Cornelia Fermuller

Jiayi Wu, Haoming Cai, Cornelia Fermuller et al.

While Video Diffusion Models (VDMs) excel at synthesizing high-fidelity videos, enabling precise camera and scene control remains challenging. Existing methods predominantly rely on implicit diffusion priors to generate unobserved regions, inevitably leading to structural collapse during high-dynamic movements or complex occlusions. To address this challenge, we propose Real2SAM2Real, a framework that leverages 3D lifting models (e.g., SAM3D) to extract an explicitly editable 3D cache, serving as a robust geometric scaffold for the VDM. By capturing the entire 3D volume of foreground entities rather than just their visible shells, this cache injects holistic spatial priors into the VDM, providing dependable 3D-aware guidance for complex scene dynamics. To effectively leverage this 3D guidance while preserving pre-trained priors, we design a Soft Spatial-Aligned Injection mechanism alongside a minimally invasive fine-tuning strategy tailored for VDMs. Furthermore, we employ masked normal maps as a cross-modal bridge to construct a 3D-free data curation and perturbation pipeline. Extensive experiments demonstrate that Real2SAM2Real enables precise, decoupled control over both camera trajectories and multi-entity motions. By utilizing the complementary context from generative 3D caches, our framework overcomes typical breakdowns caused by over-reliance on diffusion priors, maintaining exceptional spatiotemporal consistency under large camera shifts and severe occlusions. Crucially, by decoupling geometry from appearance, our VDM-tailored 3D cache eradicates perspective ambiguities caused by structural holes and erroneous facades, as well as misleading cues from reflections and refractions. Project website is available at https://jiayi-wu-leo.github.io/real2sam2real

Bharatesh Chakravarthi, Aayush Atul Verma, Kostas Daniilidis et al.

Event-based vision, inspired by the human visual system, offers transformative capabilities such as low latency, high dynamic range, and reduced power consumption. This paper presents a comprehensive survey of event cameras, tracing their evolution over time. It introduces the fundamental principles of event cameras, compares them with traditional frame cameras, and highlights their unique characteristics and operational differences. The survey covers various event camera models from leading manufacturers, key technological milestones, and influential research contributions. It explores diverse application areas across different domains and discusses essential real-world and synthetic datasets for research advancement. Additionally, the role of event camera simulators in testing and development is discussed. This survey aims to consolidate the current state of event cameras and inspire further innovation in this rapidly evolving field. To support the research community, a GitHub page (https://github.com/chakravarthi589/Event-based-Vision_Resources) categorizes past and future research articles and consolidates valuable resources.

Daniel Deniz, Cornelia Fermuller, Eduardo Ros et al.

Neuromorphic visual sensors are artificial retinas that output sequences of asynchronous events when brightness changes occur in the scene. These sensors offer many advantages including very high temporal resolution, no motion blur and smart data compression ideal for real-time processing. In this study, we introduce an event-based dataset on fine-grained manipulation actions and perform an experimental study on the use of transformers for action prediction with events. There is enormous interest in the fields of cognitive robotics and human-robot interaction on understanding and predicting human actions as early as possible. Early prediction allows anticipating complex stages for planning, enabling effective and real-time interaction. Our Transformer network uses events to predict manipulation actions as they occur, using online inference. The model succeeds at predicting actions early on, building up confidence over time and achieving state-of-the-art classification. Moreover, the attention-based transformer architecture allows us to study the role of the spatio-temporal patterns selected by the model. Our experiments show that the Transformer network captures action dynamic features outperforming video-based approaches and succeeding with scenarios where the differences between actions lie in very subtle cues. Finally, we release the new event dataset, which is the first in the literature for manipulation action recognition. Code will be available at https://github.com/DaniDeniz/EventVisionTransformer.

Jingxi Chen, Yixiao Zhang, Xiaoye Qian et al.

Images can be viewed as layered compositions, foreground objects over background, with potential occlusions. This layered representation enables independent editing of elements, offering greater flexibility for content creation. Despite the progress in large generative models, decomposing a single image into layers remains challenging due to limited methods and data. We observe a strong connection between layer decomposition and in/outpainting tasks, and propose adapting a diffusion-based inpainting model for layer decomposition using lightweight finetuning. To further preserve detail in the latent space, we introduce a novel multi-modal context fusion module with linear attention complexity. Our model is trained purely on a synthetic dataset constructed from open-source assets and achieves superior performance in object removal and occlusion recovery, unlocking new possibilities in downstream editing and creative applications.

Anthony Zador, Jean-Marc Fellous, Terrence Sejnowski et al. · uw

Neuroscience and Artificial Intelligence (AI) have made impressive progress in recent years but remain only loosely interconnected. Based on a workshop convened by the National Science Foundation in August 2025, we identify three fundamental capability gaps in current AI: the inability to interact with the physical world, inadequate learning that produces brittle systems, and unsustainable energy and data inefficiency. We describe the neuroscience principles that address each: co-design of body and controller, prediction through interaction, multi-scale learning with neuromodulatory control, hierarchical distributed architectures, and sparse event-driven computation. We present a research roadmap organized around these principles at near, mid, and long-term horizons. We argue that realizing this program requires a new generation of researchers trained across the boundary between neuroscience and engineering, and describe the institutional conditions: interdisciplinary training, hardware access, community standards, and ethics, needed to support them. We conclude that NeuroAI, neuroscience-informed artificial intelligence, has the potential to overcome limitations of current AI while deepening our understanding of biological neural computation.

Peter Sutor, Dehao Yuan, Douglas Summers-Stay et al.

Hyperdimensional Computing affords simple, yet powerful operations to create long Hyperdimensional Vectors (hypervectors) that can efficiently encode information, be used for learning, and are dynamic enough to be modified on the fly. In this paper, we explore the notion of using binary hypervectors to directly encode the final, classifying output signals of neural networks in order to fuse differing networks together at the symbolic level. This allows multiple neural networks to work together to solve a problem, with little additional overhead. Output signals just before classification are encoded as hypervectors and bundled together through consensus summation to train a classification hypervector. This process can be performed iteratively and even on single neural networks by instead making a consensus of multiple classification hypervectors. We find that this outperforms the state of the art, or is on a par with it, while using very little overhead, as hypervector operations are extremely fast and efficient in comparison to the neural networks. This consensus process can learn online and even grow or lose models in real time. Hypervectors act as memories that can be stored, and even further bundled together over time, affording life long learning capabilities. Additionally, this consensus structure inherits the benefits of Hyperdimensional Computing, without sacrificing the performance of modern Machine Learning. This technique can be extrapolated to virtually any neural model, and requires little modification to employ - one simply requires recording the output signals of networks when presented with a testing example.

Eadom Dessalene, Michael Maynord, Cornelia Fermuller et al.

In this paper we introduce a rule-based, compositional, and hierarchical modeling of action using Therbligs as our atoms. Introducing these atoms provides us with a consistent, expressive, contact-centered representation of action. Over the atoms we introduce a differentiable method of rule-based reasoning to regularize for logical consistency. Our approach is complementary to other approaches in that the Therblig-based representations produced by our architecture augment rather than replace existing architectures' representations. We release the first Therblig-centered annotations over two popular video datasets - EPIC Kitchens 100 and 50-Salads. We also broadly demonstrate benefits to adopting Therblig representations through evaluation on the following tasks: action segmentation, action anticipation, and action recognition - observing an average 10.5\%/7.53\%/6.5\% relative improvement, respectively, over EPIC Kitchens and an average 8.9\%/6.63\%/4.8\% relative improvement, respectively, over 50 Salads. Code and data will be made publicly available.

Sheng Zhong, Zhongyang Ren, Xiya Zhu et al.

Event-based cameras are bio-inspired sensors with pixels that independently and asynchronously respond to brightness changes at microsecond resolution, offering the potential to handle visual tasks in challenging scenarios. However, due to the sparse information content in individual events, directly processing the raw event data to solve vision tasks is highly inefficient, which severely limits the applicability of state-of-the-art methods in real-time tasks, such as motion segmentation, a fundamental task for dynamic scene understanding. Incorporating normal flow as an intermediate representation to compress motion information from event clusters within a localized region provides a more effective solution. In this work, we propose a normal flow-based motion segmentation framework for event-based vision. Leveraging the dense normal flow directly learned from event neighborhoods as input, we formulate the motion segmentation task as an energy minimization problem solved via graph cuts, and optimize it iteratively with normal flow clustering and motion model fitting. By using a normal flow-based motion model initialization and fitting method, the proposed system is able to efficiently estimate the motion models of independently moving objects with only a limited number of candidate models, which significantly reduces the computational complexity and ensures real-time performance, achieving nearly a 800x speedup in comparison to the open-source state-of-the-art method. Extensive evaluations on multiple public datasets fully demonstrate the accuracy and efficiency of our framework.

Jingxi Chen, Botao He, Chahat Deep Singh et al.

One of the core activities of an active observer involves moving to secure a "better" view of the scene, where the definition of "better" is task-dependent. This paper focuses on the task of human pose estimation from videos capturing a person's activity. Self-occlusions within the scene can complicate or even prevent accurate human pose estimation. To address this, relocating the camera to a new vantage point is necessary to clarify the view, thereby improving 2D human pose estimation. This paper formalizes the process of achieving an improved viewpoint. Our proposed solution to this challenge comprises three main components: a NeRF-based Drone-View Data Generation Framework, an On-Drone Network for Camera View Error Estimation, and a Combined Planner for devising a feasible motion plan to reposition the camera based on the predicted errors for camera views. The Data Generation Framework utilizes NeRF-based methods to generate a comprehensive dataset of human poses and activities, enhancing the drone's adaptability in various scenarios. The Camera View Error Estimation Network is designed to evaluate the current human pose and identify the most promising next viewing angles for the drone, ensuring a reliable and precise pose estimation from those angles. Finally, the combined planner incorporates these angles while considering the drone's physical and environmental limitations, employing efficient algorithms to navigate safe and effective flight paths. This system represents a significant advancement in active 2D human pose estimation for an autonomous UAV agent, offering substantial potential for applications in aerial cinematography by improving the performance of autonomous human pose estimation and maintaining the operational safety and efficiency of UAVs.

Konstantinos Zampogiannis, Cornelia Fermuller, Yiannis Aloimonos

We introduce cilantro, an open-source C++ library for geometric and general-purpose point cloud data processing. The library provides functionality that covers low-level point cloud operations, spatial reasoning, various methods for point cloud segmentation and generic data clustering, flexible algorithms for robust or local geometric alignment, model fitting, as well as powerful visualization tools. To accommodate all kinds of workflows, cilantro is almost fully templated, and most of its generic algorithms operate in arbitrary data dimension. At the same time, the library is easy to use and highly expressive, promoting a clean and concise coding style. cilantro is highly optimized, has a minimal set of external dependencies, and supports rapid development of performant point cloud processing software in a wide variety of contexts.

Jingxi Chen, Brandon Y. Feng, Haoming Cai et al.

Video Frame Interpolation aims to recover realistic missing frames between observed frames, generating a high-frame-rate video from a low-frame-rate video. However, without additional guidance, the large motion between frames makes this problem ill-posed. Event-based Video Frame Interpolation (EVFI) addresses this challenge by using sparse, high-temporal-resolution event measurements as motion guidance. This guidance allows EVFI methods to significantly outperform frame-only methods. However, to date, EVFI methods have relied on a limited set of paired event-frame training data, severely limiting their performance and generalization capabilities. In this work, we overcome the limited data challenge by adapting pre-trained video diffusion models trained on internet-scale datasets to EVFI. We experimentally validate our approach on real-world EVFI datasets, including a new one that we introduce. Our method outperforms existing methods and generalizes across cameras far better than existing approaches.

Snehesh Shrestha, Yantian Zha, Saketh Banagiri et al.

Recent advancements in multimodal Human-Robot Interaction (HRI) datasets have highlighted the fusion of speech and gesture, expanding robots' capabilities to absorb explicit and implicit HRI insights. However, existing speech-gesture HRI datasets often focus on elementary tasks, like object pointing and pushing, revealing limitations in scaling to intricate domains and prioritizing human command data over robot behavior records. To bridge these gaps, we introduce NatSGD, a multimodal HRI dataset encompassing human commands through speech and gestures that are natural, synchronized with robot behavior demonstrations. NatSGD serves as a foundational resource at the intersection of machine learning and HRI research, and we demonstrate its effectiveness in training robots to understand tasks through multimodal human commands, emphasizing the significance of jointly considering speech and gestures. We have released our dataset, simulator, and code to facilitate future research in human-robot interaction system learning; access these resources at https://www.snehesh.com/natsgd/

Jingxi Chen, Brandon Y. Feng, Haoming Cai et al.

This paper addresses the novel challenge of ``rewinding'' time from a single captured image to recover the fleeting moments missed just before the shutter button is pressed. This problem poses a significant challenge in computer vision and computational photography, as it requires predicting plausible pre-capture motion from a single static frame, an inherently ill-posed task due to the high degree of freedom in potential pixel movements. We overcome this challenge by leveraging the emerging technology of neuromorphic event cameras, which capture motion information with high temporal resolution, and integrating this data with advanced image-to-video diffusion models. Our proposed framework introduces an event motion adaptor conditioned on event camera data, guiding the diffusion model to generate videos that are visually coherent and physically grounded in the captured events. Through extensive experimentation, we demonstrate the capability of our approach to synthesize high-quality videos that effectively ``rewind'' time, showcasing the potential of combining event camera technology with generative models. Our work opens new avenues for research at the intersection of computer vision, computational photography, and generative modeling, offering a forward-thinking solution to capturing missed moments and enhancing future consumer cameras and smartphones. Please see the project page at https://timerewind.github.io/ for video results and code release.

Zhongqiang Ren, Bunyod Suvonov, Guofei Chen et al.

This paper investigates Path planning Among Movable Obstacles (PAMO), which seeks a minimum cost collision-free path among static obstacles from start to goal while allowing the robot to push away movable obstacles (i.e., objects) along its path when needed. To develop planners that are complete and optimal for PAMO, the planner has to search a giant state space involving both the location of the robot as well as the locations of the objects, which grows exponentially with respect to the number of objects. This paper leverages a simple yet under-explored idea that, only a small fraction of this giant state space needs to be searched during planning as guided by a heuristic, and most of the objects far away from the robot are intact, which thus leads to runtime efficient algorithms. Based on this idea, this paper introduces two PAMO formulations, i.e., bi-objective and resource constrained problems in an occupancy grid, and develops PAMO*, a planning method with completeness and solution optimality guarantees, to solve the two problems. We then further extend PAMO* to hybrid-state PAMO* to plan in continuous spaces with high-fidelity interaction between the robot and the objects. Our results show that, PAMO* can often find optimal solutions within a second in cluttered maps with up to 400 objects.

Jingxi Chen, Zongxia Li, Zhichao Liu et al.

What role does the first frame play in video generation models? Traditionally, it's viewed as the spatial-temporal starting point of a video, merely a seed for subsequent animation. In this work, we reveal a fundamentally different perspective: video models implicitly treat the first frame as a conceptual memory buffer that stores visual entities for later reuse during generation. Leveraging this insight, we show that it's possible to achieve robust and generalized video content customization in diverse scenarios, using only 20-50 training examples without architectural changes or large-scale finetuning. This unveils a powerful, overlooked capability of video generation models for reference-based video customization.

Jiayi Wu, Tianfu Wang, Md Abu Bakr Siddique et al.

Underwater image restoration algorithms seek to restore the color, contrast, and appearance of a scene that is imaged underwater. They are a critical tool in applications ranging from marine ecology and aquaculture to underwater construction and archaeology. While existing pixel-domain diffusion-based image restoration approaches are effective at restoring simple scenes with limited depth variation, they are computationally intensive and often generate unrealistic artifacts when applied to scenes with complex geometry and significant depth variation. In this work we overcome these limitations by combining a novel network architecture (SLURPP) with an accurate synthetic data generation pipeline. SLURPP combines pretrained latent diffusion models -- which encode strong priors on the geometry and depth of scenes -- with an explicit scene decomposition -- which allows one to model and account for the effects of light attenuation and backscattering. To train SLURPP we design a physics-based underwater image synthesis pipeline that applies varied and realistic underwater degradation effects to existing terrestrial image datasets. This approach enables the generation of diverse training data with dense medium/degradation annotations. We evaluate our method extensively on both synthetic and real-world benchmarks and demonstrate state-of-the-art performance. Notably, SLURPP is over 200X faster than existing diffusion-based methods while offering ~ 3 dB improvement in PSNR on synthetic benchmarks. It also offers compelling qualitative improvements on real-world data. Project website https://tianfwang.github.io/slurpp/.

Chinmaya Devaraj, Cornelia Fermuller, Yiannis Aloimonos

Videos are more informative than images because they capture the dynamics of the scene. By representing motion in videos, we can capture dynamic activities. In this work, we introduce GPT-4 generated motion descriptions that capture fine-grained motion descriptions of activities and apply them to three action datasets. We evaluated several video-text models on the task of retrieval of motion descriptions. We found that they fall far behind human expert performance on two action datasets, raising the question of whether video-text models understand motion in videos. To address it, we introduce a method of improving motion understanding in video-text models by utilizing motion descriptions. This method proves to be effective on two action datasets for the motion description retrieval task. The results draw attention to the need for quality captions involving fine-grained motion information in existing datasets and demonstrate the effectiveness of the proposed pipeline in understanding fine-grained motion during video-text retrieval.

Tianyi Xiong, Jiayi Wu, Botao He et al.

By combining differentiable rendering with explicit point-based scene representations, 3D Gaussian Splatting (3DGS) has demonstrated breakthrough 3D reconstruction capabilities. However, to date 3DGS has had limited impact on robotics, where high-speed egomotion is pervasive: Egomotion introduces motion blur and leads to artifacts in existing frame-based 3DGS reconstruction methods. To address this challenge, we introduce Event3DGS, an {\em event-based} 3DGS framework. By exploiting the exceptional temporal resolution of event cameras, Event3GDS can reconstruct high-fidelity 3D structure and appearance under high-speed egomotion. Extensive experiments on multiple synthetic and real-world datasets demonstrate the superiority of Event3DGS compared with existing event-based dense 3D scene reconstruction frameworks; Event3DGS substantially improves reconstruction quality (+3dB) while reducing computational costs by 95\%. Our framework also allows one to incorporate a few motion-blurred frame-based measurements into the reconstruction process to further improve appearance fidelity without loss of structural accuracy.

Eadom Dessalene, Chinmaya Devaraj, Michael Maynord et al.

Human actions involving hand manipulations are structured according to the making and breaking of hand-object contact, and human visual understanding of action is reliant on anticipation of contact as is demonstrated by pioneering work in cognitive science. Taking inspiration from this, we introduce representations and models centered on contact, which we then use in action prediction and anticipation. We annotate a subset of the EPIC Kitchens dataset to include time-to-contact between hands and objects, as well as segmentations of hands and objects. Using these annotations we train the Anticipation Module, a module producing Contact Anticipation Maps and Next Active Object Segmentations - novel low-level representations providing temporal and spatial characteristics of anticipated near future action. On top of the Anticipation Module we apply Egocentric Object Manipulation Graphs (Ego-OMG), a framework for action anticipation and prediction. Ego-OMG models longer term temporal semantic relations through the use of a graph modeling transitions between contact delineated action states. Use of the Anticipation Module within Ego-OMG produces state-of-the-art results, achieving 1st and 2nd place on the unseen and seen test sets, respectively, of the EPIC Kitchens Action Anticipation Challenge, and achieving state-of-the-art results on the tasks of action anticipation and action prediction over EPIC Kitchens. We perform ablation studies over characteristics of the Anticipation Module to evaluate their utility.

Matthew Evanusa, Cornelia Fermuller, Yiannis Aloimonos

The brain is known to be a highly complex, asynchronous dynamical system that is highly tailored to encode temporal information. However, recent deep learning approaches to not take advantage of this temporal coding. Spiking Neural Networks (SNNs) can be trained using biologically-realistic learning mechanisms, and can have neuronal activation rules that are biologically relevant. This type of network is also structured fundamentally around accepting temporal information through a time-decaying voltage update, a kind of input that current rate-encoding networks have difficulty with. Here we show that a large, deep layered SNN with dynamical, chaotic activity mimicking the mammalian cortex with biologically-inspired learning rules, such as STDP, is capable of encoding information from temporal data. We argue that the randomness inherent in the network weights allow the neurons to form groups that encode the temporal data being inputted after self-organizing with STDP. We aim to show that precise timing of input stimulus is critical in forming synchronous neural groups in a layered network. We analyze the network in terms of network entropy as a metric of information transfer. We hope to tackle two problems at once: the creation of artificial temporal neural systems for artificial intelligence, as well as solving coding mechanisms in the brain.

Eadom Dessalene, Michael Maynord, Chinmaya Devaraj et al.

We introduce Egocentric Object Manipulation Graphs (Ego-OMG) - a novel representation for activity modeling and anticipation of near future actions integrating three components: 1) semantic temporal structure of activities, 2) short-term dynamics, and 3) representations for appearance. Semantic temporal structure is modeled through a graph, embedded through a Graph Convolutional Network, whose states model characteristics of and relations between hands and objects. These state representations derive from all three levels of abstraction, and span segments delimited by the making and breaking of hand-object contact. Short-term dynamics are modeled in two ways: A) through 3D convolutions, and B) through anticipating the spatiotemporal end points of hand trajectories, where hands come into contact with objects. Appearance is modeled through deep spatiotemporal features produced through existing methods. We note that in Ego-OMG it is simple to swap these appearance features, and thus Ego-OMG is complementary to most existing action anticipation methods. We evaluate Ego-OMG on the EPIC Kitchens Action Anticipation Challenge. The consistency of the egocentric perspective of EPIC Kitchens allows for the utilization of the hand-centric cues upon which Ego-OMG relies. We demonstrate state-of-the-art performance, outranking all other previous published methods by large margins and ranking first on the unseen test set and second on the seen test set of the EPIC Kitchens Action Anticipation Challenge. We attribute the success of Ego-OMG to the modeling of semantic structure captured over long timespans. We evaluate the design choices made through several ablation studies. Code will be released upon acceptance

John Kanu, Eadom Dessalene, Xiaomin Lin et al.

While traditional methods for instruction-following typically assume prior linguistic and perceptual knowledge, many recent works in reinforcement learning (RL) have proposed learning policies end-to-end, typically by training neural networks to map joint representations of observations and instructions directly to actions. In this work, we present a novel framework for learning to perform temporally extended tasks using spatial reasoning in the RL framework, by sequentially imagining visual goals and choosing appropriate actions to fulfill imagined goals. Our framework operates on raw pixel images, assumes no prior linguistic or perceptual knowledge, and learns via intrinsic motivation and a single extrinsic reward signal measuring task completion. We validate our method in two environments with a robot arm in a simulated interactive 3D environment. Our method outperforms two flat architectures with raw-pixel and ground-truth states, and a hierarchical architecture with ground-truth states on object arrangement tasks.

Anton Mitrokhin, Chengxi Ye, Cornelia Fermuller et al.

We present the first event-based learning approach for motion segmentation in indoor scenes and the first event-based dataset - EV-IMO - which includes accurate pixel-wise motion masks, egomotion and ground truth depth. Our approach is based on an efficient implementation of the SfM learning pipeline using a low parameter neural network architecture on event data. In addition to camera egomotion and a dense depth map, the network estimates pixel-wise independently moving object segmentation and computes per-object 3D translational velocities for moving objects. We also train a shallow network with just 40k parameters, which is able to compute depth and egomotion. Our EV-IMO dataset features 32 minutes of indoor recording with up to 3 fast moving objects simultaneously in the camera field of view. The objects and the camera are tracked by the VICON motion capture system. By 3D scanning the room and the objects, accurate depth map ground truth and pixel-wise object masks are obtained, which are reliable even in poor lighting conditions and during fast motion. We then train and evaluate our learning pipeline on EV-IMO and demonstrate that our approach far surpasses its rivals and is well suited for scene constrained robotics applications.

Konstantinos Zampogiannis, Cornelia Fermuller, Yiannis Aloimonos

In this paper, we introduce a non-rigid registration pipeline for pairs of unorganized point clouds that may be topologically different. Standard warp field estimation algorithms, even under robust, discontinuity-preserving regularization, tend to produce erratic motion estimates on boundaries associated with `close-to-open' topology changes. We overcome this limitation by exploiting backward motion: in the opposite motion direction, a `close-to-open' event becomes `open-to-close', which is by default handled correctly. At the core of our approach lies a general, topology-agnostic warp field estimation algorithm, similar to those employed in recently introduced dynamic reconstruction systems from RGB-D input. We improve motion estimation on boundaries associated with topology changes in an efficient post-processing phase. Based on both forward and (inverted) backward warp hypotheses, we explicitly detect regions of the deformed geometry that undergo topological changes by means of local deformation criteria and broadly classify them as `contacts' or `separations'. Subsequently, the two motion hypotheses are seamlessly blended on a local basis, according to the type and proximity of detected events. Our method achieves state-of-the-art motion estimation accuracy on the MPI Sintel dataset. Experiments on a custom dataset with topological event annotations demonstrate the effectiveness of our pipeline in estimating motion on event boundaries, as well as promising performance in explicit topological event detection.

Konstantinos Zampogiannis, Kanishka Ganguly, Cornelia Fermuller et al.

When we physically interact with our environment using our hands, we touch objects and force them to move: contact and motion are defining properties of manipulation. In this paper, we present an active, bottom-up method for the detection of actor-object contacts and the extraction of moved objects and their motions in RGBD videos of manipulation actions. At the core of our approach lies non-rigid registration: we continuously warp a point cloud model of the observed scene to the current video frame, generating a set of dense 3D point trajectories. Under loose assumptions, we employ simple point cloud segmentation techniques to extract the actor and subsequently detect actor-environment contacts based on the estimated trajectories. For each such interaction, using the detected contact as an attention mechanism, we obtain an initial motion segment for the manipulated object by clustering trajectories in the contact area vicinity and then we jointly refine the object segment and estimate its 6DOF pose in all observed frames. Because of its generality and the fundamental, yet highly informative, nature of its outputs, our approach is applicable to a wide range of perception and planning tasks. We qualitatively evaluate our method on a number of input sequences and present a comprehensive robot imitation learning example, in which we demonstrate the crucial role of our outputs in developing action representations/plans from observation.

Francisco Barranco, Cornelia Fermuller, Eduardo Ros

Clustering is crucial for many computer vision applications such as robust tracking, object detection and segmentation. This work presents a real-time clustering technique that takes advantage of the unique properties of event-based vision sensors. Since event-based sensors trigger events only when the intensity changes, the data is sparse, with low redundancy. Thus, our approach redefines the well-known mean-shift clustering method using asynchronous events instead of conventional frames. The potential of our approach is demonstrated in a multi-target tracking application using Kalman filters to smooth the trajectories. We evaluated our method on an existing dataset with patterns of different shapes and speeds, and a new dataset that we collected. The sensor was attached to the Baxter robot in an eye-in-hand setup monitoring real-world objects in an action manipulation task. Clustering accuracy achieved an F-measure of 0.95, reducing the computational cost by 88% compared to the frame-based method. The average error for tracking was 2.5 pixels and the clustering achieved a consistent number of clusters along time.

Anton Mitrokhin, Cornelia Fermuller, Chethan Parameshwara et al.

Event-based vision sensors, such as the Dynamic Vision Sensor (DVS), are ideally suited for real-time motion analysis. The unique properties encompassed in the readings of such sensors provide high temporal resolution, superior sensitivity to light and low latency. These properties provide the grounds to estimate motion extremely reliably in the most sophisticated scenarios but they come at a price - modern event-based vision sensors have extremely low resolution and produce a lot of noise. Moreover, the asynchronous nature of the event stream calls for novel algorithms. This paper presents a new, efficient approach to object tracking with asynchronous cameras. We present a novel event stream representation which enables us to utilize information about the dynamic (temporal) component of the event stream, and not only the spatial component, at every moment of time. This is done by approximating the 3D geometry of the event stream with a parametric model; as a result, the algorithm is capable of producing the motion-compensated event stream (effectively approximating egomotion), and without using any form of external sensors in extremely low-light and noisy conditions without any form of feature tracking or explicit optical flow computation. We demonstrate our framework on the task of independent motion detection and tracking, where we use the temporal model inconsistencies to locate differently moving objects in challenging situations of very fast motion.

Chengxi Ye, Yezhou Yang, Cornelia Fermuller et al.

We explain that the difficulties of training deep neural networks come from a syndrome of three consistency issues. This paper describes our efforts in their analysis and treatment. The first issue is the training speed inconsistency in different layers. We propose to address it with an intuitive, simple-to-implement, low footprint second-order method. The second issue is the scale inconsistency between the layer inputs and the layer residuals. We explain how second-order information provides favorable convenience in removing this roadblock. The third and most challenging issue is the inconsistency in residual propagation. Based on the fundamental theorem of linear algebra, we provide a mathematical characterization of the famous vanishing gradient problem. Thus, an important design principle for future optimization and neural network design is derived. We conclude this paper with the construction of a novel contractive neural network.

Went Luan, Yezhou Yang, Cornelia Fermuller et al.

In this work, we present a fast target detection framework for real-world robotics applications. Considering that an intelligent agent attends to a task-specific object target during execution, our goal is to detect the object efficiently. We propose the concept of early recognition, which influences the candidate proposal process to achieve fast and reliable detection performance. To check the target constraints efficiently, we put forward a novel policy to generate a sub-optimal checking order, and prove that it has bounded time cost compared to the optimal checking sequence, which is not achievable in polynomial time. Experiments on two different scenarios: 1) rigid object and 2) non-rigid body part detection validate our pipeline. To show that our method is widely applicable, we further present a human-robot interaction system based on our non-rigid body part detection.

Ren Mao, John S. Baras, Yezhou Yang et al.

In this paper we address the problem of robot movement adaptation under various environmental constraints interactively. Motion primitives are generally adopted to generate target motion from demonstrations. However, their generalization capability is weak while facing novel environments. Additionally, traditional motion generation methods do not consider the versatile constraints from various users, tasks, and environments. In this work, we propose a co-active learning framework for learning to adapt robot end-effector's movement for manipulation tasks. It is designed to adapt the original imitation trajectories, which are learned from demonstrations, to novel situations with various constraints. The framework also considers user's feedback towards the adapted trajectories, and it learns to adapt movement through human-in-the-loop interactions. The implemented system generalizes trained motion primitives to various situations with different constraints considering user preferences. Experiments on a humanoid platform validate the effectiveness of our approach.

Wentao Luan, Yezhou Yang, Cornelia Fermuller et al.

We consider the problem of object recognition in 3D using an ensemble of attribute-based classifiers. We propose two new concepts to improve classification in practical situations, and show their implementation in an approach implemented for recognition from point-cloud data. First, the viewing conditions can have a strong influence on classification performance. We study the impact of the distance between the camera and the object and propose an approach to fuse multiple attribute classifiers, which incorporates distance into the decision making. Second, lack of representative training samples often makes it difficult to learn the optimal threshold value for best positive and negative detection rate. We address this issue, by setting in our attribute classifiers instead of just one threshold value, two threshold values to distinguish a positive, a negative and an uncertainty class, and we prove the theoretical correctness of this approach. Empirical studies demonstrate the effectiveness and feasibility of the proposed concepts.

Chengxi Ye, Chen Zhao, Yezhou Yang et al.

LightNet is a lightweight, versatile and purely Matlab-based deep learning framework. The idea underlying its design is to provide an easy-to-understand, easy-to-use and efficient computational platform for deep learning research. The implemented framework supports major deep learning architectures such as Multilayer Perceptron Networks (MLP), Convolutional Neural Networks (CNN) and Recurrent Neural Networks (RNN). The framework also supports both CPU and GPU computation, and the switch between them is straightforward. Different applications in computer vision, natural language processing and robotics are demonstrated as experiments.

Chengxi Ye, Yezhou Yang, Cornelia Fermuller et al.

For robots that have the capability to interact with the physical environment through their end effectors, understanding the surrounding scenes is not merely a task of image classification or object recognition. To perform actual tasks, it is critical for the robot to have a functional understanding of the visual scene. Here, we address the problem of localizing and recognition of functional areas from an arbitrary indoor scene, formulated as a two-stage deep learning based detection pipeline. A new scene functionality testing-bed, which is complied from two publicly available indoor scene datasets, is used for evaluation. Our method is evaluated quantitatively on the new dataset, demonstrating the ability to perform efficient recognition of functional areas from arbitrary indoor scenes. We also demonstrate that our detection model can be generalized onto novel indoor scenes by cross validating it with the images from two different datasets.

Yezhou Yang, Yi Li, Cornelia Fermuller et al.

In this paper we consider the problem of continuously discovering image contents by actively asking image based questions and subsequently answering the questions being asked. The key components include a Visual Question Generation (VQG) module and a Visual Question Answering module, in which Recurrent Neural Networks (RNN) and Convolutional Neural Network (CNN) are used. Given a dataset that contains images, questions and their answers, both modules are trained at the same time, with the difference being VQG uses the images as input and the corresponding questions as output, while VQA uses images and questions as input and the corresponding answers as output. We evaluate the self talk process subjectively using Amazon Mechanical Turk, which show effectiveness of the proposed method.

Yezhou Yang, Yiannis Aloimonos, Cornelia Fermuller et al.

In this paper we present a formal computational framework for modeling manipulation actions. The introduced formalism leads to semantics of manipulation action and has applications to both observing and understanding human manipulation actions as well as executing them with a robotic mechanism (e.g. a humanoid robot). It is based on a Combinatory Categorial Grammar. The goal of the introduced framework is to: (1) represent manipulation actions with both syntax and semantic parts, where the semantic part employs $λ$-calculus; (2) enable a probabilistic semantic parsing schema to learn the $λ$-calculus representation of manipulation action from an annotated action corpus of videos; (3) use (1) and (2) to develop a system that visually observes manipulation actions and understands their meaning while it can reason beyond observations using propositional logic and axiom schemata. The experiments conducted on a public available large manipulation action dataset validate the theoretical framework and our implementation.

Somak Aditya, Yezhou Yang, Chitta Baral et al.

In this paper we propose the construction of linguistic descriptions of images. This is achieved through the extraction of scene description graphs (SDGs) from visual scenes using an automatically constructed knowledge base. SDGs are constructed using both vision and reasoning. Specifically, commonsense reasoning is applied on (a) detections obtained from existing perception methods on given images, (b) a "commonsense" knowledge base constructed using natural language processing of image annotations and (c) lexical ontological knowledge from resources such as WordNet. Amazon Mechanical Turk(AMT)-based evaluations on Flickr8k, Flickr30k and MS-COCO datasets show that in most cases, sentences auto-constructed from SDGs obtained by our method give a more relevant and thorough description of an image than a recent state-of-the-art image caption based approach. Our Image-Sentence Alignment Evaluation results are also comparable to that of the recent state-of-the art approaches.