arXiv subjects

Bertram E. Shi

Publications and source records attributed to Bertram E. Shi.

28 records · Page 2Linked to original sources

arXiv2019

Gaze Training by Modulated Dropout Improves Imitation Learning

Imitation learning by behavioral cloning is a prevalent method that has achieved some success in vision-based autonomous driving. The basic idea behind behavioral cloning is to have the neural network learn from observing a human expert's behavior. Typically, a convolutional neural network learns to predict the steering commands from raw driver-view images by mimicking the behaviors of human drivers. However, there are other cues, such as gaze behavior, available from human drivers that have yet to be exploited. Previous researches have shown that novice human learners can benefit from observing experts' gaze patterns. We present here that deep neural networks can also profit from this. We propose a method, gaze-modulated dropout, for integrating this gaze information into a deep driving network implicitly rather than as an additional input. Our experimental results demonstrate that gaze-modulated dropout enhances the generalization capability of the network to unseen scenes. Prediction error in steering commands is reduced by 23.5% compared to uniform dropout. Running closed loop in the simulator, the gaze-modulated dropout net increased the average distance travelled between infractions by 58.5%. Consistent with these results, the gaze-modulated dropout net shows lower model uncertainty.

cs.CV↗

arXiv2019

Coupled Recurrent Network (CRN)

Many semantic video analysis tasks can benefit from multiple, heterogenous signals. For example, in addition to the original RGB input sequences, sequences of optical flow are usually used to boost the performance of human action recognition in videos. 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). However, two-stream RNNs do not fully exploit the reciprocal information contained in the multiple signals, let alone exploit it in a recurrent manner. To this end, we propose in this paper a novel recurrent architecture, termed Coupled Recurrent Network (CRN), to deal with multiple input sources. In CRN, the parallel streams of RNNs are coupled together. Key design of CRN is a Recurrent Interpretation Block (RIB) that supports learning of reciprocal feature representations from multiple signals in a recurrent manner. Different from RNNs which stack the training loss at each time step or the last time step, we propose an effective and efficient training strategy for CRN. Experiments show the efficacy of the proposed CRN. In particular, we achieve the new state of the art on the benchmark datasets of human action recognition and multi-person pose estimation.

cs.CV↗

arXiv2019

Appearance-Based Gaze Estimation Using Dilated-Convolutions

Appearance-based gaze estimation has attracted more and more attention because of its wide range of applications. The use of deep convolutional neural networks has improved the accuracy significantly. In order to improve the estimation accuracy further, we focus on extracting better features from eye images. Relatively large changes in gaze angles may result in relatively small changes in eye appearance. We argue that current architectures for gaze estimation may not be able to capture such small changes, as they apply multiple pooling layers or other downsampling layers so that the spatial resolution of the high-level layers is reduced significantly. To evaluate whether the use of features extracted at high resolution can benefit gaze estimation, we adopt dilated-convolutions to extract high-level features without reducing spatial resolution. In cross-subject experiments on the Columbia Gaze dataset for eye contact detection and the MPIIGaze dataset for 3D gaze vector regression, the resulting Dilated-Nets achieve significant (up to 20.8%) gains when compared to similar networks without dilated-convolutions. Our proposed Dilated-Net achieves state-of-the-art results on both the Columbia Gaze and the MPIIGaze datasets.

cs.CV↗

arXiv2018

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. Much previous work has focused on instantaneous emotion recognition. The 2018 One-Minute Gradual-Emotion Recognition (OMG-Emotion) challenge, which was held in conjunction with the IEEE World Congress on Computational Intelligence, encouraged participants to address long-term emotion recognition by integrating cues from multiple modalities, including facial expression, audio and language. Intuitively, a multi-modal inference network should be able to leverage information from each modality and their correlations to improve recognition over that achievable by a single modality network. We describe here a multi-modal neural architecture that integrates visual information over time using an LSTM, and combines it with utterance level audio and text cues to recognize human sentiment from multimodal clips. Our model outperforms the unimodal baseline, achieving the concordance correlation coefficients (CCC) of 0.400 on the arousal task, and 0.353 on the valence task.

eess.IV↗

arXiv2017

Lattice Long Short-Term Memory for Human Action Recognition

Human actions captured in video sequences are three-dimensional signals characterizing visual appearance and motion dynamics. To learn action patterns, existing methods adopt Convolutional and/or Recurrent Neural Networks (CNNs and RNNs). CNN based methods are effective in learning spatial appearances, but are limited in modeling long-term motion dynamics. RNNs, especially Long Short-Term Memory (LSTM), are able to learn temporal motion dynamics. However, naively applying RNNs to video sequences in a convolutional manner implicitly assumes that motions in videos are stationary across different spatial locations. This assumption is valid for short-term motions but invalid when the duration of the motion is long. In this work, we propose Lattice-LSTM (L2STM), which extends LSTM by learning independent hidden state transitions of memory cells for individual spatial locations. 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. Additionally, we introduce a novel multi-modal training procedure for training our network. Unlike traditional two-stream architectures which use RGB and optical flow information as input, our two-stream model leverages both modalities to jointly train both input gates and both forget gates in the network rather than treating the two streams as separate entities with no information about the other. We apply this end-to-end system to benchmark datasets (UCF-101 and HMDB-51) of human action recognition. Experiments show that on both datasets, our proposed method outperforms all existing ones that are based on LSTM and/or CNNs of similar model complexities.

cs.CV↗

arXiv2016

Developing and Assessing MATLAB Exercises for Active Concept Learning

New technologies, such as MOOCs, provide innovative methods to tackle new challenges in teaching and learning, such as globalization and changing contemporary culture and to remove the limits of conventional classrooms. However, they also bring challenges in course delivery and assessment, due to factors such as less direct student-instructor interaction. These challenges are especially severe in engineering education, which relies heavily on experiential learning, such as computer simulations and laboratory exercises, to assist students in understanding concepts. As a result, effective design of experiential learning components is extremely critical for engineering MOOCs. In this paper, we will share our experience gained through developing and offering a MOOC on communication systems, with special focus on the development and assessment of MATLAB exercises for active concept learning. Our approach introduced students to concepts using learning components commonly provided by many MOOC platforms (e.g., online lectures and quizzes), and augmented the student experience with MATLAB based computer simulations and exercises to enable more concrete and detailed understanding of the material. We describe here a systematic approach to MATLAB problem design and assessment, based on our experience with the MATLAB server provided by MathWorks and integrated with the edX MOOC platform. We discuss the effectiveness of the instructional methods as evaluated through students' learning performance. We analyze the impact of the course design tools from both the instructor and the student perspective.

cs.CY↗

arXiv2016

An active efficient coding model of the optokinetic nystagmus

Optokinetic nystagmus (OKN) is an involuntary eye movement responsible for stabilizing retinal images in the presence of relative motion between an observer and the environment. Fully understanding the development of optokinetic nystagmus requires a neurally plausible computational model that accounts for the neural development and the behavior. To date, work in this area has been limited. We propose a neurally plausible framework for the joint development of disparity and motion tuning in the visual cortex, the optokinetic and vergence eye movements. 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. Because the model includes behavior, we can simulate the same perturbations as performed in past experiments, such as artificially induced strabismus. The proposed model agrees both qualitatively and quantitatively with a number of findings from the literature on both binocular vision as well as the optokinetic reflex. Finally, our model also makes quantitative predictions about the OKN behavior using the same methods used to characterize the OKN in the experimental literature.

q-bio.NC↗

arXiv2016

Invariant feature extraction from event based stimuli

We propose a novel architecture, the event-based GASSOM for learning and extracting invariant representations from event streams originating from neuromorphic vision sensors. The framework is inspired by feed-forward cortical models for visual processing. The model, which is based on the concepts of sparsity and temporal slowness, is able to learn feature extractors that resemble neurons in the primary visual cortex. Layers of units in the proposed model can be cascaded to learn feature extractors with different levels of complexity and selectivity. We explore the applicability of the framework on real world tasks by using the learned network for object recognition. The proposed model achieve higher classification accuracy compared to other state-of-the-art event based processing methods. Our results also demonstrate the generality and robustness of the method, as the recognizers for different data sets and different tasks all used the same set of learned feature detectors, which were trained on data collected independently of the testing data.

cs.CV↗

arXiv2015

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. Inspired by the success of convolutional neural networks (CNN) for image classification, recent attempts have been made to learn 3D CNNs for recognizing human actions in videos. However, partly due to the high complexity of training 3D convolution kernels and the need for large quantities of training videos, only limited success has been reported. This has triggered us to investigate in this paper a new deep architecture which can handle 3D signals more effectively. Specifically, we propose factorized spatio-temporal convolutional networks (FstCN) that factorize the original 3D convolution kernel learning as a sequential process of learning 2D spatial kernels in the lower layers (called spatial convolutional layers), followed by learning 1D temporal kernels in the upper layers (called temporal convolutional layers). We introduce a novel transformation and permutation operator to make factorization in FstCN possible. Moreover, to address the issue of sequence alignment, we propose an effective training and inference strategy based on sampling multiple video clips from a given action video sequence. We have tested FstCN on two commonly used benchmark datasets (UCF-101 and HMDB-51). Without using auxiliary training videos to boost the performance, FstCN outperforms existing CNN based methods and achieves comparable performance with a recent method that benefits from using auxiliary training videos.

cs.CV↗

arXiv2014

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. Our extension combines sparse coding and reinforcement learning so that sensory processing and behavior co-develop to optimize a shared intrinsic motivational signal: the fidelity of the neural encoding of the sensory input under resource constraints. Applying this framework to a model system consisting of an active eye behaving in a time varying environment, we find that this generic principle leads to the simultaneous development of both smooth pursuit behavior and model neurons whose properties are similar to those of primary visual cortical neurons selective for different directions of visual motion. We suggest that this general principle may form the basis for a unified and integrated explanation of many perception/action loops.

cs.CV↗