We investigate a new task in human motion prediction, which aims to forecast future body poses from historically observed sequences while accounting for arbitrary latency. This differs from existing works that assume an ideal scenario where future motions can be "instantaneously" predicted, thereby neglecting time delays caused by network transmission and algorithm execution. Addressing this task requires tackling two key challenges: The length of latency period can vary significantly across samples; the prediction model must be efficient. In this paper, we propose ALIEN, which treats the motion as a continuous function parameterized by a neural network, enabling predictions under any latency condition. By incorporating Mamba-like linear attention as a hyper-network and designing subsequent low-rank modulation, ALIEN efficiently learns a set of implicit neural representation weights from the observed motion to encode instance-specific information. Additionally, our model integrates the primary motion prediction task with an extra-designed variable-delay pose reconstruction task in a unified multi-task learning framework, enhancing its ability to capture richer motion patterns. Extensive experiments demonstrate that our approach outperforms state-of-the-art baselines adapted for our new task, while maintaining competitive performance in traditional prediction setting.

Making accurate prediction of human motions based on the historical observation is a crucial technology for robots to collaborate with humans. Existing human motion prediction methods are all built under an ideal assumption that robots can instantaneously react, which ignores the time delay introduced during data processing & analysis and future reaction planning – jointly known as "response latency". Consequently, the predictions made within this latency period become meaningless for practical use, as part of the time has passed and the corresponding real motions have already occurred before robot deliver its reaction. In this paper, we argue that the seemingly meaningless prediction period, however, can be leveraged to enhance prediction accuracy significantly. We propose LAL, a Latency-aware Auxiliary Learning framework, which shifts the existing "reaction instantaneous" convention into a new motion prediction paradigm with both latency compatibility and utility. The framework consists of two branches handling different tasks: the primary branch learns to directly predict the valid target (excluding the beginning latency period) based on observation; while the auxiliary branch learns the same target, but based on the reformed observation with additional latency data incorporated. A direct and effective way of auxiliary feature sharing is forced by our tailored consistency loss, to gradually integrate auxiliary latency insights into the primary prediction branch. Estimated feature statistics-based alignment method is presented as optional step for primary branch refinement. Experiments show that LAL achieves significant improvement on prediction accuracy, without additional time consumption during testing.

The emergence of text-driven motion synthesis technique provides animators with great potential to create efficiently. However, in most cases, textual expressions only contain general and qualitative motion descriptions, while lack fine depiction and sufficient intensity, leading to the synthesized motions that either (a) semantically compliant but uncontrollable over specific pose details, or (b) even deviates from the provided descriptions, bringing animators with undesired cases. In this paper, we propose DiffKFC, a conditional diffusion model for text-driven motion synthesis with KeyFrames Collaborated, enabling realistic generation with collaborative and efficient dual-level control: coarse guidance at semantic level, with only few keyframes for direct and fine-grained depiction down to body posture level. Unlike existing inference-editing diffusion models that incorporate conditions without training, our conditional diffusion model is explicitly trained and can fully exploit correlations among texts, keyframes and the diffused target frames. To preserve the control capability of discrete and sparse keyframes, we customize dilated mask attention modules where only partial valid tokens participate in local-to-global attention, indicated by the dilated keyframe mask. Additionally, we develop a simple yet effective smoothness prior, which steers the generated frames towards seamless keyframe transitions at inference. Extensive experiments show that our model not only achieves state-of-the-art performance in terms of semantic fidelity, but more importantly, is able to satisfy animator requirements through fine-grained guidance without tedious labor.

Domain shift is a challenge for supervised human pose estimation, where the source data and target data come from different distributions. This is why pose estimation methods generally perform worse on the test set than on the training set. Recently, test-time adaptation has proven to be an effective way to deal with domain shift in human pose estimation. Although the performance on the target domain has been improved, existing methods require a large number of weight updates for convergence, which is time-consuming and brings catastrophic forgetting. To solve these issues, we propose a meta-auxiliary learning method to achieve fast adaptation for domain shift during inference. Specifically, we take human pose estimation as the supervised primary task, and propose body-specific image inpainting as a self-supervised auxiliary task. First, we Jointly train the primary and auxiliary tasks to get a pre-trained model on the source domain. Then, meta-training correlates the performance of the two tasks to learn a good weight initialization. Finally, meta-testing adapts the meta-learned model to the target data through self-supervised learning. Benefiting from the meta-learning paradigm, the proposed method enables fast adaptation to the target domain while preserving the source domain knowledge. The carefully designed auxiliary task better pays attention to human-related semantics in a single image. Extensive experiments demonstrate the effectiveness of our test-time fast adaptation.

In the academic field, the research on human motion pre-diction tasks mainly focuses on exploiting the observed in-formation to forecast human movements accurately in the near future horizon. However, a significant gap appears when it comes to the application field, as current models are all trained offline, with fixed parameters that are inher-ently suboptimal to handle the complex yet ever-changing nature of human behaviors. To bridge this gap, in this pa-per, we introduce the task of online meta adaptation for hu-man motion prediction, based on the insight that finding “smart weights” capable of swift adjustments to suit dif-ferent motion contexts along the time is a key to improving predictive accuracy. We propose MoML, which ingeniously borrows the bilevel optimization spirit of model-agnostic meta-learning, to transform previous predictive mistakes into strong inductive biases to guide online adaptation. This is achieved by our MoAdapter blocks that can learn er-ror information by facilitating efficient adaptation via a few gradient steps, which fine-tunes our meta-learned “smart” initialization produced by the generic predictor. Considering real-time requirements in practice, we further propose Fast-MoML, a more efficient variant of MoML that features a closed-form solution instead of conventional gradient up-date. Experimental results show that our approach can ef-fectively bring many existing offline motion prediction mod-els online, and improves their predictive accuracy.

Generating realistic human motions with high framerate is an underexplored task, due to the varied framerates of training data, huge memory burden brought by high framerates and slow sampling speed of generative models. Recent advances make a compromise for training by downsampling high-framerate details away and discarding low-framerate samples, which suffer from severe information loss and restricted-framerate generation. In this paper, we found that the recent emerging paradigm of Implicit Neural Representations (INRs) that encode a signal into a continuous function can effectively tackle this challenging problem. To this end, we introduce NeRM, a generative model capable of taking advantage of varied-size data and capturing variational distribution of motions for high-framerate motion synthesis. By optimizing latent representation and a auto-decoder conditioned on temporal coordinates, NeRM learns continuous motion fields of sampled motion clips that ingeniously avoid explicit modeling of raw varied-size motions. This expressive latent representation is then used to learn a diffusion model that enables both unconditional and conditional generation of human motions. We demonstrate that our approach achieves competitive results with state-of-the-art methods, and can generate arbitrary framerate motions. Additionally, we show that NeRM is not only memory-friendly, but also highly efficient even when generating high-framerate motions.

Heatmap regression has dominated human pose estimation due to its superior performance and strong generalization. To meet the requirements of traditional explicit neural networks for output form, existing heatmap-based methods discretize the originally continuous heatmap representation into 2D pixel arrays, which leads to performance degradation due to the introduction of quantization errors. This problem is significantly exacerbated as the size of the input image decreases, which makes heatmap-based methods not much better than coordinate regression on low-resolution images. In this paper, we propose a novel neural representation for human pose estimation called NerPE to achieve continuous heatmap regression. Given any position within the image range, NerPE regresses the corresponding confidence scores for body joints according to the surrounding image features, which guarantees continuity in space and confidence during training. Thanks to the decoupling from spatial resolution, NerPE can output the predicted heatmaps at arbitrary resolution during inference without retraining, which easily achieves sub-pixel localization precision. To reduce the computational cost, we design progressive coordinate decoding to cooperate with continuous heatmap regression, in which localization no longer requires the complete generation of high-resolution heatmaps. The code is available at https://github.com/hushengxiang/NerPE.

Linear regression, a widely-used method in representation learning, initially faced limitations in incorporating structural information within the regression space. Existing models designed to extract structural insights often prioritize the proximity of data points in feature space, while overlooking crucial interdependencies and co-occurrences among them. In response to the challenges posed by the inherent limitations, we introduce a novel representation learning model based on linear regression. This model seamlessly integrates three essential modules: flexible regression learning, graph embedding learning, and embedded block-diagonal self-representation learning. The collaborative functioning of these modules establishes a closed optimization loop. The self-representation matrix directly captures the latent graph structure across the entire data domain, without the need for setting additional parameters such as the neighborhood scale of the graph. Concurrently, it facilitates flexible regression learning by uncovering latent structural patterns. Experimental results on multiple benchmark datasets demonstrate the superiority of our approach over state-of-the-art methods, providing a more comprehensive solution for representation learning.

Previous works on human motion prediction follow the pattern of building an extrapolation mapping between the sequence observed and the one to be predicted. However, the inherent difficulty of time-series extrapolation and complexity of human motion data still result in many failure cases. In this paper, we explore a longer horizon of sequence with more poses following behind, which breaks the limit in extrapolation problems that data/information on the other side of the predictive target is completely unknown. As these poses are unavailable for testing, we regard them as a privileged sequence, and propose a Two-stage Privileged Knowledge Distillation framework that incorporates privileged information in the forecasting process while avoiding direct use of it. Specifically, in the first stage, both the observed and privileged sequence are encoded for interpolation, with Privileged-sequence-Encoder (Priv-Encoder) learning privileged knowledge (PK) simultaneously. Then, in the second stage where privileged sequence is not observable, a novel PK-Simulator distills PK by approximating the behavior of Priv-Encoder, but only taking as input the observed sequence, to enable a PK-aware prediction pattern. Moreover, we present a One-stage version of this framework, using Shared Encoder that integrates the observation encoding in both interpolation and prediction branches to realize parallel training, which helps produce the most conducive PK to prediction pipeline. Experimental results show that our frameworks are model-agnostic, and can be applied to existing motion prediction models with encoder-decoder architecture to achieve improved performance.

In recent years, multi-kernel learning (MKL) methods have been widely used in performing nonlinear data subspace clustering tasks, benefiting from the fact that they do not require the selection and tuning of predefined kernels. However, the effect of raw noise on the data structure in the feature space has been neglected in most MKL studies so far. In this paper, we propose a robust subspace clustering method called purity kernel tensor low-rank learning (KTLL), which effectively isolates noise transfer from the original data space to the high-dimensional feature space. Specifically, we construct the kernel pool obtained by MKL as a primitive third-order kernel tensor, separate the corrupted information in the feature space, and use the separated pure kernel tensor to learn the optimal affinity matrix. The tensor learning of the kernel pool can effectively mine the higher-order correlations among different kernel matrices, thus improving the clustering performance of KTLL.We have conducted extensive experiments to compare KTLL with state-of-the-art MKL and deep subspace clustering algorithms, and our results demonstrate the superiority of KTLL.

Predicting high-fidelity future human poses, from a historically observed sequence, is crucial for intelligent robots to interact with humans. Deep end-to-end learning approaches, which typically train a generic pre-trained model on external datasets and then directly apply it to all test samples, emerge as the dominant solution to solve this issue. Despite encouraging progress, they remain non-optimal, as the unique properties (e.g., motion style, rhythm) of a specific sequence cannot be adapted. More generally, once encountering out-of-distributions, the predicted poses tend to be unreliable. Motivated by this observation, we propose a novel test-time adaptation framework that leverages two self-supervised auxiliary tasks to help the primary forecasting network adapt to the test sequence. In the testing phase, our model can adjust the model parameters by several gradient updates to improve the generation quality. However, due to catastrophic forgetting, both auxiliary tasks typically have a low ability to automatically present the desired positive incentives for the final prediction performance. For this reason, we also propose a meta-auxiliary learning scheme for better adaptation. Extensive experiments show that the proposed approach achieves higher accuracy and more realistic visualization.

Stochastic human motion prediction aims to forecast multiple plausible future motions given a single pose sequence from the past. Most previous works focus on designing elaborate losses to improve the accuracy, while the diversity is typically characterized by randomly sampling a set of latent variables from the latent prior, which is then decoded into possible motions. This joint training of sampling and decoding, however, suffers from posterior collapse as the learned latent variables tend to be ignored by a strong decoder, leading to limited diversity. Alternatively, inspired by the diffusion process in nonequilibrium thermodynamics, we propose MotionDiff, a diffusion probabilistic model to treat the kinematics of human joints as heated particles, which will diffuse from original states to a noise distribution. This process not only offers a natural way to obtain the "whitened'' latents without any trainable parameters, but also introduces a new noise in each diffusion step, both of which facilitate more diverse motions. Human motion prediction is then regarded as the reverse diffusion process that converts the noise distribution into realistic future motions conditioned on the observed sequence. Specifically, MotionDiff consists of two parts: a spatial-temporal transformer-based diffusion network to generate diverse yet plausible motions, and a flexible refinement network to further enable geometric losses and align with the ground truth. Experimental results on two datasets demonstrate that our model yields the competitive performance in terms of both diversity and accuracy.

Let us rethink the real-world scenarios that require human motion prediction techniques, such as human-robot collaboration. Current works simplify the task of predicting human motions into a one-off process of forecasting a short future sequence (usually no longer than 1 second) based on a historical observed one. However, such simplification may fail to meet practical needs due to the neglect of the fact that motion prediction in real applications is not an isolated “observe then predict” unit, but a consecutive process composed of many rounds of such unit, semi-overlapped along the entire sequence. As time goes on, the predicted part of previous round has its corresponding ground truth observable in the new round, but their deviation in-between is neither exploited nor able to be captured by existing isolated learning fashion. In this paper, we propose DeFeeNet, a simple yet effective network that can be added on existing one-off prediction models to realize deviation perception and feedback when applied to consecutive motion prediction task. At each prediction round, the deviation generated by previous unit is first encoded by our DeFeeNet, and then incorporated into the existing predictor to enable a deviation-aware prediction manner, which, for the first time, allows for information transmit across adjacent prediction units. We design two versions of DeFeeNet as MLP-based and GRU-based, respectively. On Human3.6M and more complicated BABEL, experimental results indicate that our proposed network improves consecutive human motion prediction performance regardless of the basic model.

Current motion forecasting approaches typically train a deep end-to-end model from the source domain data, and then apply it directly to target subjects. Despite promising results, they remain non-optimal, due to privacy considerations, the test person and his/her natural properties (e.g., behavioral trait) are typically unseen in training. In this case, the source pre-trained model has a low ability to adapt to these out-of-source characteristics, resulting in an unreliable prediction. To tackle this issue, we propose a novel helper-predictor test-time personalization approach (H/P-TTP), which allows for a generalizable representation of out-of-source subjects to gain more realistic predictions. Concretely, the helper is preceded by explicit and implicit augmenters, where the former yields noisy sequences to improve robustness, while the latter is to generate novel-domain data with an adversarial learning paradigm. Then, the domain-generalizable learning is achieved where the helper can extract cross-subject invariant-knowledge to update the predictor. At test time, given a new person, the predictor is able to be further optimized to empower personalized capabilities to the specific properties. Extensive experiments show that with H/P-TTP, the existing models are significantly improved for various unseen subjects. The project page is available at https://sites.google.com/view/hp-ttp.

Deep subspace learning is an important branch of self-supervised learning and has been a hot research topic in recent years, but current methods do not fully consider the individualities of temporal data and related tasks. In this paper, by transforming the individualities of motion capture data and segmentation task as the supervision, we propose the local self-expression subspace learning network. Specifically, considering the temporality of motion data, we use the temporal convolution module to extract temporal features. To implement the local validity of self-expression in temporal tasks, we design the local self-expression layer which only maintains the representation relations with temporally adjacent motion frames. To simulate the interpolatability of motion data in the feature space, we impose a group sparseness constraint on the local self-expression layer to impel the representations only using selected keyframes. Besides, based on the subspace assumption, we propose the subspace projection loss, which is induced from distances of each frame projected to the fitted subspaces, to penalize the potential clustering errors. The superior performances of the proposed model on the segmentation task of synthetic data and three tasks of real motion capture data demonstrate the feature learning ability of our model.

Projecting the original data into a low-dimensional target space for feature extraction is a common method. Recently, presentation-based approaches have been widely concerned and many feature extraction algorithms based on this have been proposed. However, in the process of acquiring real data, the pollution of complex noise cannot always be avoided, which will greatly increase the difficulty of feature extraction and even lead to failed feature extraction results. Thus, a robust image feature extraction model based on Orthogonal Low-Rank Projection Learning (OLRPL) is proposed, in which the introduction of orthogonal matrix can encourage the preservation of the main components of the sample. Particularly, the row sparsity constraint introduced on the projection matrix can encourage the features to be more compact, discriminative and interpretable. In particular, the Weighted Truncated Schattenp-norm (WTSN) is proposed to better solve the optimization problem of low-rank constraints. At the same time, the correntropy is applied in OLRPL to suppress the complex noise in the data and thus improve the robustness of the model. Finally, we specially design a robust classification loss function so that our model can be fitted the supervised scene effectively. Experiments on five general databases have proved that OLRPL has better effectiveness and robustness than existing advanced methods.

Predicting accurate and realistic future human poses from historically observed sequences is a fundamental task in the intersection of computer vision, graphics, and artificial intelligence. Recently, continuous efforts have been devoted to addressing this issue, which has achieved remarkable progress. However, the existing work is seriously limited by complete observation, that is, once the historical motion sequence is incomplete (with missing values), it can only produce unexpected predictions or even deformities. Furthermore, due to inevitable reasons such as occlusion and the lack of equipment precision, the incompleteness of motion data occurs frequently, which hinders the practical application of current algorithms.In this work, we first notice this challenging problem, i.e., how to generate high-fidelity human motion predictions from incomplete observations. To solve it, we propose a novel multi-task graph convolutional network (MTGCN). Specifically, the model involves two branches, in which the primary task is to focus on forecasting future 3D human actions accurately, while the auxiliary one is to repair the missing value of the incomplete observation. Both of them are integrated into a unified framework to share the spatio-temporal representation, which improves the final performance of each collaboratively. On three large-scale datasets, for various data missing scenarios in the real world, extensive experiments demonstrate that our approach is consistently superior to the state-of-the-art methods in which the missing values from incomplete observations are not explicitly analyzed.

Motion capture (MoCap) technology aims to provide an accurate record of human motion, with specific potentials in activity analysis, human behavior understanding, as well as multimedia industries of animation production and special effects movies. However, because of joint occlusion and limitation of equipment precision, the raw motion data are often damaged, which severely hinders its downstream applications. The latest method relies on deep neural networks to reconstruct the underlying complete motion from the degraded observation, achieving remarkable results. Unfortunately, due to the non-enumerability of human motion, the trained model from large-scale training data often fails to comprehensively cover incomputable action categories, which may lead to a sharp decline in the performance of deep learning-based methods. To handle these limitations, we propose an untrained deep generative model, in which Graph Convolutional Networks (GCNs) are utilized to efficiently capture complicated topological relationships of human joints. We show that the untrained GCN architecture with randomly-initialized weights is sufficient to extract some low-level statistics for human motion reconstruction without any training process. Notably, the performance of our approach is comparable to that of those trained models, while its application is not restricted by the availability of training data or a pre-trained network. Moreover, the proposed model even surpasses the state-of-the-art methods when encountering unprecedented samples in the human action database, regardless of the tasks of human motion recovery and gap-filling problem.

By exploiting the kernel trick, the sparse subspace model is extended to the nonlinear version with one or a combination of predefined kernels, but the high-dimensional space induced by predefined kernels is not guaranteed to be able to capture the features of the nonlinear data in theory. In this article, we propose a nonconvex low-rank learning framework in an unsupervised way to learn a kernel to replace the predefined kernel in the sparse subspace model. The learned kernel by a nonconvex relaxation of rank can better exploiting the low-rank property of nonlinear data to induce a high-dimensional Hilbert space that more closely approaches the true feature space. Furthermore, we give a global closed-form optimal solution of the nonconvex rank minimization and prove it. Considering the low-rank and sparseness characteristics of motion capture data in its feature space, we use them to verify the better representation of nonlinear data with the learned kernel via two tasks: keyframe extraction and motion segmentation. The performances on both tasks demonstrate the advantage of our model over the sparse subspace model with predefined kernels and some other related state-of-art methods.

3D human motion prediction, i.e., forecasting future sequences from given historical poses, is a fundamental task for action analysis, human-computer interaction, machine intelligence. Recently, the state-of-the-art method assumes that the whole human motion sequence involves a fully-connected graph formed by links between each joint pair. Although encouraging performance has been made, due to the neglect of the inherent and meaningful characteristics of the natural connectivity of human joints, unexpected results may be produced. Moreover, such a complicated topology greatly increases the training difficulty. To tackle these issues, we propose a deep generative model based on graph networks and adversarial learning. Specifically, the skeleton pose is represented as a novel dynamic graph, in which natural connectivities of the joint pairs are exploited explicitly, and the links of geometrically separated joints can also be learned implicitly. Notably, in the proposed model, the natural connection strength is adaptively learned, whereas, in previous schemes, it was constant. Our approach is evaluated on two representations (i.e., angle-based, position-based) from various large-scale 3D skeleton benchmarks (e.g., H3.6M, CMU, 3DPW MoCap). Extensive experiments demonstrate that our approach achieves significant improvements against existing baselines in accuracy and visualization. Code will be available at https://github.com/cuiqiongjie/LDRGCN.

Recently, sparse representation-based classification (SRC) has been widely studied and has produced state-of-the-art results in various classification tasks. Learning useful and computationally convenient representations from complex redundant and highly variable visual data is crucial for the success of SRC. However, how to find the best feature representation to work with SRC remains an open question. In this paper, we present a novel discriminative projection learning approach with the objective of seeking a projection matrix such that the learned low-dimensional representation can fit SRC well and that it has well discriminant ability. More specifically, we formulate the learning algorithm as a bilevel optimization problem, where the optimization includes an ℓ1-norm minimization problem in its constraints. Through the bilevel optimization model, the relationship between sparse representation and the desired feature projection can be explicitly exploited during the learning process. Therefore, SRC can achieve a better performance in the transformed subspace. The optimization model can be solved by using a stochastic gradient ascent algorithm, and the desired gradient is computed using implicit differentiation. Furthermore, our method can be easily extended to learn a dictionary. The extensive experimental results on a series of benchmark databases show that our method outperforms many state-of-the-art algorithms.

Subspace clustering plays an important role in the tasks such as data processing and pattern recognition. Since the high-dimensional data may contain complex noise, as well as non-linear structure, learning low-dimensional subspace structures is a challenging task. However, the existing methods to deal with both problems relax the original problem convexly. The results of solving by these methods deviate from the solution of the original problem. In this paper, to overcome this deficiency, we propose a robust low-rank kernel subspace clustering model, which coalesces the non-convex Schatten p-norm (0 <; p ≤ 1) regularizer with “kernel trick” and correntropy. Our “kernel trick” extends linear subspace clustering to non-linear counterparts, the Schatten p-norm regularizer can approximate the rank of the data in feature space effectively, and the correntropy is a robust measure to large corruptions. Furthermore, an efficient iterative algorithm (HQ-ADMM) is designed to solve the formulated problem, which coalesces the half-quadratic technique and Alternating Direction Method of Multipliers. This algorithm can ensure the closed form solutions at each iteration, which improves the computation speed of the algorithm. Extensive experiments on face/object clustering and motion segmentation clearly attest the ascendancy of the proposed method over several state-of-the-art methods.

Human motion capture (mocap) data, recording the movement of markers attached to specific joints, has gradually become the most popular solution of animation production. However, the raw motion data are often corrupted due to joint occlusion, marker shedding and the lack of equipment precision, which severely limits the performance in real-world applications. Since human motion is essentially a sequential data, the latest methods resort to variants of long short-time memory network (LSTM) to solve related problems, but most of them tend to obtain visually unreasonable results. This is mainly because these methods hardly capture long-term dependencies and cannot explicitly utilize relevant context, especially in long sequences. To address these issues, we propose a deep bi-directional attention network (BAN) which can not only capture the long-term dependencies but also adaptively extract relevant information at each time step. Moreover, the proposed model, embedded attention mechanism in the bi-directional LSTM (BLSTM) structure at the encoding and decoding stages, can decide where to borrow information and use it to recover corrupted frame effectively. Extensive experiments on CMU database demonstrate that the proposed model consistently outperforms other state-of-the-art methods in terms of recovery accuracy and visualization.

This work presents a novel robust image compressive sensing reconstruction approach. In contrast to the existing work, we employ the truncated Cauchy loss function to measure the errors induced during the measurement, showing strong robustness to impulsive noise and outliers. To ensure high quality reconstructed images, we utilize a non-local low rank regularizer - with truncated Schatten-p norm being the surrogate function of rank - to capture the self-similar property inherent in most natural images. Considering the fact that the whole optimization model is neither convex nor smooth, to solve it effectively, we firstly use the half-quadratic strategy to transform the loss function into a quadratic objective by introducing some auxiliary variables, and then iteratively and alternatively optimize different groups of variables. Extensive experimental results demonstrate its effectiveness in terms of both quantitative indexes of Peak Signal-to-Noise Ratio (PSNR) and Structural SIMilarity (SSIM), and visual quality under impulsive noise.

Motion synthesis technology can produce natural and coordinated motion data without a motion capture process, which is complex and costly. Current motion synthesis methods usually provide a few interfaces to avoid the arbitrariness of the synthesis process, but this actually reduces the understandability of the synthesis process. In this paper, we propose a learning-based Sphere nonlinear interpolation (Snerp) model that can generate natural in-between motions in terms of a given start-end frame pair. Variety of the input frame pairs will enrich the diversity of the generated motions. The angle speed of natural human motion is not uniform and presents different change rules (we call them motion patterns) for different motions, so we first extract the motion patterns and then build the relation between motion pattern space and frame pair space via a paired dictionary learning process. After learning, we estimate the motion pattern according to the representation of a given start-end frame pair on the frame pair dictionary. We select several different types of start-end frame pairs from the real motion sequences as the testing data and good results of both objective and subjective evaluations on the generated motions demonstrate the superior performance of Snerp.

Human motion capture data has been widely used in many areas, but it involves a complex capture process and the captured data inevitably contains missing data due to the occlusions caused by the actor's body or clothing. Motion recovery, which aims to recover the underlying complete motion sequence from its degraded observation, still remains as a challenging task due to the nonlinear structure and kinematics property embedded in motion data. Low-rank matrix completion based methods have shown promising performance in short-time-missing motion recovery problems. However, low-rank matrix completion, which is designed for linear data, lacks the theoretic guarantee when applied to the recovery of nonlinear motion data. To overcome this drawback, we propose a tailored nonlinear matrix completion model for human motion recovery. Within the model, we first learn a combined low-rank kernel via multiple kernel learning. By exploiting the learned kernel, we embed the motion data into a high dimensional Hilbert space where motion data is of desirable low-rank and we then use the low-rank matrix completion to recover motions. In addition, we add two kinematic constraints to the proposed model to preserve the kinematics property of human motion. Extensive experiment results and comparisons with five other state-of-the-art methods demonstrate the advantage of the proposed method.

Studies on human motion have attracted a lot of attentions. Human motion capture data, which much more precisely records human motion than videos do, has been widely used in many areas. Motion segmentation is an indispensable step for many related applications, but current segmentation methods for motion capture data do not effectively model some important characteristics of motion capture data, such as Riemannian manifold structure and containing non-Gaussian noise. In this paper, we convert the segmentation of motion capture data into a temporal subspace clustering problem. Under the framework of sparse subspace clustering, we propose to use the geodesic exponential kernel to model the Riemannian manifold structure, use correntropy to measure the reconstruction error, use the triangle constraint to guarantee temporal continuity in each cluster and use multi-view reconstruction to extract the relations between different joints. Therefore, exploiting some special characteristics of motion capture data, we propose a new segmentation method, which is robust to non-Gaussian noise, since correntropy is a localized similarity measure. We also develop an efficient optimization algorithm based on block coordinate descent method to solve the proposed model. Our optimization algorithm has a linear complexity while sparse subspace clustering is originally a quadratic problem. Extensive experiment results both on simulated noisy data set and real noisy data set demonstrate the advantage of the proposed method.Studies on human motion have attracted a lot of attentions. Human motion capture data, which much more precisely records human motion than videos do, has been widely used in many areas. Motion segmentation is an indispensable step for many related applications, but current segmentation methods for motion capture data do not effectively model some important characteristics of motion capture data, such as Riemannian manifold structure and containing non-Gaussian noise. In this paper, we convert the segmentation of motion capture data into a temporal subspace clustering problem. Under the framework of sparse subspace clustering, we propose to use the geodesic exponential kernel to model the Riemannian manifold structure, use correntropy to measure the reconstruction error, use the triangle constraint to guarantee temporal continuity in each cluster and use multi-view reconstruction to extract the relations between different joints. Therefore, exploiting some special characteristics of motion capture data, we propose a new segmentation method, which is robust to non-Gaussian noise, since correntropy is a localized similarity measure. We also develop an efficient optimization algorithm based on block coordinate descent method to solve the proposed model. Our optimization algorithm has a linear complexity while sparse subspace clustering is originally a quadratic problem. Extensive experiment results both on simulated noisy data set and real noisy data set demonstrate the advantage of the proposed method.

In recent years, sparse representation-based classification (SRC) is one of the most successful methods and has been shown impressive performance in various classification tasks. However, when the training data have a different distribution than the testing data, the learned sparse representation may not be optimal, and the performance of SRC will be degraded significantly. To address this problem, in this paper, we propose an optimal couple projections for domain-adaptive SRC (OCPD-SRC) method, in which the discriminative features of data in the two domains are simultaneously learned with the dictionary that can succinctly represent the training and testing data in the projected space. OCPD-SRC is designed based on the decision rule of SRC, with the objective to learn coupled projection matrices and a common discriminative dictionary such that the between-class sparse reconstruction residuals of data from both domains are maximized, and the within-class sparse reconstruction residuals of data are minimized in the projected low-dimensional space. Thus, the resulting representations can well fit SRC and simultaneously have a better discriminant ability. In addition, our method can be easily extended to multiple domains and can be kernelized to deal with the nonlinear structure of data. The optimal solution for the proposed method can be efficiently obtained following the alternative optimization method. Extensive experimental results on a series of benchmark databases show that our method is better or comparable to many state-of-the-art methods.

Sparse representation-based classification (SRC) has been developed and shown great potential for real-world application. Based on SRC, Yang et al. devised an SRC steered discriminative projection (SRC-DP) method. However, as a linear algorithm, SRC-DP cannot handle the data with highly nonlinear distribution. Kernel sparse representation-based classifier (KSRC) is a non-linear extension of SRC and can remedy the drawback of SRC. KSRC requires the use of a predetermined kernel function and selection of the kernel function and its parameters is difficult. Recently, multiple kernel learning for SRC (MKL-SRC) has been proposed to learn a kernel from a set of base kernels. However, MKL-SRC only considers the within-class reconstruction residual while ignoring the between-class relationship, when learning the kernel weights. In this paper, we propose a novel multiple kernel sparse representation-based classifier, and then we use it as a criterion to design a multiple kernel sparse representation-based orthogonal discriminative projection method. The proposed algorithm aims at learning a projection matrix and a corresponding kernel from the given base kernels such that in the low dimension subspace the between-class reconstruction residual is maximized and the within-class reconstruction residual is minimized. Furthermore, to achieve a minimum overall loss by performing recognition in the learned low-dimensional subspace, we introduce cost information into the dimensionality reduction method. The solutions for the proposed method can be efficiently found based on trace ratio optimization method. Extensive experimental results demonstrate the superiority of the proposed algorithm when compared with the state-of-the-art methods.

ABSTRACT Content‐based human motion retrieval is important for animators with the development of motion editing and synthesis, which need to search similar motions in large databases. Obtaining text‐based representation from quantization of mocap data turned out to be efficient. It becomes a fundamental step of many researches in human motion analysis. Geometric features are one of these techniques, which involve much prior knowledge and reduce data redundancy of numerical data. We describe geometric features as basic unit to define human motions (also called mo‐words) and view a human motion as a generative process. Therefore, we obtain topic motions, which possess more semantic information using latent Dirichlet allocation by learning from massive training examples in order to understand motions better. We combine probabilistic model with human motion retrieval and come up with a new representation of human motions and a new retrieval framework. Our experiments demonstrate its advantages, both for understanding motions and retrieval. Copyright © 2011 John Wiley & Sons, Ltd.