This work tackles the challenge of continuous sign language segmentation, a key task with huge implications for sign language translation and data annotation. We propose a transformer-based architecture that models the temporal dynamics of signing and frames segmentation as a sequence labeling problem using the Begin-In-Out (BIO) tagging scheme. Our method leverages the HaMeR hand features, and is complemented with 3D Angles. Extensive experiments show that our model achieves state-of-the-art results on the DGS Corpus, while our features surpass prior benchmarks on BSLCorpus.

We propose HandOcc, a novel framework for hand rendering based upon occupancy. Popular rendering methods such as NeRF are often combined with parametric meshes to provide deformable hand models. However, in doing so, such approaches present a trade-off between the fidelity of the mesh and the complexity and dimensionality of the parametric model. The simplicity of parametric mesh structures is appealing, but the underlying issue is that it binds methods to mesh initialization, making it unable to generalize to objects where a parametric model does not exist. It also means that estimation is tied to mesh resolution and the accuracy of mesh fitting. This paper presents a pipeline for meshless 3D rendering, which we apply to the hands. By providing only a 3D skeleton, the desired appearance is extracted via a convolutional model. We do this by exploiting a NeRF renderer conditioned upon an occupancy-based representation. The approach uses the hand occupancy to resolve hand-to-hand interactions further improving results, allowing fast rendering, and excellent hand appearance transfer. On the benchmark InterHand2.6M dataset, we achieved state-of-the-art results.

Photorealistic and controllable human avatars have gained popularity in the research community thanks to rapid advances in neural rendering, providing fast and realistic synthesis tools. However, a limitation of current solutions is the presence of noticeable blurring. To solve this problem, we propose GaussianGAN, an animatable avatar approach developed for photorealistic rendering of people in real-time. We introduce a novel Gaussian splatting densification strategy to build Gaussian points from the surface of cylindrical structures around estimated skeletal limbs. Given the camera calibration, we render an accurate semantic segmentation with our novel view segmentation module. Finally, a UNet generator uses the rendered Gaussian splatting features and the segmentation maps to create photorealistic digital avatars. Our method runs in real-time with a rendering speed of 79 FPS. It outperforms previous methods regarding visual perception and quality, achieving a state-of-the-art results in terms of a pixel fidelity of 32.94db on the ZJU Mocap dataset and 33.39db on the Thuman4 dataset.

Sign language representation learning presents unique challenges due to the complex spatio-temporal nature of signs and the scarcity of labeled datasets. Existing methods often rely either on models pre-trained on general visual tasks, that lack sign-specific features, or use complex multimodal and multi-branch architectures. To bridge this gap, we introduce a scalable, self-supervised framework for sign representation learning. We leverage important inductive (sign) priors during the training of our RGB model. To do this, we leverage simple but important cues based on skeletons while pretraining a masked autoencoder. These sign specific priors alongside feature regularization and an adversarial style agnostic loss provide a powerful backbone. Notably, our model does not require skeletal keypoints during inference, avoiding the limitations of keypoint-based models during downstream tasks. When finetuned, we achieve state-of-the-art performance for sign recognition on the WLASL, ASL-Citizen and NMFs-CSL datasets, using a simpler architecture and with only a single-modality. Beyond recognition, our frozen model excels in sign dictionary retrieval and sign translation, surpassing standard MAE pretraining and skeletal-based representations in retrieval. It also reduces computational costs for training existing sign translation models while maintaining strong performance on Phoenix2014T, CSL-Daily and How2Sign.

As robots increasingly coexist with humans, they must navigate complex, dynamic environments rich in visual information and implicit social dynamics, like when to yield or move through crowds. Addressing these challenges requires significant advances in vision-based sensing and a deeper understanding of socio-dynamic factors, particularly in tasks like navigation. To facilitate this, robotics researchers need advanced simulation platforms offering dynamic, photorealistic environments with realistic actors. Unfortunately, most existing simulators fall short, prioritizing geometric accuracy over visual fidelity, and employing unrealistic agents with fixed trajectories and low-quality visuals. To overcome these limitations, we developed a simulator that incorporates three essential elements: (1) photorealistic neural rendering of environments, (2) neurally animated human entities with behaviour management, and (3) an ego-centric robotic agent providing multi-sensor output. By utilizing advanced neural rendering techniques in a dual-NeRF simulator, our system produces high-fidelity, photorealistic renderings of both environments and human entities. Additionally, it integrates a state-of-the-art Social Force Model (SoFM) to model dynamic human-human and human-robot interactions, creating the first photorealistic and accessible human-robot simulation system powered by neural rendering. The code for the simulator is available at https://gitlab.surrey.ac.uk/gn00217/radiance-of-neural-fields-simulator/.

We explore symbolic policy optimization for various legged locomotion challenges; specifically walker environments ranging from bipedal to highly redundant systems with 128 legs. These represent a broad range of action space dimensionalities. We find that state-of-the-art symbolic policy optimization approaches struggle to scale to these higher dimensional problems, due to the need to iterate over action dimensions, and their reliance on a neural network anchor policy. We thus propose Fast Symbolic Policy (FSP) to accelerate the training of symbolic locomotion policies. This approach avoids the need to iterate over the action dimensions, and does not require a pre-trained neural network anchor. We also propose Dim-X, a method for effectively reducing the action space dimensionality using the inductive priors of legged locomotion. We demonstrate that FSP with Dim-X can learn symbolic policies, with improved scaling performance compared to the baselines, vastly exceeding that possible with previous symbolic techniques. We further show that Dim-X on its own can also be integrated into neural network policies to shorten their training time and improve scaling performance.

One of the largest challenges in the deployment of legged robots in the real world is deriving effective general gaits. In this paper, we present BeeTLe, which is a framework that enables terrain aware locomotion without the need for dedicated terrain sensors. BeeTLe is realised as a multi-expert policy Reinforcement Learning (RL) algorithm. This enables multiple gaits, applicable to different surface types, to be stored and shared in a single policy. Sensor free terrain awareness is incorporated using a Recurrent Neural Network (RNN) to infer surface type purely from actuator positions over time. The RNN achieves an accuracy of 94% in terrain identification out of 8 possible options. We demonstrate that BeeTLe achieves a greater performance than the baselines across a series of challenges including: the traversal of a flat plane, a tilted plane, a sequence of tilted planes and geometry modelling a natural hilly terrain. This is despite not seeing the sequence of tilted planes and the natural hilly terrain during training.The code, policy and simulated environments are available at: https://gitlab.surrey.ac.uk/rf00350/BeeTLe

Recent progress in Sign Language Translation has focussed primarily on improving the representational capacity of large language models to incorporate sign-language features. This work explores an alternative direction: enhancing the geometric properties of skeletal representations themselves. We propose Geo-Sign, a method that leverages the properties of hyperbolic geometry to model the hierarchical structure inherent in sign language kinematics. By projecting skeletal features derived from Spatio-Temporal Graph Convolutional Networks (ST-GCNs) into the Poincaré ball model, we aim to create more discriminative embeddings, particularly for fine-grained motions like finger articulations. We introduce a hyperbolic projection layer, a weighted Fréchet mean aggregation scheme, and a geometric contrastive loss operating directly in hyperbolic space. These components are integrated into an end-to-end translation framework as a regularisation function, to enhance the representations within the language model. This work demonstrates the potential of hyperbolic geometry to improve skeletal representations for Sign Language Translation, improving on SOTA RGB methods while preserving privacy and improving computational efficiency.

Sign languages, often categorised as low-resource languages, face significant challenges in achieving accurate translation due to the scarcity of parallel annotated datasets. This paper introduces Select and Reorder (S&R), a novel approach that addresses data scarcity by breaking down the translation process into two distinct steps: Gloss Selection (GS) and Gloss Reordering (GR). Our method leverages large spoken language models and the substantial lexical overlap between source spoken languages and target sign languages to establish an initial alignment. Both steps make use of Non-AutoRegressive (NAR) decoding for reduced computation and faster inference speeds. Through this disentanglement of tasks, we achieve state-of-the-art BLEU and Rouge scores on the Meine DGS Annotated (mDGS) dataset, demonstrating a substantial BLUE-1 improvement of 37.88% in Text to Gloss (T2G) Translation. This innovative approach paves the way for more effective translation models for sign languages, even in resource-constrained settings.

3D hand pose estimation from images has seen considerable interest from the literature, with new methods improving overall 3D accuracy. One current challenge is to address hand-to-hand interaction where self-occlusions and finger articulation pose a significant problem to estimation. Little work has applied physical constraints that minimize the hand intersections that occur as a result of noisy estimation. This work addresses the intersection of hands by exploiting an occupancy network that represents the hand's volume as a continuous manifold. This allows us to model the probability distribution of points being inside a hand. We designed an intersection loss function to minimize the likelihood of hand-to-point intersections. Moreover, we propose a new hand mesh parameterization that is superior to the commonly used MANO model in many respects including lower mesh complexity, underlying 3D skeleton extraction, watertightness, etc. On the benchmark Interhand2.6m dataset, the models trained using our intersection loss achieve better results than the state-of-the-art by significantly decreasing the number of hand intersections while lowering the mean per-joint positional error. Additionally, we demonstrate superior performance for 3D hand uplift on Re:interhand and SMILE datasets and show reduced hand-to-hand intersections for complex domains such as sign-language pose estimation.

This paper addresses the problem of diversity-aware sign language production, where we want to give an image (or sequence) of a signer and produce another image with the same pose but different attributes (e.g. gender, skin color). To this end, we extend the variational inference paradigm to include information about the pose and the conditioning of the attributes. This formulation improves the quality of the synthesised images. The generator framework is presented as a UNet architecture to ensure spatial preservation of the input pose, and we include the visual features from the variational inference to maintain control over appearance and style. We generate each body part with a separate decoder. This architecture allows the generator to deliver better overall results. Experiments on the SMILE II dataset show that the proposed model performs quantitatively better than state-of-the-art baselines regarding diversity, per-pixel image quality, and pose estimation. Quantitatively, it faithfully reproduces non-manual features for signers.

Recent years have seen significant progress in human image generation, particularly with the advancements in diffusion models. However, existing diffusion methods encounter challenges when producing consistent hand anatomy and the generated images often lack precise control over the hand pose. To address this limitation, we introduce a novel approach to pose-conditioned human image generation, dividing the process into two stages: hand generation and subsequent body outpainting around the hands. We propose training the hand generator in a multi-task setting to produce both hand images and their corresponding segmentation masks, and employ the trained model in the first stage of generation. An adapted ControlNet model is then used in the second stage to outpaint the body around the generated hands, producing the final result. A novel blending technique is introduced to preserve the hand details during the second stage that combines the results of both stages in a coherent way. This involves sequential expansion of the outpainted region while fusing the latent representations, to ensure a seamless and cohesive synthesis of the final image. Experimental evaluations demonstrate the superiority of our proposed method over state-of-the-art techniques, in both pose accuracy and image quality, as validated on the HaGRID dataset. Our approach not only enhances the quality of the generated hands but also offers improved control over hand pose, advancing the capabilities of pose-conditioned human image generation. The source code is available here.11https://github.com/apelykh/hand-to-diffusion

Phonetic representations are used when recording spoken languages, but no equivalent exists for recording signed languages. As a result, linguists have proposed several annotation systems that operate on the gloss or sub-unit level; however, these resources are notably irregular and scarce. Sign Language Production (SLP) aims to automatically translate spoken language sentences into continuous sequences of sign language. However, current state-of-the-art approaches rely on scarce linguistic resources to work. This has limited progress in the field. This paper introduces an innovative solution by transforming the continuous pose generation problem into a discrete sequence generation problem. Thus, overcoming the need for costly annotation. Although, if available, we leverage the additional information to enhance our approach. By applying Vector Quantisation (VQ) to sign language data, we first learn a codebook of short motions that can be combined to create a natural sequence of sign. Where each token in the codebook can be thought of as the lexicon of our representation. Then using a transformer we perform a translation from spoken language text to a sequence of codebook tokens. Each token can be directly mapped to a sequence of poses allowing the translation to be performed by a single network. Furthermore, we present a sign stitching method to effectively join tokens together. We evaluate on the RWTH-PHOENIX-Weather-2014T (PHOENIX14T) and the more challenging meineDGST (mDGS) datasets. An extensive evaluation shows our approach outperforms previous methods, increasing the BLED-1 back translation score by up to 72%.

Automatic Sign Language Translation requires the integration of both computer vision and natural language processing to effectively bridge the communication gap between sign and spoken languages. However, the deficiency in large-scale training data to support sign language translation means we need to leverage resources from spoken language. We introduce, Sign2GPT, a novel framework for sign language translation that utilizes large-scale pretrained vision and language models via lightweight adapters for gloss-free sign language translation. The lightweight adapters are crucial for sign language translation, due to the constraints imposed by limited dataset sizes and the computational requirements when training with long sign videos. We also propose a novel pretraining strategy that directs our encoder to learn sign representations from automatically extracted pseudo-glosses without requiring gloss order information or annotations. We evaluate our approach on two public benchmark sign language translation datasets, namely RWTH-PHOENIX-Weather 2014T and CSL-Daily, and improve on state-of-the-art gloss-free translation performance with a significant margin.

Significant advances in robotics and machine learning have resulted in many datasets designed to support research into autonomous vehicle technology. However, these datasets are rarely suitable for a wide variety of navigation tasks. For example, datasets that include multiple cameras often have short trajectories without loops that are unsuitable for the evaluation of longer-range SLAM or odometry systems, and datasets with a single camera often lack other sensors, making them unsuitable for sensor fusion approaches. Furthermore, alternative environmental representations such as semantic Bird’s Eye View (BEV) maps are growing in popularity, but datasets often lack accurate ground truth and are not flexible enough to adapt to new research trends.To address this gap, we introduce Campus Map, a novel large-scale multi-camera dataset with 2M images from 6 mounted cameras that includes GPS data and 64-beam, 125k point LiDAR scans totalling 8M points (raw packets also provided). The dataset consists of 16 sequences in a large car park and 6 long-term trajectories around a university campus that provide data to support research into a variety of autonomous driving and parking tasks. Long trajectories (average 10 min) and many loops make the dataset ideal for the evaluation of SLAM, odometry and loop closure algorithms, and we provide several state-of-the-art baselines.We also include 40k semantic BEV maps rendered from a digital twin. This novel approach to ground truth generation allows us to produce more accurate and crisp semantic maps than are currently available. We make the simulation environment available to allow researchers to adapt the dataset to their specific needs. Dataset available at: cvssp.org/data/twizy_data

This paper is a brief summary of the First WMT Shared Task on Sign Language Translation (WMT-SLT22), a project partly funded by EAMT. The focus of this shared task is automatic translation between signed and spoken languages. Details can be found on our website (https://www.wmt-slt.com/) or in the findings paper (Müller et al., 2022).

Graph convolutional networks (GCNs) enable end-to-end learning on graph structured data. However, many works assume a given graph structure. When the input graph is noisy or unavailable, one approach is to construct or learn a latent graph structure. These methods typically fix the choice of node degree for the entire graph, which is suboptimal. Instead, we propose a novel end-to-end differentiable graph generator which builds graph topologies where each node selects both its neighborhood and its size. Our module can be readily integrated into existing pipelines involving graph convolution operations, replacing the predetermined or existing adjacency matrix with one that is learned, and optimized, as part of the general objective. As such it is applicable to any GCN. We integrate our module into trajectory prediction, point cloud classification and node classification pipelines resulting in improved accuracy over other structure-learning methods across a wide range of datasets and GCN backbones. We will release the code.

Self-supervised monocular depth estimation (SS-MDE) has the potential to scale to vast quantities of data. Unfortunately, existing approaches limit themselves to the automotive domain, resulting in models incapable of generalizing to complex environments such as natural or indoor settings.To address this, we propose a large-scale SlowTV dataset curated from YouTube, containing an order of magnitude more data than existing automotive datasets. SlowTV contains 1.7M images from a rich diversity of environments, such as worldwide seasonal hiking, scenic driving and scuba diving. Using this dataset, we train an SS-MDE model that provides zero-shot generalization to a large collection of indoor/outdoor datasets. The resulting model outperforms all existing SSL approaches and closes the gap on supervised SoTA, despite using a more efficient architecture.We additionally introduce a collection of best-practices to further maximize performance and zero-shot generalization. This includes 1) aspect ratio augmentation, 2) camera intrinsic estimation, 3) support frame randomization and 4) flexible motion estimation. Code is available at https://github.com/jspenmar/slowtv_monodepth.

We approach instantaneous mapping, converting images to a top-down view of the world, as a translation problem. We show how a novel form of transformer network can be used to map from images and video directly to an overhead map or bird's-eye-view (BEV) of the world, in a single end-to-end network. We assume a 1-1 correspondence between a vertical scanline in the image, and rays passing through the camera location in an overhead map. This lets us formulate map generation from an image as a set of sequence-to-sequence translations. This constrained formulation, based upon a strong physical grounding of the problem, leads to a restricted transformer network that is convolutional in the horizontal direction only. The structure allows us to make efficient use of data when training, and obtains state-of-the-art results for instantaneous mapping of three large-scale datasets, including a 15\% and 30\% relative gain against existing best performing methods on the nuScenes and Argoverse datasets, respectively.

Estimating a semantically segmented bird's-eye-view (BEV) map from a single image has become a popular technique for autonomous control and navigation. However, they show an increase in localization error with distance from the camera. While such an increase in error is entirely expected -localization is harder at distance - much of the drop in performance can be attributed to the cues used by current texture-based models, in particular, they make heavy use of object-ground intersections (such as shadows) [10], which become increasingly sparse and uncertain for distant objects. In this work, we address these shortcomings in BEV-mapping by learning the spatial relationship between objects in a scene. We propose a graph neural network which predicts BEV objects from a monocular image by spatially reasoning about an object within the context of other objects. Our approach sets a new state-of-the-art in BEV estimation from monocular images across three large-scale datasets, including a 50% relative improvement for objects on nuScenes.

Sign languages are visual languages, with vocabularies as rich as their spoken language counterparts. However, current deep-learning based Sign Language Production (SLP) models produce under-articulated skeleton pose sequences from constrained vocabularies and this limits applicability. To be understandable and accepted by the deaf, an automatic SLP system must be able to generate co-articulated photo-realistic signing sequences for large domains of discourse. In this work, we tackle large-scale SLP by learning to co-articulate between dictionary signs, a method capable of producing smooth signing while scaling to unconstrained domains of discourse. To learn sign co-articulation, we propose a novel Frame Selection Network (FS-NET) that improves the temporal alignment of interpolated dictionary signs to continuous signing sequences. Additionally, we propose SIGNGAN, a pose-conditioned human synthesis model that produces photo-realistic sign language videos direct from skeleton pose. We propose a novel keypoint-based loss function which improves the quality of synthe-sized hand images. We evaluate our SLP model on the large-scale meineDGS (mDGS) corpus, conducting extensive user evaluation showing our FS-NET approach improves coarticulation of interpolated dictionary signs. Additionally, we show that SIGNGAN significantly outperforms all baseline methods for quantitative metrics, human perceptual studies and native deaf signer comprehension.

We approach instantaneous mapping, converting images to a top-down view of the world, as a translation problem. We show how a novel form of transformer network can be used to map from images and video directly to an overhead map or bird's-eye-view (BEV) of the world, in a single end-to-end network. We assume a 1–1 correspondence between a vertical scanline in the image, and rays passing through the camera location in an overhead map. This lets us formulate map generation from an image as a set of sequence-to-sequence translations. Posing the problem as translation allows the network to use the context of the image when interpreting the role of each pixel. This constrained formulation, based upon a strong physical grounding of the problem, leads to a restricted transformer network that is convolutional in the horizontal direction only. The structure allows us to make efficient use of data when training, and obtains state-of-the-art results for instantaneous mapping of three large-scale datasets, including a 15% and 30% relative gain against existing best performing methods on the nuScenes and Argoverse datasets, respectively.

To plan safe maneuvers and act with foresight, autonomous vehicles must be capable of accurately predicting the uncertain future. In the context of autonomous driving, deep neural networks have been successfully applied to learning pre-dictive models of human driving behavior from data. However, the predictions suffer from cascading errors, resulting in large inaccuracies over long time horizons. Furthermore, the learned models are black boxes, and thus it is often unclear how they arrive at their predictions. In contrast, rule-based models-which are informed by human experts-maintain long-term coherence in their predictions and are human-interpretable. However, such models often lack the sufficient expressiveness needed to capture complex real-world dynamics. In this work, we begin to close this gap by embedding the Intelligent Driver Model, a popular hand-crafted driver model, into deep neural networks. Our model's transparency can offer considerable advantages, e.g., in debugging the model and more easily interpreting its predictions. We evaluate our approach on a simulated merging scenario, showing that it yields a robust model that is end-to-end trainable and provides greater transparency at no cost to the model's predictive accuracy.

Motion estimation approaches typically employ sensor fusion techniques, such as the Kalman Filter, to handle individual sensor failures. More recently, deep learning-based fusion approaches have been proposed, increasing the performance and requiring less model-specific implementations. However, current deep fusion approaches often assume that sensors are synchronised, which is not always practical, especially for low-cost hardware. To address this limitation, in this work, we propose AFT-VO, a novel transformer-based sensor fusion architecture to estimate VO from multiple sensors. Our framework combines predictions from asynchronous multi-view cameras and accounts for the time discrepancies of measurements coming from different sources. Our approach first employs a Mixture Density Network (MDN) to estimate the probability distributions of the 6-DoF poses for every camera in the system. Then a novel transformer-based fusion module, AFT-VO, is introduced, which combines these asynchronous pose estimations, along with their confidences. More specifically, we introduce Discretiser and Source Encoding techniques which enable the fusion of multi-source asynchronous signals. We evaluate our approach on the popular nuScenes and KITTI datasets. Our experiments demonstrate that multi-view fusion for VO estimation provides robust and accurate trajectories, outperforming the state of the art in both challenging weather and lighting conditions.

The ability to produce large-scale maps for nav-igation, path planning and other tasks is a crucial step for autonomous agents, but has always been challenging. In this work, we introduce BEV-SLAM, a novel type of graph-based SLAM that aligns semantically-segmented Bird's Eye View (BEV) predictions from monocular cameras. We introduce a novel form of occlusion reasoning into BEV estimation and demonstrate its importance to aid spatial aggregation of BEV predictions. The result is a versatile SLAM system that can operate across arbitrary multi-camera configurations and can be seamlessly integrated with other sensors. We show that the use of multiple cameras significantly increases performance, and achieves lower relative error than high-performance GPS. The resulting system is able to create large, dense, globally-consistent world maps from monocular cameras mounted around an ego vehicle. The maps are metric and correctly-scaled, making them suitable for downstream navigation tasks.

Disentangled representations support a range of downstream tasks including causal reasoning, generative modeling, and fair machine learning. Unfortunately, disentanglement has been shown to be impossible without the incorporation of supervision or inductive bias. Given that supervision is often expensive or infeasible to acquire, we choose to incorporate structural inductive bias and present an unsupervised, deep State-Space-Model for Video Disentanglement (VDSM). The model disentangles latent time-varying and dynamic factors via the incorporation of hierarchical structure with a dynamic prior and a Mixture of Experts decoder. VDSM learns separate disentangled representations for the identity of the object or person in the video, and for the action being performed. We evaluate VDSM across a range of qualitative and quantitative tasks including identity and dynamics transfer, sequence generation, Fréchet Inception Distance, and factor classification. VDSM achieves state-of-the-art performance and exceeds adversarial methods, even when the methods use additional supervision.

Computational sign language research lacks the large-scale datasets that enables the creation of useful real-life applications. To date, most research has been limited to prototype systems on small domains of discourse, e.g. weather forecasts. To address this issue and to push the field forward, we release six datasets comprised of 190 hours of footage on the larger domain of news. From this, 20 hours of footage have been annotated by Deaf experts and interpreters and is made publicly available for research purposes. In this paper, we share the dataset collection process and tools developed to enable the alignment of sign language video and subtitles, as well as baseline translation results to underpin future research.

In this paper, we focus on the task of one-shot sign spotting, i.e. given an example of an isolated sign (query), we want to identify whether/where this sign appears in a continuous, co-articulated sign language video (target). To achieve this goal, we propose a transformer-based network, called Sign-Lookup. We employ 3D Convolutional Neural Networks (CNNs) to extract spatio-temporal representations from video clips. To solve the temporal scale discrepancies between the query and the target videos, we construct multiple queries from a single video clip using different frame-level strides. Self-attention is applied across these query clips to simulate a continuous scale space. We also utilize another self-attention module on the target video to learn the contextual within the sequence. Finally mutual-attention is used to match the temporal scales to localize the query within the target sequence. Extensive experiments demonstrate that the proposed approach can not only reliably identify isolated signs in continuous videos, regardless of the signers' appearance, but can also generalize to different sign languages. By taking advantage of the attention mechanism and the adaptive features, our model achieves state-of-the-art performance on the sign spotting task with accuracy as high as 96% on challenging benchmark datasets and significantly outperforming other approaches.

We present a new approach for synthesizing novel views of people in new poses. Our novel differentiable renderer enables the synthesis of highly realistic images from any viewpoint. Rather than operating over mesh-based structures, our renderer makes use of diffuse Gaussian primitives that directly represent the underlying skeletal structure of a human. Rendering these primitives gives results in a high-dimensional latent image, which is then transformed into an RGB image by a decoder network. The formulation gives rise to a fully differentiable framework that can be trained end-to-end. We demonstrate the effectiveness of our approach to image reconstruction on both the Human3.6M and Panoptic Studio datasets. We show how our approach can be used for motion transfer between individuals; novel view synthesis of individuals captured from just a single camera; to synthesize individuals from any virtual viewpoint; and to re-render people in novel poses. Code and video results are available at https://github.com/GuillaumeRochette/HumanViewSynthesis.

The visual anonymisation of sign language data is an essential task to address privacy concerns raised by large-scale dataset collection. Previous anonymisation techniques have either significantly affected sign comprehension or required manual, labour-intensive work. In this paper, we formally introduce the task of Sign Language Video Anonymisation (SLVA) as an automatic method to anonymise the visual appearance of a sign language video whilst retaining the meaning of the original sign language sequence. To tackle SLVA, we propose Anonysign, a novel automatic approach for visual anonymisation of sign language data. We first extract pose information from the source video to remove the original signer appearance. We next generate a photo-realistic sign language video of a novel appearance from the pose sequence, using image-to-image translation methods in a conditional variational autoencoder framework. An approximate posterior style distribution is learnt, which can be sampled from to synthesise novel human appearances. In addition, we propose a novel style loss that ensures style consistency in the anonymised sign language videos. We evaluate ANONYSIGN for the SLVA task with extensive quantitative and qualitative experiments highlighting both realism and anonymity of our novel human appearance synthesis. In addition, we formalise an anonymity perceptual study as an evaluation criteria for the SLVA task and showcase that video anonymisation using ANONYSIGN retains the original sign language content.

In this work, we propose a framework to collect a large-scale, diverse sign language dataset that can be used to train automatic sign language recognition models.The first contribution of this work is SDTrack, a generic method for signer tracking and diarisation in the wild. Our second contribution is SeeHear, a dataset of 90 hours of British Sign Language (BSL) content featuring more than 1000 signers, and including interviews, monologues and debates. Using SDTrack, the SeeHear dataset is annotated with 35K active signing tracks, with corresponding signer identities and subtitles, and 40K automatically localised sign labels. As a third contribution, we provide benchmarks for signer diarisation and sign recognition on SeeHear.

It is common practice to represent spoken languages at their phonetic level. However, for sign languages, this implies breaking motion into its constituent motion primitives. Avatar based Sign Language Production (SLP) has traditionally done just this, building up animation from sequences of hand motions, shapes and facial expressions. However, more recent deep learning based solutions to SLP have tackled the problem using a single network that estimates the full skeletal structure.We propose splitting the SLP task into two distinct jointly-trained sub-tasks. The first translation sub-task translates from spoken language to a latent sign language representation, with gloss supervision. Subsequently, the animation sub-task aims to produce expressive sign language sequences that closely resemble the learnt spatio-temporal representation. Using a progressive transformer for the translation sub-task, we propose a novel Mixture of Motion Primitives (MOMP) architecture for sign language animation. A set of distinct motion primitives are learnt during training, that can be temporally combined at inference to animate continuous sign language sequences.We evaluate on the challenging RWTH-PHOENIX-Weather-2014T (PHOENIX14T) dataset, presenting extensive ablation studies and showing that MOMP outperforms baselines in user evaluations. We achieve state-of-the-art back translation performance with an 11% improvement over competing results. Importantly, and for the first time, we showcase stronger performance for a full translation pipeline going from spoken language to sign, than from gloss to sign.

Constructing Birds-Eye-View (BEV) maps from monocular images is typically a complex multi-stage process involving the separate vision tasks of ground plane estimation, road segmentation and 3D object detection. However, recent approaches have adopted end-to-end solutions which warp image-based features from the image-plane to BEV while implicitly taking account of camera geometry. In this work, we show how such instantaneous BEV estimation of a scene can be learnt, and a better state estimation of the world can be achieved by incorporating temporal information. Our model learns a representation from monocular video through factorised 3D convolutions and uses this to estimate a BEV occupancy grid of the final frame. We achieve state-of-the-art results for BEV estimation from monocular images, and establish a new benchmark for single-scene BEV estimation from monocular video.

Across a wide range of applications, from autonomous vehicles to medical imaging, multi-spectral images provide an opportunity to extract additional information not present in color images. One of the most important steps in making this information readily available is the accurate estimation of dense correspondences between different spectra.Due to the nature of cross-spectral images, most correspondence solving techniques for the visual domain are simply not applicable. Furthermore, most cross-spectral techniques utilize spectra-specific characteristics to perform the alignment. In this work, we aim to address the dense correspondence estimation problem in a way that generalizes to more than one spectrum. We do this by introducing a novel cycle-consistency metric that allows us to self-supervise. This, combined with our spectra-agnostic loss functions, allows us to train the same network across multiple spectra.We demonstrate our approach on the challenging task of dense RGB-FIR correspondence estimation. We also show the performance of our unmodified network on the cases of RGB-NIR and RGB-RGB, where we achieve higher accuracy than similar self-supervised approaches. Our work shows that cross-spectral correspondence estimation can be solved in a common framework that learns to generalize alignment across spectra.

Visual Odometry (VO) is used in many applications including robotics and autonomous systems. However, traditional approaches based on feature matching are computationally expensive and do not directly address failure cases, instead relying on heuristic methods to detect failure. In this work, we propose a deep learning-based VO model to efficiently estimate 6-DoF poses, as well as a confidence model for these estimates. We utilise a CNN - RNN hybrid model to learn feature representations from image sequences. We then employ a Mixture Density Network (MDN) which estimates camera motion as a mixture of Gaussians, based on the extracted spatio-temporal representations. Our model uses pose labels as a source of supervision, but derives uncertainties in an unsupervised manner. We evaluate the proposed model on the KITTI and nuScenes datasets and report extensive quantitative and qualitative results to analyse the performance of both pose and uncertainty estimation. Our experiments show that the proposed model exceeds state-of-the-art performance in addition to detecting failure cases using the predicted pose uncertainty.

Attention is an important component of modern deep learning. However, less emphasis has been put on its inverse: ignoring distraction. Our daily lives require us to explicitly avoid giving attention to salient visual features that confound the task we are trying to accomplish. This visual prioritisation allows us to concentrate on important tasks while ignoring visual distractors.In this work, we introduce Neural Blindness, which gives an agent the ability to completely ignore objects or classes that are deemed distractors. More explicitly, we aim to render a neural network completely incapable of representing specific chosen classes in its latent space. In a very real sense, this makes the network "blind" to certain classes, allowing and agent to focus on what is important for a given task, and demonstrates how this can be used to improve localisation.

Abstract Sign languages are multi-channel visual languages, where signers use a continuous 3D space to communicate. Sign language production (SLP), the automatic translation from spoken to sign languages, must embody both the continuous articulation and full morphology of sign to be truly understandable by the Deaf community. Previous deep learning-based SLP works have produced only a concatenation of isolated signs focusing primarily on the manual features, leading to a robotic and non-expressive production. In this work, we propose a novel Progressive Transformer architecture, the first SLP model to translate from spoken language sentences to continuous 3D multi-channel sign pose sequences in an end-to-end manner. Our transformer network architecture introduces a counter decoding that enables variable length continuous sequence generation by tracking the production progress over time and predicting the end of sequence. We present extensive data augmentation techniques to reduce prediction drift, alongside an adversarial training regime and a mixture density network (MDN) formulation to produce realistic and expressive sign pose sequences. We propose a back translation evaluation mechanism for SLP, presenting benchmark quantitative results on the challenging PHOENIX14T dataset and setting baselines for future research. We further provide a user evaluation of our SLP model, to understand the Deaf reception of our sign pose productions.

Designing a controller for autonomous vehicles capable of providing adequate performance in all driving scenarios is challenging due to the highly complex environment and inability to test the system in the wide variety of scenarios which it may encounter after deployment. However, deep learning methods have shown great promise in not only providing excellent performance for complex and non-linear control problems, but also in generalising previously learned rules to new scenarios. For these reasons, the use of deep learning for vehicle control is becoming increasingly popular. Although important advancements have been achieved in this field, these works have not been fully summarised. This paper surveys a wide range of research works reported in the literature which aim to control a vehicle through deep learning methods. Although there exists overlap between control and perception, the focus of this paper is on vehicle control, rather than the wider perception problem which includes tasks such as semantic segmentation and object detection. The paper identifies the strengths and limitations of available deep learning methods through comparative analysis and discusses the research challenges in terms of computation, architecture selection, goal specification, generalisation, verification and validation, as well as safety. Overall, this survey brings timely and topical information to a rapidly evolving field relevant to intelligent transportation systems.

Prior work on Sign Language Translation has shown that having a mid-level sign gloss representation (effectively recognizing the individual signs) improves the translation performance drastically. In fact, the current state-of-the-art in translation requires gloss level tokenization in order to work. We introduce a novel transformer based architecture that jointly learns Continuous Sign Language Recognition and Translation while being trainable in an end-to-end manner. This is achieved by using a Connectionist Temporal Classification (CTC) loss to bind the recognition and translation problems into a single unified architecture. This joint approach does not require any ground-truth timing information, simultaneously solving two co-dependant sequence-to-sequence learning problems and leads to significant performance gains. We evaluate the recognition and translation performances of our approaches on the challenging RWTH-PHOENIX-Weather-2014T (PHOENIX14T) dataset. We report state-of-the-art sign language recognition and translation results achieved by our Sign Language Transformers. Our translation networks outperform both sign video to spoken language and gloss to spoken language translation models, in some cases more than doubling the performance (9.58 vs. 21.80 BLEU-4 Score). We also share new baseline translation results using transformer networks for several other text-to-text sign language translation tasks.

"Like night and day" is a commonly used expression to imply that two things are completely different. Unfortunately, this tends to be the case for current visual feature representations of the same scene across varying seasons or times of day. The aim of this paper is to provide a dense feature representation that can be used to perform localization, sparse matching or image retrieval, regardless of the current seasonal or temporal appearance. Recently, there have been several proposed methodologies for deep learning dense feature representations. These methods make use of ground truth pixel-wise correspondences between pairs of images and focus on the spatial properties of the features. As such, they don't address temporal or seasonal variation. Furthermore, obtaining the required pixel-wise correspondence data to train in cross-seasonal environments is highly complex in most scenarios. We propose Deja-Vu, a weakly supervised approach to learning season invariant features that does not require pixel-wise ground truth data. The proposed system only requires coarse labels indicating if two images correspond to the same location or not. From these labels, the network is trained to produce "similar" dense feature maps for corresponding locations despite environmental changes. Code will be made available at: https://github.com/jspenmar/DejaVu_Features.

In the current monocular depth research, the dominant approach is to employ unsupervised training on large datasets, driven by warped photometric consistency. Such approaches lack robustness and are unable to generalize to challenging domains such as nighttime scenes or adverse weather conditions where assumptions about photometric consistency break down. We propose DeFeat-Net (Depth & Feature network), an approach to simultaneously learn a cross-domain dense feature representation, alongside a robust depth-estimation framework based on warped feature consistency. The resulting feature representation is learned in an unsupervised manner with no explicit ground-truth correspondences required. We show that within a single domain, our technique is comparable to both the current state of the art in monocular depth estimation and supervised feature representation learning. However, by simultaneously learning features, depth and motion, our technique is able to generalize to challenging domains, allowing DeFeat-Net to outperform the current state-of-the-art with around 10% reduction in all error measures on more challenging sequences such as nighttime driving.

Fair and unbiased machine learning is an important and active field of research, as decision processes are increasingly driven by models that learn from data. Unfortunately, any biases present in the data may be learned by the model, thereby inappropriately transferring that bias into the decision making process. We identify the connection between the task of bias reduction and that of isolating factors common between domains whilst encouraging domain specific invariance. To isolate the common factors we combine the theory of deep latent variable models with information bottleneck theory for scenarios whereby data may be naturally paired across domains and no additional supervision is required. The result is the Nested Variational AutoEncoder (NestedVAE). Two outer VAEs with shared weights attempt to reconstruct the input and infer a latent space, whilst a nested VAE attempts to reconstruct the latent representation of one image, from the latent representation of its paired image. In so doing, the nested VAE isolates the common latent factors/causes and becomes invariant to unwanted factors that are not shared between paired images. We also propose a new metric to provide a balanced method of evaluating consistency and classifier performance across domains which we refer to as the Adjusted Parity metric. An evaluation of NestedVAE on both domain and attribute invariance, change detection, and learning common factors for the prediction of biological sex demonstrates that NestedVAE significantly outperforms alternative methods.

Variational AutoEncoders (VAEs) provide a means to generate representational latent embeddings. Previous research has highlighted the benefits of achieving representations that are disentangled, particularly for downstream tasks. However, there is some debate about how to encourage disentanglement with VAEs, and evidence indicates that existing implementations do not achieve disentanglement consistently. The evaluation of how well a VAE's latent space has been disentangled is often evaluated against our subjective expectations of which attributes should be disentangled for a given problem. Therefore, by definition, we already have domain knowledge of what should be achieved and yet we use unsupervised approaches to achieve it. We propose a weakly-supervised approach that incorporates any available domain knowledge into the training process to form a Gated-VAE. The process involves partitioning the representational embedding and gating backpropagation. All partitions are utilised on the forward pass but gradients are backpropagated through different partitions according to selected image/target pairings. The approach can be used to modify existing VAE models such as beta-VAE, InfoVAE and DIP-VAE-II. Experiments demonstrate that using gated backpropagation, latent factors are represented in their intended partition. The approach is applied to images of faces for the purpose of disentangling head-pose from facial expression. Quantitative metrics show that using Gated-VAE improves average disentanglement, completeness and informativeness, as compared with un-gated implementations. Qualitative assessment of latent traversals demonstrate its disentanglement of head-pose from expression, even when only weak/noisy supervision is available.

Deep learning has become an increasingly common technique for various control problems, such as robotic arm manipulation, robot navigation, and autonomous vehicles. However, the downside of using deep neural networks to learn control policies is their opaque nature and the difficulties of validating their safety. As the networks used to obtain state-of-the-art results become increasingly deep and complex, the rules they have learned and how they operate become more challenging to understand. This presents an issue, since in safety-critical applications the safety of the control policy must be ensured to a high confidence level. In this paper, we propose an automated black box testing framework based on adversarial reinforcement learning. The technique uses an adversarial agent, whose goal is to degrade the performance of the target model under test. We test the approach on an autonomous vehicle problem, by training an adversarial reinforcement learning agent, which aims to cause a deep neural network-driven autonomous vehicle to collide. Two neural networks trained for autonomous driving are compared, and the results from the testing are used to compare the robustness of their learned control policies. We show that the proposed framework is able to find weaknesses in both control policies that were not evident during online testing and therefore, demonstrate a significant benefit over manual testing methods.

Abstract The use of human-level semantic information to aid robotic tasks has recently become an important area for both Computer Vision and Robotics. This has been enabled by advances in Deep Learning that allow consistent and robust semantic understanding. Leveraging this semantic vision of the world has allowed human-level understanding to naturally emerge from many different approaches. Particularly, the use of semantic information to aid in localisation and reconstruction has been at the forefront of both fields. Like robots, humans also require the ability to localise within a structure. To aid this, humans have designed high-level semantic maps of our structures called floorplans. We are extremely good at localising in them, even with limited access to the depth information used by robots. This is because we focus on the distribution of semantic elements, rather than geometric ones. Evidence of this is that humans are normally able to localise in a floorplan that has not been scaled properly. In order to grant this ability to robots, it is necessary to use localisation approaches that leverage the same semantic information humans use. In this paper, we present a novel method for semantically enabled global localisation. Our approach relies on the semantic labels present in the floorplan. Deep Learning is leveraged to extract semantic labels from RGB images, which are compared to the floorplan for localisation. While our approach is able to use range measurements if available, we demonstrate that they are unnecessary as we can achieve results comparable to state-of-the-art without them.

Abstract We present a novel approach to automatic Sign Language Production using recent developments in Neural Machine Translation (NMT), Generative Adversarial Networks, and motion generation. Our system is capable of producing sign videos from spoken language sentences. Contrary to current approaches that are dependent on heavily annotated data, our approach requires minimal gloss and skeletal level annotations for training. We achieve this by breaking down the task into dedicated sub-processes. We first translate spoken language sentences into sign pose sequences by combining an NMT network with a Motion Graph. The resulting pose information is then used to condition a generative model that produces photo realistic sign language video sequences. This is the first approach to continuous sign video generation that does not use a classical graphical avatar. We evaluate the translation abilities of our approach on the PHOENIX14 T Sign Language Translation dataset. We set a baseline for text-to-gloss translation, reporting a BLEU-4 score of 16.34/15.26 on dev/test sets. We further demonstrate the video generation capabilities of our approach for both multi-signer and high-definition settings qualitatively and quantitatively using broadcast quality assessment metrics.

In this work we present a new approach to the field of weakly supervised learning in the video domain. Our method is relevant to sequence learning problems which can be split up into sub-problems that occur in parallel. Here, we experiment with sign language data. The approach exploits sequence constraints within each independent stream and combines them by explicitly imposing synchronisation points to make use of parallelism that all sub-problems share. We do this with multi-stream HMMs while adding intermediate synchronisation constraints among the streams. We embed powerful CNN-LSTM models in each HMM stream following the hybrid approach. This allows the discovery of attributes which on their own lack sufficient discriminative power to be identified. We apply the approach to the domain of sign language recognition exploiting the sequential parallelism to learn sign language, mouth shape and hand shape classifiers. We evaluate the classifiers on three publicly available benchmark data sets featuring challenging real-life sign language with over 1,000 classes, full sentence based lip-reading and articulated hand shape recognition on a fine-grained hand shape taxonomy featuring over 60 different hand shapes. We clearly outperform the state-of-the-art on all data sets and observe significantly faster convergence using the parallel alignment approach.

How do computers and intelligent agents view the world around them? Feature extraction and representation constitutes one the basic building blocks towards answering this question. Traditionally, this has been done with carefully engineered hand-crafted techniques such as HOG, SIFT or ORB. However, there is no "one size fits all" approach that satisfies all requirements. In recent years, the rising popularity of deep learning has resulted in a myriad of end-to-end solutions to many computer vision problems. These approaches, while successful, tend to lack scalability and can't easily exploit information learned by other systems. Instead, we propose SAND features, a dedicated deep learning solution to feature extraction capable of providing hierarchical context information. This is achieved by employing sparse relative labels indicating relationships or similarity of dissimilarity between image locations. The nature of these labels results in an almost infinite set of dissimilar examples to choose from. We demonstrate how the selection of negative examples during training can be used to modify the feature space and vary it's learned properties. To demonstrate the generality of this approach, we apply the proposed features to a multitude of tasks, each requiring different properties. This includes disparity estimation, semantic segmentation, self-localisation and SLAM. In all cases, we show how incorporating SAND features results in better or comparable results to the baseline, whilst requiring little to no additional training.

Sign language conveys information through multiple channels, such as hand shape, hand movement, and mouthing. Modeling this multichannel information is a highly challenging problem. In this paper, we elucidate the link between spoken language and sign language in terms of production phenomenon and perception phenomenon. Through this link we show that hidden Markov model-based approaches developed to model "articulatory" features for spoken language processing can be exploited to model the multichannel information inherent in sign language for sign language processing.

Accurate extrinsic sensor calibration is essential for both autonomous vehicles and robots. Traditionally this is an involved process requiring calibration targets, known fiducial markers and is generally performed in a lab. Moreover, even a small change in the sensor layout requires recalibration. With the anticipated arrival of consumer autonomous vehicles, there is demand for a system which can do this automatically, after deployment and without specialist human expertise. To solve these limitations, we propose a flexible framework which can estimate extrinsic parameters without an explicit calibration stage, even for sensors with unknown scale. Our first contribution builds upon standard hand-eye calibration by jointly recovering scale. Our second contribution is that our system is made robust to imperfect and degenerate sensor data, by collecting independent sets of poses and automatically selecting those which are most ideal. We show that our approach's robustness is essential for the target scenario. Unlike previous approaches, ours runs in real time and constantly estimates the extrinsic transform. For both an ideal experimental setup and a real use case, comparison against these approaches shows that we outperform the state-of-the-art. Furthermore, we demonstrate that the recovered scale may be applied to the full trajectory, circumventing the need for scale estimation via sensor fusion.

This paper proposes a Hybrid Approximate Representation (HAR) based on unifying several efficient approximations of the generalized reprojection error (which is known as the gold standard for multiview geometry). The HAR is an over-parameterization scheme where the approximation is applied simultaneously in multiple parameter spaces. A joint minimization scheme "HAR-Descent" can then solve the PnP problem efficiently, while remaining robust to approximation errors and local minima. The technique is evaluated extensively, including numerous synthetic benchmark protocols and the real-world data evaluations used in previous works. The proposed technique was found to have runtime complexity comparable to the fastest O(n) techniques, and up to 10 times faster than current state of the art minimization approaches. In addition, the accuracy exceeds that of all 9 previous techniques tested, providing definitive state of the art performance on the benchmarks, across all 90 of the experiments in the paper and supplementary material, which can be found on the Computer Society Digital Library at http://doi.ieeecomputersociety.org/10.1109/TPAMI.2018.2806446.

Sign Language Recognition (SLR) has been an active research field for the last two decades. However, most research to date has considered SLR as a naive gesture recognition problem. SLR seeks to recognize a sequence of continuous signs but neglects the underlying rich grammatical and linguistic structures of sign language that differ from spoken language. In contrast, we introduce the Sign Language Translation (SLT) problem. Here, the objective is to generate spoken language translations from sign language videos, taking into account the different word orders and grammar. We formalize SLT in the framework of Neural Machine Translation (NMT) for both end-to-end and pretrained settings (using expert knowledge). This allows us to jointly learn the spatial representations, the underlying language model, and the mapping between sign and spoken language. To evaluate the performance of Neural SLT, we collected the first publicly available Continuous SLT dataset, RWTH-PHOENIX-Weather 2014T1. It provides spoken language translations and gloss level annotations for German Sign Language videos of weather broadcasts. Our dataset contains over .95M frames with >67K signs from a sign vocabulary of >1K and >99K words from a German vocabulary of >2.8K. We report quantitative and qualitative results for various SLT setups to underpin future research in this newly established field. The upper bound for translation performance is calculated at 19.26 BLEU-4, while our end-to-end frame-level and gloss-level tokenization networks were able to achieve 9.58 and 18.13 respectively.

How does a person work out their location using a floorplan? It is probably safe to say that we do not explicitly measure depths to every visible surface and try to match them against different pose estimates in the floorplan. And yet, this is exactly how most robotic scan-matching algorithms operate. Similarly, we do not extrude the 2D geometry present in the floorplan into 3D and try to align it to the real-world. And yet, this is how most vision-based approaches localise. Humans do the exact opposite. Instead of depth, we use high level semantic cues. Instead of extruding the floorplan up into the third dimension, we collapse the 3D world into a 2D representation. Evidence of this is that many of the floorplans we use in everyday life are not accurate, opting instead for high levels of discriminative landmarks. In this work, we use this insight to present a global localisation approach that relies solely on the semantic labels present in the floorplan and extracted from RGB images. While our approach is able to use range measurements if available, we demonstrate that they are unnecessary as we can achieve results comparable to state-of-the-art without them.

This manuscript introduces the end-to-end embedding of a CNN into a HMM, while interpreting the outputs of the CNN in a Bayesian framework. The hybrid CNN-HMM combines the strong discriminative abilities of CNNs with the sequence modelling capabilities of HMMs. Most current approaches in the field of gesture and sign language recognition disregard the necessity of dealing with sequence data both for training and evaluation. With our presented end-to-end embedding we are able to improve over the state-of-the-art on three challenging benchmark continuous sign language recognition tasks by between 15 and 38% relative reduction in word error rate and up to 20% absolute. We analyse the effect of the CNN structure, network pretraining and number of hidden states. We compare the hybrid modelling to a tandem approach and evaluate the gain of model combination.

We propose a novel deep learning approach to solve simultaneous alignment and recognition problems (referred to as “Sequence-to-sequence” learning). We decompose the problem into a series of specialised expert systems referred to as SubUNets. The spatio-temporal relationships between these SubUNets are then modelled to solve the task, while remaining trainable end-to-end. The approach mimics human learning and educational techniques, and has a number of significant advantages. SubUNets allow us to inject domain-specific expert knowledge into the system regarding suitable intermediate representations. They also allow us to implicitly perform transfer learning between different interrelated tasks, which also allows us to exploit a wider range of more varied data sources. In our experiments we demonstrate that each of these properties serves to significantly improve the performance of the overarching recognition system, by better constraining the learning problem. The proposed techniques are demonstrated in the challenging domain of sign language recognition. We demonstrate state-of-the-art performance on hand-shape recognition (outperforming previous techniques by more than 30%). Furthermore, we are able to obtain comparable sign recognition rates to previous research, without the need for an alignment step to segment out the signs for recognition.

Reconstruction of 3D environments is a problem that has been widely addressed in the literature. While many approaches exist to perform reconstruction, few of them take an active role in deciding where the next observations should come from. Furthermore, the problem of travelling from the camera's current position to the next, known as pathplanning, usually focuses on minimising path length. This approach is ill-suited for reconstruction applications, where learning about the environment is more valuable than speed of traversal. We present a novel Scenic Route Planner that selects paths which maximise information gain, both in terms of total map coverage and reconstruction accuracy. We also introduce a new type of collaborative behaviour into the planning stage called opportunistic collaboration, which allows sensors to switch between acting as independent Structure from Motion (SfM) agents or as a variable baseline stereo pair. We show that Scenic Planning enables similar performance to state-of-the-art batch approaches using less than 0.00027% of the possible stereo pairs (3% of the views). Comparison against length-based pathplanning approaches show that our approach produces more complete and more accurate maps with fewer frames. Finally, we demonstrate the Scenic Pathplanner's ability to generalise to live scenarios by mounting cameras on autonomous ground-based sensor platforms and exploring an environment.

Action recognition "in the wild" is extremely challenging, particularly when complex 3D actions are projected down to the image plane, losing a great deal of information. The recent growth of 3D data in broadcast content and commercial depth sensors, makes it possible to overcome this. However, there is little work examining the best way to exploit this new modality. In this paper we introduce the Hollywood 3D benchmark, which is the first dataset containing "in the wild" action footage including 3D data. This dataset consists of 650 stereo video clips across 14 action classes, taken from Hollywood movies. We provide stereo calibrations and depth reconstructions for each clip. We also provide an action recognition pipeline, and propose a number of specialised depth-aware techniques including five interest point detectors and three feature descriptors. Extensive tests allow evaluation of different appearance and depth encoding schemes. Our novel techniques exploiting this depth allow us to reach performance levels more than triple those of the best baseline algorithm using only appearance information. The benchmark data, code and calibrations are all made available to the community.

Significant effort has been devoted within the visual tracking community to rapid learning of object properties on the fly. However, state-of-the-art approaches still often fail in cases such as rapid out-of-plane rotation, when the appearance changes suddenly. One of the major contributions of this paper is a radical rethinking of the traditional wisdom of modeling 3D motion as appearance changes during tracking. Instead, 3D motion is modeled as 3D motion. This intuitive but previously unexplored approach provides new possibilities in visual tracking research. First, 3D tracking is more general, as large out-of-plane motion is often fatal for 2D trackers, but helps 3D trackers to build better models. Second, the tracker's internal model of the object can be used in many different applications and it could even become the main motivation, with tracking supporting reconstruction rather than vice versa. This effectively bridges the gap between visual tracking and structure from motion. A new benchmark data set of sequences with extreme out-of-plane rotation is presented and an online leader-board offered to stimulate new research in the relatively underdeveloped area of 3D tracking. The proposed method, provided as a baseline, is capable of successfully tracking these sequences, all of which pose a considerable challenge to 2D trackers (error reduced by 46%).

This work presents a new approach to learning a framebased classifier on weakly labelled sequence data by embedding a CNN within an iterative EM algorithm. This allows the CNN to be trained on a vast number of example images when only loose sequence level information is available for the source videos. Although we demonstrate this in the context of hand shape recognition, the approach has wider application to any video recognition task where frame level labelling is not available. The iterative EM algorithm leverages the discriminative ability of the CNN to iteratively refine the frame level annotation and subsequent training of the CNN. By embedding the classifier within an EM framework the CNN can easily be trained on 1 million hand images. We demonstrate that the final classifier generalises over both individuals and data sets. The algorithm is evaluated on over 3000 manually labelled hand shape images of 60 different classes which will be released to the community. Furthermore, we demonstrate its use in continuous sign language recognition on two publicly available large sign language data sets, where it outperforms the current state-of-the-art by a large margin. To our knowledge no previous work has explored expectation maximization without Gaussian mixture models to exploit weak sequence labels for sign language recognition.

In this paper, we propose using 3D Convolutional Neural Networks for large scale user-independent continuous gesture recognition. We have trained an end-to-end deep network for continuous gesture recognition (jointly learning both the feature representation and the classifier). The network performs three-dimensional (i.e. space-time) convolutions to extract features related to both the appearance and motion from volumes of color frames. Space-time invariance of the extracted features is encoded via pooling layers. The earlier stages of the network are partially initialized using the work of Tran et al. before being adapted to the task of gesture recognition. An earlier version of the proposed method, which was trained for 11,250 iterations, was submitted to ChaLearn 2016 Continuous Gesture Recognition Challenge and ranked 2nd with the Mean Jaccard Index Score of 0.269235. When the proposed method was further trained for 28,750 iterations, it achieved state-of-the-art performance on the same dataset, yielding a 0.314779 Mean Jaccard Index Score.

Long-term tracking of an object, given only a single instance in an initial frame, remains an open problem. We propose a visual tracking algorithm, robust to many of the difficulties that often occur in real-world scenes. Correspondences of edge-based features are used, to overcome the reliance on the texture of the tracked object and improve invariance to lighting. Furthermore, we address long-term stability, enabling the tracker to recover from drift and to provide redetection following object disappearance or occlusion. The two-module principle is similar to the successful state-of-the-art long-term TLD tracker; however, our approach offers better performance in benchmarks and extends to cases of low-textured objects. This becomes obvious in cases of plain objects with no texture at all, where the edge-based approach proves the most beneficial. We perform several different experiments to validate the proposed method. First, results on short-term sequences show the performance of tracking challenging (low textured and/or transparent) objects that represent failure cases for competing the state-of-the-art approaches. Second, long sequences are tracked, including one of almost 30 000 frames, which, to the best of our knowledge, is the longest tracking sequence reported to date. This tests the redetection and drift resistance properties of the tracker. Finally, we report the results of the proposed tracker on the VOT Challenge 2013 and 2014 data sets as well as on the VTB1.0 benchmark, and we show relative performance of the tracker compared with its competitors. All the results are comparable with the state of the art on sequences with textured objects and superior on non-textured objects. The new annotated sequences are made publicly available.

We present a novel approach to 3D reconstruction which is inspired by the human visual system. This system unifies standard appearance matching and triangulation techniques with higher level reasoning and scene understanding, in order to resolve ambiguities between different interpretations of the scene. The types of reasoning integrated in the approach includes recognising common configurations of surface normals and semantic edges (e.g. convex, concave and occlusion boundaries). We also recognise the coplanar, collinear and symmetric structures which are especially common in man made environments.

Causal relationships can often be found in visual object tracking between the motions of the camera and that of the tracked object. This object motion may be an effect of the camera motion, e.g. an unsteady handheld camera. But it may also be the cause, e.g. the cameraman framing the object. In this paper we explore these relationships, and provide statistical tools to detect and quantify them, these are based on transfer entropy and stem from information theory. The relationships are then exploited to make predictions about the object location. The approach is shown to be an excellent measure for describing such relationships. On the VOT2013 dataset the prediction accuracy is increased by 62 % over the best non-causal predictor. We show that the location predictions are robust to camera shake and sudden motion, which is invaluable for any tracking algorithm and demonstrate this by applying causal prediction to two state-of-the-art trackers. Both of them benefit, Struck gaining a 7 % accuracy and 22 % robustness increase on the VTB1.1 benchmark, becoming the new state-of-the-art.

This paper tackles the problem of spotting a set of signs occuring in videos with sequences of signs. To achieve this, we propose to model the spatio-temporal signatures of a sign using an extension of sequential patterns that contain temporal intervals called Sequential Interval Patterns (SIP). We then propose a novel multi-class classifier that organises different sequential interval patterns in a hierarchical tree structure called a Hierarchical SIP Tree (HSP-Tree). This allows one to exploit any subsequence sharing that exists between different SIPs of different classes. Multiple trees are then combined together into a forest of HSP-Trees resulting in a strong classifier that can be used to spot signs. We then show how the HSP-Forest can be used to spot sequences of signs that occur in an input video. We have evaluated the method on both concatenated sequences of isolated signs and continuous sign sequences. We also show that the proposed method is superior in robustness and accuracy to a state of the art sign recogniser when applied to spotting a sequence of signs.

In this paper, an algorithm is presented for estimating scene flow, which is a richer, 3D analog of optical flow. The approach operates orders of magnitude faster than alternative techniques and is well suited to further performance gains through parallelized implementation. The algorithm employs multiple hypotheses to deal with motion ambiguities, rather than the traditional smoothness constraints, removing oversmoothing errors and providing significant performance improvements on benchmark data, over the previous state of the art. The approach is flexible and capable of operating with any combination of appearance and/or depth sensors, in any setup, simultaneously estimating the structure and motion if necessary. Additionally, the algorithm propagates information over time to resolve ambiguities, rather than performing an isolated estimation at each frame, as in contemporary approaches. Approaches to smoothing the motion field without sacrificing the benefits of multiple hypotheses are explored, and a probabilistic approach to occlusion estimation is demonstrated, leading to 10 and 15 percent improved performance, respectively. Finally, a data-driven tracking approach is described, and used to estimate the 3D trajectories of hands during sign language, without the need to model complex appearance variations at each viewpoint.

Action recognition in unconstrained situations is a difficult task, suffering from massive intra-class variations. It is made even more challenging when complex 3D actions are projected down to the image plane, losing a great deal of information. The recent emergence of 3D data, both in broadcast content, and commercial depth sensors, provides the possibility to overcome this issue. This paper presents a new dataset, for benchmarking action recognition algorithms in natural environments, while making use of 3D information. The dataset contains around 650 video clips, across 14 classes. In addition, two state of the art action recognition algorithms are extended to make use of the 3D data, and five new interest point detection strategies are also proposed, that extend to the 3D data. Our evaluation compares all 4 feature descriptors, using 7 different types of interest point, over a variety of threshold levels, for the Hollywood3D dataset. We make the dataset including stereo video, estimated depth maps and all code required to reproduce the benchmark results, available to the wider community.

We organized a Grand Challenge and Workshop on Multi-Modal Gesture Recognition.

This paper presents a novel, discriminative, multi-class classifier based on Sequential Pattern Trees. It is efficient to learn, compared to other Sequential Pattern methods, and scalable for use with large classifier banks. For these reasons it is well suited to Sign Language Recognition. Using deterministic robust features based on hand trajectories, sign level classifiers are built from sub-units. Results are presented both on a large lexicon single signer data set and a multi-signer Kinect™ data set. In both cases it is shown to out perform the non-discriminative Markov model approach and be equivalent to previous, more costly, Sequential Pattern (SP) techniques.

This paper presents a novel adaptation of fuzzy clustering and feature encoding for image classification. Visual word ambiguity has recently been successfully modeled by kernel codebooks to provide improvement in classification performance over the standard `Bag-of-Features' (BoF) approach, which uses hard partitioning and crisp logic for assignment of features to visual words. Motivated by this progress we utilize fuzzy logic to model the ambiguity and combine it with clustering to discover fuzzy visual words. The feature descriptors of an image are encoded using the learned fuzzy membership function associated with each word. The codebook built using this fuzzy encoding technique is demonstrated to provide superior performance over BoF. We use the Gustafson-Kessel algorithm which is an improvement over Fuzzy C-Means clustering and can adapt to local distributions. We evaluate our approach on several popular datasets and demonstrate that it consistently provides superior performance to the BoF approach.

We present an approach to iteratively cluster images and video in an efficient and intuitive manor. While many techniques use the traditional approach of time consuming groundtruthing large amounts of data [10, 16, 20, 23], this is increasingly infeasible as dataset size and complexity increase. Furthermore it is not applicable to the home user, who wants to intuitively group his/her own media without labelling the content. Instead we propose a solution that allows the user to select media that semantically belongs to the same class and use machine learning to this and other related content together. We introduce an signature descriptor and use min-Hash and greedy clustering to efficiently present the user with clusters of the dataset using multi-dimensional scaling. The image signatures of the dataset are then adjusted by APriori data mining identifying the common elements between a small subset of image signatures. This is able to both pull together true positive clusters and push apart false positive examples. The approach is tested on real videos harvested from the web using the state of the art YouTube dataset [18]. The accuracy of correct group label increases from 60.4% to 81.7% using 15 iterations of pulling and pushing the media around. While the process takes only 1 minute to compute the pair wise similarities of the image signatures and visualise the youtube whole dataset. © 2011. The copyright of this document resides with its authors.

This paper proposes a novel machine learning algorithm (SP-Boosting) to tackle the problem of lipreading by building visual sequence classifiers based on sequential patterns. We show that an exhaustive search of optimal sequential patterns is not possible due to the immense search space, and tackle this with a novel, efficient tree-search method with a set of pruning criteria. Crucially, the pruning strategies preserve our ability to locate the optimal sequential pattern. Additionally, the tree-based search method accounts for the training set’s boosting weight distribution. This temporal search method is then integrated into the boosting framework resulting in the SP-Boosting algorithm. We also propose a novel constrained set of strong classifiers that further improves recognition accuracy. The resulting learnt classifiers are applied to lipreading by performing multi-class recognition on the OuluVS database. Experimental results show that our method achieves state of the art recognition performane, using only a small set of sequential patterns.

This paper introduces a novel approach to social behaviour recognition governed by the exchange of non-verbal cues between people. We conduct experiments to try and deduce distinct rules that dictate the social dynamics of people in a conversation, and utilise semi-supervised computer vision techniques to extract their social signals such as laughing and nodding. Data mining is used to deduce frequently occurring patterns of social trends between a speaker and listener in both interested and not interested social scenarios. The confidence values from rules are utilised to build a Social Dynamic Model (SDM), that can then be used for classification and visualisation. By visualising the rules generated in the SDM, we can analyse distinct social trends between an interested and not interested listener in a conversation. Results show that these distinctions can be applied generally and used to accurately predict conversational interest.

This paper presents an approach to the categorisation of spatio-temporal activity in video, which is based solely on the relative distribution of feature points. Introducing a Relative Motion Descriptor for actions in video, we show that the spatio-temporal distribution of features alone (without explicit appearance information) effectively describes actions, and demonstrate performance consistent with state-of-the-art. Furthermore, we propose that for actions where noisy examples exist, it is not optimal to group all action examples as a single class. Therefore, rather than engineering features that attempt to generalise over noisy examples, our method follows a different approach: We make use of Random Sampling Consensus (RANSAC) to automatically discover and reject outlier examples within classes. We evaluate the Relative Motion Descriptor and outlier rejection approaches on four action datasets, and show that outlier rejection using RANSAC provides a consistent and notable increase in performance, and demonstrate superior performance to more complex multiple-feature based approaches.

We present a generic, efficient and iterative algorithm for interactively clustering classes of images and videos. The approach moves away from the use of large hand labelled training datasets, instead allowing the user to find natural groups of similar content based upon a handful of “seed” examples. Two efficient data mining tools originally developed for text analysis; min-Hash and APriori are used and extended to achieve both speed and scalability on large image and video datasets. Inspired by the Bag-of-Words (BoW) architecture, the idea of an image signature is introduced as a simple descriptor on which nearest neighbour classification can be performed. The image signature is then dynamically expanded to identify common features amongst samples of the same class. The iterative approach uses APriori to identify common and distinctive elements of a small set of labelled true and false positive signatures. These elements are then accentuated in the signature to increase similarity between examples and “pull” positive classes together. By repeating this process, the accuracy of similarity increases dramatically despite only a few training examples, only 10% of the labelled groundtruth is needed, compared to other approaches. It is tested on two image datasets including the caltech101 [9] dataset and on three state-of-the-art action recognition datasets. On the YouTube [18] video dataset the accuracy increases from 72% to 97% using only 44 labelled examples from a dataset of over 1200 videos. The approach is both scalable and efficient, with an iteration on the full YouTube dataset taking around 1 minute on a standard desktop machine.

The motion field of a scene can be used for object segmentation and to provide features for classification tasks like action recognition. Scene flow is the full 3D motion field of the scene, and is more difficult to estimate than it's 2D counterpart, optical flow. Current approaches use a smoothness cost for regularisation, which tends to over-smooth at object boundaries. This paper presents a novel formulation for scene flow estimation, a collection of moving points in 3D space, modelled using a particle filter that supports multiple hypotheses and does not oversmooth the motion field. In addition, this paper is the first to address scene flow estimation, while making use of modern depth sensors and monocular appearance images, rather than traditional multi-viewpoint rigs. The algorithm is applied to an existing scene flow dataset, where it achieves comparable results to approaches utilising multiple views, while taking a fraction of the time.

The field of Action Recognition has seen a large increase in activity in recent years. Much of the progress has been through incorporating ideas from single-frame object recognition and adapting them for temporal-based action recognition. Inspired by the success of interest points in the 2D spatial domain, their 3D (space-time) counterparts typically form the basic components used to describe actions, and in action recognition the features used are often engineered to fire sparsely. This is to ensure that the problem is tractable; however, this can sacrifice recognition accuracy as it cannot be assumed that the optimum features in terms of class discrimination are obtained from this approach. In contrast, we propose to initially use an overcomplete set of simple 2D corners in both space and time. These are grouped spatially and temporally using a hierarchical process, with an increasing search area. At each stage of the hierarchy, the most distinctive and descriptive features are learned efficiently through data mining. This allows large amounts of data to be searched for frequently reoccurring patterns of features. At each level of the hierarchy, the mined compound features become more complex, discriminative, and sparse. This results in fast, accurate recognition with real-time performance on high-resolution video. As the compound features are constructed and selected based upon their ability to discriminate, their speed and accuracy increase at each level of the hierarchy. The approach is tested on four state-of-the-art data sets, the popular KTH data set to provide a comparison with other state-of-the-art approaches, the Multi-KTH data set to illustrate performance at simultaneous multiaction classification, despite no explicit localization information provided during training. Finally, the recent Hollywood and Hollywood2 data sets provide challenging complex actions taken from commercial movie sequences. For all four data sets, the proposed hierarchical approach outperforms all other methods reported thus far in the literature and can achieve real-time operation.

This paper proposes a learned data-driven approach for accurate, real-time tracking of facial features using only intensity information. The task of automatic facial feature tracking is nontrivial since the face is a highly deformable object with large textural variations and motion in certain regions. Existing works attempt to address these problems by either limiting themselves to tracking feature points with strong and unique visual cues (e.g., mouth and eye corners) or by incorporating a priori information that needs to be manually designed (e.g., selecting points for a shape model). The framework proposed here largely avoids the need for such restrictions by automatically identifying the optimal visual support required for tracking a single facial feature point. This automatic identification of the visual context required for tracking allows the proposed method to potentially track any point on the face. Tracking is achieved via linear predictors which provide a fast and effective method for mapping pixel intensities into tracked feature position displacements. Building upon the simplicity and strengths of linear predictors, a more robust biased linear predictor is introduced. Multiple linear predictors are then grouped into a rigid flock to further increase robustness. To improve tracking accuracy, a novel probabilistic selection method is used to identify relevant visual areas for tracking a feature point. These selected flocks are then combined into a hierarchical multiresolution LP model. Finally, we also exploit a simple shape constraint for correcting the occasional tracking failure of a minority of feature points. Experimental results show that this method performs more robustly and accurately than AAMs, with minimal training examples on example sequences that range from SD quality to Youtube quality. Additionally, an analysis of the visual support consistency across different subjects is also provided.

We introduce a new algorithm for real-time interactive motion control and demonstrate its application to motion captured data, prerecorded videos, and HCI. Firstly, a data set of frames are projected into a lower dimensional space. An appearance model is learnt using a multivariate probability distribution. A novel approach to determining transition points is presented based on k-medoids, whereby appropriate points of intersection in the motion trajectory are derived as cluster centers. These points are used to segment the data into smaller subsequences. A transition matrix combined with a kernel density estimation is used to determine suitable transitions between the subsequences to develop novel motion. To facilitate real-time interactive control, conditional probabilities are used to derive motion given user commands. The user commands can come from any modality including auditory, touch, and gesture. The system is also extended to HCI using audio signals of speech in a conversation to trigger nonverbal responses from a synthetic listener in real-time. We demonstrate the flexibility of the model by presenting results ranging from data sets composed of vectorized images, 2-D, and 3-D point representations. Results show real-time interaction and plausible motion generation between different types of movement.

Research into facial expression recognition has predominantly been based upon near frontal view data. However, a recent 3D facial expression database (BU-3DFE database) has allowed empirical investigation of facial expression recognition across pose. In this paper, we investigate the effects of pose from frontal to profile view on facial expression recognition. Experiments are carried out on 100 subjects with 5 yaw angles over 6 prototypical expressions. Expressions have 4 levels of intensity from subtle to exaggerated. We evaluate features such as local binary patterns (LBPs) as well as various extensions of LBPs. In addition, a novel approach to facial expression recognition is proposed using local gabor binary patterns (LGBPs). Multi class support vector machines (SVMs) are used for classification. We investigate the effects of image resolution and pose on facial expression classification using a variety of different features.

This paper introduces a fully automated, unsupervised method to recognise sign from subtitles. It does this by using data mining to align correspondences in sections of videos. Based on head and hand tracking, a novel temporally constrained adaptation of a priori mining is used to extract similar regions of video, with the aid of a proposed contextual negative selection method. These regions are refined in the temporal domain to isolate the occurrences of similar signs in each example. The system is shown to automatically identify and segment signs from standard news broadcasts containing a variety of topics.

Within the field of action recognition, features and descriptors are often engineered to be sparse and invariant to transformation. While sparsity makes the problem tractable, it is not necessarily optimal in terms of class separability and classification. This paper proposes a novel approach that uses very dense corner features that are spatially and temporally grouped in a hierarchical process to produce an overcomplete compound feature set. Frequently reoccurring patterns of features are then found through data mining, designed for use with large data sets. The novel use of the hierarchical classifier allows real time operation while the approach is demonstrated to handle camera motion, scale, human appearance variations, occlusions and background clutter. The performance of classification, outperforms other state-of-the-art action recognition algorithms on the three datasets; KTH, multi-KTH, and Hollywood. Multiple action localisation is performed, though no groundtruth localisation data is required, using only weak supervision of class labels for each training sequence. The Hollywood dataset contain complex realistic actions from movies, the approach outperforms the published accuracy on this dataset and also achieves real time performance.

This paper proposes a learnt data-driven approach for accurate, real-time tracking of facial features using only intensity information. Constraints such as a-priori shape models or temporal models for dynamics are not required or used. Tracking facial features simply becomes the independent tracking of a set of points on the face. This allows us to cope with facial configurations not present in the training data. Tracking is achieved via linear predictors which provide a fast and effective method for mapping pixel-level information to tracked feature position displacements. To improve on this, a novel and robust biased linear predictor is proposed in this paper. Multiple linear predictors are grouped into a rigid flock to increase robustness. To further improve tracking accuracy, a novel probabilistic selection method is used to identify relevant visual areas for tracking a feature point. These selected flocks are then combined into a hierarchical multi-resolution LP model. Experimental results also show that this method performs more robustly and accurately than AAMs, without any a priori shape information and with minimal training examples.

A novel approach to learning and tracking arbitrary image features is presented. Tracking is tackled by learning the mapping from image inten-sity differences to displacements. Linear regression is used, resulting in low computational cost. An appearance model of the target is built on-the-fly by clustering sub-sampled image templates. The medoidshift algorithm is used to cluster the templates thus identifying various modes or aspects of the target appearance, each mode is associated to the most suitable set of linear predic-tors allowing piecewise linear regression from image intensity differences to warp updates. Despite no hard-coding or offline learning, excellent results are shown on three publicly available video sequences and comparisons with related approaches made. 1

Mutual Information (MI) is popular for registration via function optimisation. This work proposes an inverse compositional formulation of MI for Levenberg-Marquardt optimisation. This yields a constant Hessian, which may be pre-computed. Speed improvements of 15% were obtained, with convergence accuracies similar to those of the standard formulation.

Recently, the Nonparametric (NP) Windows has been proposed to estimate the statistics of real 1D and 2D signals. NP Windows is accurate, because it is equivalent to sampling images at a high (infinite) resolution for an assumed interpolation model. This paper extends the proposed approach to consider joint distributions of image-pairs. Second, Green's Theorem is used to simplify the previous NP Windows algorithm. Finally, a resolution-aware NP Windows algorithm is proposed to improve robustness to relative scaling between an image pair. Comparative testing of 2D image registration was performed using translation-only and affine transformations. Although more expensive than other methods, NP Windows frequently demonstrated superior performance for bias (distance between ground truth and global maximum) and frequency of convergence. Unlike other methods, the number of samples and the number of bins have little effect on NP Windows and the prior selection of a kernel is not required.

An approach for fast tracking of arbitrary image features with no prior model and no offline learning stage is presented. Fast tracking is achieved using banks of linear displacement predictors learnt online. A multi-modal appearance model is also learnt on-the-fly that facilitates the selection of subsets of predictors suitable for prediction in the next frame. The approach is demonstrated in real-time on a number of challenging video sequences and experimentally compared to other simultaneous modeling and tracking approaches with favourable results.

This paper presents an approach to object tracking which, given a single example of a target, learns a hierarchical constellation model of appearance and structure on the fly. The model becomes more robust over time as evidence of the variability of the object is acquired and added to the model. Tracking is performed in an optimised Lucas-Kanade type framework, using Mutual Information as a similarity metric. Several novelties are presented: an improved template update strategy using Bayes theorem, a multi-tier model topology, and a semi-automatic testing method. A critical comparison with other methods is made using exhaustive testing. In all 11 challenging test sequences were used with a mean length of 568 frames. 1

This paper presents a method for learning distance functions of arbitrary feature representations that is based on the concept of wormholes.We introduce wormholes and describe how it provides a method for warping the topology of visual representation spaces such that a meaningful distance between examples is available.Additionally, we show how a more general distance function can be learnt through the combination of many wormholes via an inter-wormhole network.We then demonstrate the application of the distance learning method on a variety of problems including nonlinear synthetic data, face illumination detection and the retrieval of images containing natural landscapes and man-made objects (e.g.cities).

This paper presents a scalable solution to the problem of tracking objects across spatially separated, uncalibrated, non-overlapping cameras. Unlike other approaches this technique uses an incremental learning method to create the spatio-temporal links between cameras, and thus model the posterior probability distribution of these links. This can then be used with an appearance model of the object to track across cameras. It requires no calibration or batch preprocessing and becomes more accurate over time as evidence is accumulated. 1

This paper presents a probabilistic framework of assembling detected human body parts into a full 2D human configuration. The face, torso, legs and hands are detected in cluttered scenes using boosted body part detectors trained by AdaBoost. Body configurations are assembled from the detected parts using RANSAC, and a coarse heuristic is applied to eliminate obvious outliers. An a priori mixture model of upper-body configurations is used to provide a pose likelihood for each configuration. A joint-likelihood model is then determined by combining the pose, part detector and corresponding skin model likelihoods. The assembly with the highest likelihood is selected by RANSAC, and the elbow positions are inferred. This paper also illustrates the combination of skin colour likelihood and detection likelihood to further reduce false hand and face detections. 1

A novel method for the simultaneous modeling and tracking (SMAT) of a feature set during motion sequence is proposed. The method requires no prior information. Instead the a posteriori distribution of appearance and shape is built up incrementally using an exemplar based approach. The resulting model is less optimal than when a priori data is used, but can be built in real-time. Data in any form may be used, provided a distance measure and a means to classify outliers exists. Here, a two tier implementation of SMAT is used: at the feature level, mutual information is used to track image patches; and at the object level, a structure model is built from the feature positions. As experiments demonstrate, the tracker is robust and operates in real-time without requiring prelearned data.

This paper presents a flexible monocular system capable of recognising sign lexicons far greater in number than previous approaches. The power of the system is due to four key elements: (i) Head and hand detection based upon boosting which removes the need for temperamental colour segmentation; (ii) A body centred description of activity which overcomes issues with camera placement, calibration and user; (iii) A two stage classification in which stage I generates a high level linguistic description of activity which naturally generalises and hence reduces training; (iv) A stage II classifier bank which does not require HMMs, further reducing training requirements. The outcome of which is a system capable of running in real-time, and generating extremely high recognition rates for large lexicons with as little as a single training instance per sign. We demonstrate classification rates as high as 92 % for a lexicon of 164 words with extremely low training requirements outperforming previous approaches where thousands of training examples are required. 1

This paper presents a real time approach to locate and track the upper torso of the human body. Our main interest is not in 3D biometric accuracy, but rather a sufficient discriminatory representation for visual interaction. The algorithm employs background suppression and a general approximation to body shape, applied within a particle filter framework, making use of integral images to maintain real-time performance. Furthermore, we present a novel method to disambiguate the hands of the subject and to predict the likely position of elbows. The final system is demonstrated segmenting multiple subjects from a cluttered scene at above real time operation. 1

and tracking objects when detailed information of the object's appearance is not available. The approach relies upon motion, shape cues and colour information to help in associating objects temporally within a video stream. Unlike previous applications of colour in object tracking, where relatively large-size targets are tracked, our method is designed to track small colour targets. Our approach uses a robust background model based around Expectation Maximisation to segment moving objects with very low false detection rates. The system also incorporates a shadow detection algorithm which helps alleviate standard environmental problems associated with such approaches. A colour transformation derived from anthropological studies to model colour distributions of low-resolution targets is used along with a probabilistic method of combining colour and motion information. This provides a robust visual tracking system which is capable of performing accurately and consistently within a real world visual surveillance arena. This paper shows the system successfully tracking multiple people moving independently and the ability of the approach to recover lost tracks due to occlusions and background clutter.

This work presents a piecewise linear approximation to non-linear Point Distribution Models for modelling the human hand. The work utilises the natural segmentation of shape space, inherent to the technique, to apply temporal constraints which can be used with CONDENSATION to support multiple hypotheses and quantum leaps through shape space. This paper presents a novel method by which the one-state transitions of the English Language are projected into shape space for tracking and model prediction using a HMM like approach. 1 Introduction Previous work by the author and other researchers have investigated statistical models of deformation [1-8]. These deformable models have been used to learn a priori shape and deformation from a training set of examples which, represent the shape and deformation of an object or a class of objects. Models are typically constructed that know what is valid deformation but not when deformation is valid. This important temporal constraint is benef...

This paper presents a model based approach to human body tracking in which the 2D silhouette of a moving human and the corresponding 3D skeletal structure are encapsulated within a non-linear Point Distribution Model. This statistical model allows a direct mapping to be achieved between the external boundary of a human and the anatomical position. It is shown how this information, along with the position of landmark features such as the hands and head can be used to reconstruct information about the pose and structure of the human body from a monoscopic view of a scene.