integration of information across multiple modalities and across time is a promising way to enhance the emotion recognition performance of affective systems.
Lattice Long Short-Term Memory for Human Action Recognition
This method effectively enhances the ability to model dynamics across time and addresses the non-stationary issue of long-term motion dynamics without significantly increasing the model complexity.
An active efficient coding model of the optokinetic nystagmus
This framework models the joint emergence of both perception and behavior, and accounts for the importance of the development of normal vergence control and binocular vision in achieving normal monocular OKN (mOKN) behaviors.
Invariant feature extraction from event based stimuli
The framework is inspired by feed-forward cortical models for visual processing.
Human Action Recognition using Factorized Spatio-Temporal Convolutional Networks
Human actions in video sequences are three-dimensional (3D) spatio-temporal signals characterizing both the visual appearance and motion dynamics of the involved humans and objects.
Intrinsically Motivated Learning of Visual Motion Perception and Smooth Pursuit
We extend the framework of efficient coding, which has been used to model the development of sensory processing in isolation, to model the development of the perception/action cycle.
Extending Phase Mechanism to Differential Motion Opponency for Motion Pop-out
We extend the concept of phase tuning, a ubiquitous mechanism in sensory neurons including motion and disparity detection neurons, to the motion contrast detection.
Estimating disparity with confidence from energy neurons
When optimized for natural images, it yields a feature that can be explained by the normalization which is a common model in V1 neurons.
