We propose a method for improving the quality of synthetic room impulse responses generated using acoustic simulators for far-field speech recognition tasks. We bridge the gap between the synthetic room impulse responses and the real room impulse responses using our novel, one-dimensional CycleGAN architecture. We pass a synthetic room impulse response in the form of raw-waveform audio to our one-dimensional CycleGAN and translate it into a real room impulse response. We also perform sub-band room equalization to the translated room impulse response to further improve the quality of the room impulse response. We artificially create far-field speech by convolving the LibriSpeech clean speech dataset [1] with room impulse response and adding background noise. We show that far-field speech simulated with the improved room impulse response using our approach reduces the word error rate by up to 19.9% compared to the unmodified room impulse response in Kaldi LibriSpeech far-field automatic speech recognition benchmark [2].
We present Affect2MM, a learning method for time-series emotion prediction for multimedia content. Our goal is to automatically capture the varying emotions depicted by characters in real-life human-centric situations and behaviors. We use the ideas from emotion causation theories to computationally model and determine the emotional state evoked in clips of movies. Affect2MM explicitly models the temporal causality using attention-based methods and Granger causality. We use a variety of components like facial features of actors involved, scene understanding, visual aesthetics, action/situation description, and movie script to obtain an affective-rich representation to understand and perceive the scene. We use an LSTM-based learning model for emotion perception. To evaluate our method, we analyze and compare our performance on three datasets, SENDv1, MovieGraphs, and the LIRIS-ACCEDE dataset, and observe an average of 10-15% increase in the performance over SOTA methods for all three datasets.
We present a novel approach to robustly detect and perceive vehicles in different camera views as part of a cooperative vehicle-infrastructure system (CVIS). Our formulation is designed for arbitrary camera views and makes no assumptions about intrinsic or extrinsic parameters. First, to deal with multi-view data scarcity, we propose a part-assisted novel view synthesis algorithm for data augmentation. We train a part-based texture inpainting network in a self-supervised manner. Then we render the textured model into the background image with the target 6-DoF pose. Second, to handle various camera parameters, we present a new method that produces dense mappings between image pixels and 3D points to perform robust 2D/3D vehicle parsing. Third, we build the first CVIS dataset for benchmarking, which annotates more than 1540 images (14017 instances) from real-world traffic scenarios. We combine these novel algorithms and datasets to develop a robust approach for 2D/3D vehicle parsing for CVIS. In practice, our approach outperforms SOTA methods on 2D detection, instance segmentation, and 6-DoF pose estimation, by 4.5%, 4.3%, and 2.9%, respectively. More details and results are included in the supplement. To facilitate future research, we will release the source code and the dataset on GitHub.
We present a new learning-based method for identifying safe and navigable regions in off-road terrains and unstructured environments from RGB images. Our approach consists of classifying groups of terrain classes based on their navigability levels using coarse-grained semantic segmentation. We propose a bottleneck transformer-based deep neural network architecture that uses a novel group-wise attention mechanism to distinguish between navigability levels of different terrains.Our group-wise attention heads enable the network to explicitly focus on the different groups and improve the accuracy. In addition, we propose a dynamic weighted cross entropy loss function to handle the long-tailed nature of the dataset. We show through extensive evaluations on the RUGD and RELLIS-3D datasets that our learning algorithm improves the accuracy of visual perception in off-road terrains for navigation. We compare our approach with prior work on these datasets and achieve an improvement over the state-of-the-art mIoU by 6.74-39.1% on RUGD and 3.82-10.64% on RELLIS-3D.
We present a decentralized collision avoidance method for dense environments that is based on buffered Voronoi cells (BVC) and reciprocal velocity obstacles (RVO). Our approach is designed for scenarios with large number of close proximity agents and provides passive-friendly collision avoidance guarantees. The Voronoi cells are superimposed with RVO cones to compute a suitable direction for each agent and we use that direction for computing a local collision-free path. Our approach can satisfy double-integrator dynamics constraints and we use the properties of the BVC to formulate a simple, decentralized deadlock resolution strategy. We demonstrate the benefits of V-RVO in complex scenarios with tens of agents in close proximity. In practice, V-RVO's performance is comparable to prior velocity-obstacle methods and the collision avoidance behavior is significantly less conservative than ORCA.
We present a new approach, that we call AdaGTCN, for identifying human reader intent from Electroencephalogram~(EEG) and Eye movement~(EM) data in order to help differentiate between normal reading and task-oriented reading. Understanding the physiological aspects of the reading process~(the cognitive load and the reading intent) can help improve the quality of crowd-sourced annotated data. Our method, Adaptive Graph Temporal Convolution Network (AdaGTCN), uses an Adaptive Graph Learning Layer and Deep Neighborhood Graph Convolution Layer for identifying the reading activities using time-locked EEG sequences recorded during word-level eye-movement fixations. Adaptive Graph Learning Layer dynamically learns the spatial correlations between the EEG electrode signals while the Deep Neighborhood Graph Convolution Layer exploits temporal features from a dense graph neighborhood to establish the state of the art in reading task identification over other contemporary approaches. We compare our approach with several baselines to report an improvement of 6.29% on the ZuCo 2.0 dataset, along with extensive ablation experiments
We present a novel redirected walking controller based on alignment that allows the user to explore large and complex virtual environments, while minimizing the number of collisions with obstacles in the physical environment. Our alignment-based redirection controller, ARC, steers the user such that their proximity to obstacles in the physical environment matches the proximity to obstacles in the virtual environment as closely as possible. To quantify a controller's performance in complex environments, we introduce a new metric, Complexity Ratio (CR), to measure the relative environment complexity and characterize the difference in navigational complexity between the physical and virtual environments. Through extensive simulation-based experiments, we show that ARC significantly outperforms current state-of-the-art controllers in its ability to steer the user on a collision-free path. We also show through quantitative and qualitative measures of performance that our controller is robust in complex environments with many obstacles. Our method is applicable to arbitrary environments and operates without any user input or parameter tweaking, aside from the layout of the environments. We have implemented our algorithm on the Oculus Quest head-mounted display and evaluated its performance in environments with varying complexity. Our project website is available at https://gamma.umd.edu/arc/.
Holistically understanding an object and its 3D movable parts through visual perception models is essential for enabling an autonomous agent to interact with the world. For autonomous driving, the dynamics and states of vehicle parts such as doors, the trunk, and the bonnet can provide meaningful semantic information and interaction states, which are essential to ensuring the safety of the self-driving vehicle. Existing visual perception models mainly focus on coarse parsing such as object bounding box detection or pose estimation and rarely tackle these situations. In this paper, we address this important autonomous driving problem by solving three critical issues. First, to deal with data scarcity, we propose an effective training data generation process by fitting a 3D car model with dynamic parts to vehicles in real images before reconstructing human-vehicle interaction (VHI) scenarios. Our approach is fully automatic without any human interaction, which can generate a large number of vehicles in uncommon states (VUS) for training deep neural networks (DNNs). Second, to perform fine-grained vehicle perception, we present a multi-task network for VUS parsing and a multi-stream network for VHI parsing. Third, to quantitatively evaluate the effectiveness of our data augmentation approach, we build the first VUS dataset in real traffic scenarios (e.g., getting on/out or placing/removing luggage). Experimental results show that our approach advances other baseline methods in 2D detection and instance segmentation by a big margin (over 8%). In addition, our network yields large improvements in discovering and understanding these uncommon cases. Moreover, we have released the source code, the dataset, and the trained model on Github (https://github.com/zongdai/EditingForDNN).
We present a novel approach SAfE that can identify parts of an outdoor scene that are safe for driving, based on attention models. Our formulation is designed for hazardous weather conditions that can impair the visibility of human drivers as well as autonomous vehicles, increasing the risk of accidents. Our approach is unsupervised and uses domain adaptation, with entropy minimization and attention transfer discriminators, to leverage the large amounts of labeled data corresponding to clear weather conditions. Our attention transfer discriminator uses attention maps from the clear weather image to help the network learn relevant regions to attend to, on the images from the hazardous weather dataset. We conduct experiments on CityScapes simulated datasets depicting various weather conditions such as rain, fog and snow under different intensities, and additionally on Berkeley Deep Drive. Our result show that using attention models improves the standard unsupervised domain adaptation performance by 29.29%. Furthermore, we also compare with unsupervised domain adaptation methods and show an improvement of at least 12.02% (mIoU) over the state-of-the-art.