We consider the Imitation Learning (IL) setup where expert data are not collected on the actual deployment environment but on a different version. To address the resulting distribution shift, we combine behavior cloning (BC) with a planner that is tasked to bring the agent back to states visited by the expert whenever the agent deviates from the demonstration distribution. The resulting algorithm, POIR, can be trained offline, and leverages online interactions to efficiently fine-tune its planner to improve performance over time. We test POIR on a variety of human-generated manipulation demonstrations in a realistic robotic manipulation simulator and show robustness of the learned policy to different initial state distributions and noisy dynamics.
Reasoning on the context of human beings is crucial for many real-world applications especially for those deploying autonomous systems (e.g. robots). In this paper, we present a new approach for context reasoning to further advance the field of human motion prediction. We therefore propose a neuro-symbolic approach for human motion prediction (NeuroSyM), which weights differently the interactions in the neighbourhood by leveraging an intuitive technique for spatial representation called Qualitative Trajectory Calculus (QTC). The proposed approach is experimentally tested on medium and long term time horizons using two architectures from the state of art, one of which is a baseline for human motion prediction and the other is a baseline for generic multivariate time-series prediction. Six datasets of challenging crowded scenarios, collected from both fixed and mobile cameras, were used for testing. Experimental results show that the NeuroSyM approach outperforms in most cases the baseline architectures in terms of prediction accuracy.
Spatiotemporal traffic data imputation is of great significance in intelligent transportation systems and data-driven decision-making processes. To make an accurate reconstruction from partially observed traffic data, we assert the importance of characterizing both global and local trends in traffic time series. In the literature, substantial prior works have demonstrated the effectiveness of utilizing low-rankness property of traffic data by matrix/tensor completion models. In this study, we first introduce a Laplacian kernel to temporal regularization for characterizing local trends in traffic time series, which can be formulated in the form of circular convolution. Then, we develop a low-rank Laplacian convolutional representation (LCR) model by putting the nuclear norm of a circulant matrix and the Laplacian temporal regularization together, which is proved to meet a unified framework that takes a fast Fourier transform (FFT) solution in a relatively low time complexity. Through extensive experiments on some traffic datasets, we demonstrate the superiority of LCR for imputing traffic time series of various time series behaviors (e.g., data noises and strong/weak periodicity). The proposed LCR model is an efficient and effective solution to large-scale traffic data imputation over the existing baseline models. Despite the LCR's application to time series data, the key modeling idea lies in bridging the low-rank models and the Laplacian regularization through FFT, which is also applicable to image inpainting. The adapted datasets and Python implementation are publicly available at https://github.com/xinychen/transdim.
Current video text spotting methods can achieve preferable performance, powered with sufficient labeled training data. However, labeling data manually is time-consuming and labor-intensive. To overcome this, using low-cost synthetic data is a promising alternative. This paper introduces a novel video text synthesis technique called FlowText, which utilizes optical flow estimation to synthesize a large amount of text video data at a low cost for training robust video text spotters. Unlike existing methods that focus on image-level synthesis, FlowText concentrates on synthesizing temporal information of text instances across consecutive frames using optical flow. This temporal information is crucial for accurately tracking and spotting text in video sequences, including text movement, distortion, appearance, disappearance, shelter, and blur. Experiments show that combining general detectors like TransDETR with the proposed FlowText produces remarkable results on various datasets, such as ICDAR2015video and ICDAR2013video. Code is available at https://github.com/callsys/FlowText.
In the context of robotic grasping, object segmentation encounters several difficulties when faced with dynamic conditions such as real-time operation, occlusion, low lighting, motion blur, and object size variability. In response to these challenges, we propose the Graph Mixer Neural Network that includes a novel collaborative contextual mixing layer, applied to 3D event graphs formed on asynchronous events. The proposed layer is designed to spread spatiotemporal correlation within an event graph at four nearest neighbor levels parallelly. We evaluate the effectiveness of our proposed method on the Event-based Segmentation (ESD) Dataset, which includes five unique image degradation challenges, including occlusion, blur, brightness, trajectory, scale variance, and segmentation of known and unknown objects. The results show that our proposed approach outperforms state-of-the-art methods in terms of mean intersection over the union and pixel accuracy. Code available at: https://github.com/sanket0707/GNN-Mixer.git
Image-based rendering techniques stand at the core of an immersive experience for the user, as they generate novel views given a set of multiple input images. Since they have shown good performance in terms of objective and subjective quality, the research community devotes great effort to their improvement. However, the large volume of data necessary to render at the receiver's side hinders applications in limited bandwidth environments or prevents their employment in real-time applications. We present LeHoPP, a method for input pixel pruning, where we examine the importance of each input pixel concerning the rendered view, and we avoid the use of irrelevant pixels. Even without retraining the image-based rendering network, our approach shows a good trade-off between synthesis quality and pixel rate. When tested in the general neural rendering framework, compared to other pruning baselines, LeHoPP gains between $0.9$ dB and $3.6$ dB on average.
We propose a machine-learning approach to model long-term out-of-sample dynamics of brain activity from task-dependent fMRI data. Our approach is a three stage one. First, we exploit Diffusion maps (DMs) to discover a set of variables that parametrize the low-dimensional manifold on which the emergent high-dimensional fMRI time series evolve. Then, we construct reduced-order-models (ROMs) on the embedded manifold via two techniques: Feedforward Neural Networks (FNNs) and the Koopman operator. Finally, for predicting the out-of-sample long-term dynamics of brain activity in the ambient fMRI space, we solve the pre-image problem coupling DMs with Geometric Harmonics (GH) when using FNNs and the Koopman modes per se. For our illustrations, we have assessed the performance of the two proposed schemes using a benchmark fMRI dataset with recordings during a visuo-motor task. The results suggest that just a few (for the particular task, five) non-linear coordinates of the high-dimensional fMRI time series provide a good basis for modelling and out-of-sample prediction of the brain activity. Furthermore, we show that the proposed approaches outperform the one-step ahead predictions of the naive random walk model, which, in contrast to our scheme, relies on the knowledge of the signals in the previous time step. Importantly, we show that the proposed Koopman operator approach provides, for any practical purposes, equivalent results to the FNN-GH approach, thus bypassing the need to train a non-linear map and to use GH to extrapolate predictions in the ambient fMRI space; one can use instead the low-frequency truncation of the DMs function space of L^2-integrable functions, to predict the entire list of coordinate functions in the fMRI space and to solve the pre-image problem.
Animal affective computing is a quickly growing field of research, where only recently first efforts to go beyond animal tracking into recognizing their internal states, such as pain and emotions, have emerged. In most mammals, facial expressions are an important channel for communicating information about these states. However, unlike the human domain, there is an acute lack of datasets that make automation of facial analysis of animals feasible. This paper aims to fill this gap by presenting a dataset called Cat Facial Landmarks in the Wild (CatFLW) which contains 2016 images of cat faces in different environments and conditions, annotated with 48 facial landmarks specifically chosen for their relationship with underlying musculature, and relevance to cat-specific facial Action Units (CatFACS). To the best of our knowledge, this dataset has the largest amount of cat facial landmarks available. In addition, we describe a semi-supervised (human-in-the-loop) method of annotating images with landmarks, used for creating this dataset, which significantly reduces the annotation time and could be used for creating similar datasets for other animals. The dataset is available on request.
Simulation engines are widely adopted in robotics. However, they lack either full simulation control, ROS integration, realistic physics, or photorealism. Recently, synthetic data generation and realistic rendering has advanced tasks like target tracking and human pose estimation. However, when focusing on vision applications, there is usually a lack of information like sensor measurements or time continuity. On the other hand, simulations for most robotics tasks are performed in (semi)static environments, with specific sensors and low visual fidelity. To solve this, we introduced in our previous work a fully customizable framework for generating realistic animated dynamic environments (GRADE) [1]. We use GRADE to generate an indoor dynamic environment dataset and then compare multiple SLAM algorithms on different sequences. By doing that, we show how current research over-relies on known benchmarks, failing to generalize. Our tests with refined YOLO and Mask R-CNN models provide further evidence that additional research in dynamic SLAM is necessary. The code, results, and generated data are provided as open-source at https://eliabntt.github.io/grade-rrSimulation of Dynamic Environments for SLAM
Many of us researchers take extra measures to control for known-unknowns. However, unknown-unknowns can, at best, be negligible, but otherwise, they could produce unreliable data that might have dire consequences in real-life downstream applications. Human-Robot Interaction standards informed by empirical data could save us time and effort and provide us with the path toward the robots of the future. To this end, we share some of our pilot studies, lessons learned, and how they affected the outcome of our experiments. While these aspects might not be publishable in themselves, we hope our work might save time and effort for other researchers towards their research and serve as additional considerations for discussion at the workshop.