Predicting trajectories is essential for interpreting human behavior, yet it remains a challenging task when relying solely on observed motion patterns. Despite substantial progress, most existing methods assume fully observed trajectories and fail to account for missing data caused by occlusion, limited field of view, or sensor failures. This limitation substantially compromises the reliability of trajectory prediction, particularly in real-world deployment where observations are often incomplete. In light of this issue, our work presents the Gaussian Mixture Conditional Variational Recurrent Neural Network (GMC-VRNN), which unifies trajectory imputation and prediction within a single framework. Our GMC-VRNN framework couples a Multi-Space Graph Neural Network (MS-GNN) with a Gaussian Mixture Conditional VRNN, further augmented by a Bidirectional Temporal Decay (BTD) module, to achieve robust spatio-temporal representation learning under incomplete observations. To verify its effectiveness, we conduct extensive evaluations on two sports datasets covering multiple scenarios, jointly tackling trajectory imputation and prediction. Our experiments confirm that GMC-VRNN surpasses recent state-of-the-art approaches, offering enhanced precision and stronger robustness under diverse conditions.

Trajectory prediction is a fundamental problem in computer vision, vision-language-action models, world models, and autonomous systems, with broad impact on applications including autonomous driving, robotics, and surveillance. Most existing approaches assume observations are complete and relatively clean, and thus do not adequately address out-ofsight agents or the intrinsic noise in sensing modalities (e.g., sensor measurements) caused by restricted camera coverage, occlusions, and the lack of ground-truth denoised trajectories. These factors introduce substantial safety concerns and reduce the robustness of trajectory prediction in practical deployments. In this extended study, we introduce major improvements to Out-of-Sight Trajectory (OST), a new task aimed at predicting noise-free visual trajectories of out-of-sight objects from noisy sensor observations. Based on our prior work, we expand the setting of Out-of-Sight Trajectory Prediction (OOSTraj) from pedestrians to both pedestrians and vehicles, thereby increasing its relevance to autonomous driving, robotics, and surveillance scenarios. Our improved Vision-Positioning Denoising Module utilizes camera calibration to construct a vision-position correspondence, mitigating the absence of direct visual cues while enabling effective unsupervised denoising of noisy sensor signals. Extensive experiments on the Vi-Fi and JRDB datasets demonstrate that our method achieves state-of-the-art results for both trajectory denoising and trajectory prediction, with clear gains over prior baselines. We further provide comparisons against classical denoising techniques, including Kalman filtering, and adapt recent trajectory prediction models to this setting, establishing a stronger and more comprehensive benchmark. To the best of our knowledge, this is the first work to incorporate vision-positioning projection to denoise noisy sensor trajectories of out-of-sight agents, opening new directions for future research in this area. The code and preprocessed datasets are available at https://github.com/Hai-chao-Zhang/OST.

Foundation models learn highly transferable representations through large-scale pretraining on diverse data.An increasing body of research indicates that these representations exhibit a remarkable degree of similarity across architectures and modalities.In this survey, we investigate the representation potentials of foundation models, defined as the latent capacity of their learned representations to capture task-specific information within a single modality while also providing a transferable basis for alignment and unification across modalities.We begin by reviewing representative foundation models and the key metrics that make alignment measurable.We then synthesize empirical evidence of representation potentials from studies in vision, language, speech, multimodality, and neuroscience.The evidence suggests that foundation models often exhibit structural regularities and semantic consistencies in their representation spaces, positioning them as strong candidates for cross-modal transfer and alignment.We further analyze the key factors that foster representation potentials, discuss open questions, and highlight potential challenges.

Trajectory prediction in multi-agent sports scenarios is inherently challenging due to the structural heterogeneity across agent roles (e.g., players vs. ball) and dynamic distribution gaps across different sports domains. Existing unified frameworks often fail to capture these structured distributional shifts, resulting in suboptimal generalization across roles and domains. We propose AdaSports-Traj, an adaptive trajectory modeling framework that explicitly addresses both intra-domain and inter-domain distribution discrepancies in sports. At its core, AdaSports-Traj incorporates a Role- and Domain-Aware Adapter to conditionally adjust latent representations based on agent identity and domain context. Additionally, we introduce a Hierarchical Contrastive Learning objective, which separately supervises role-sensitive and domain-aware representations to encourage disentangled latent structures without introducing optimization conflict. Experiments on three diverse sports datasets, BasketballU, Football-U, and Soccer-U, demonstrate the effectiveness of our adaptive design, achieving strong performance in both unified and cross-domain trajectory prediction settings.

Unsupervised multivariate time series (MTS) representation learning aims to extract compact and informative representations from raw sequences without relying on labels, enabling efficient transfer to diverse downstream tasks. In this paper, we propose Dual-Masked Autoencoder (DMAE), a novel masked time-series modeling framework for unsupervised MTS representation learning. DMAE formulates two complementary pretext tasks: (1) reconstructing masked values based on visible attributes, and (2) estimating latent representations of masked features, guided by a teacher encoder. To further improve representation quality, we introduce a feature-level alignment constraint that encourages the predicted latent representations to align with the teacher's outputs. By jointly optimizing these objectives, DMAE learns temporally coherent and semantically rich representations. Comprehensive evaluations across classification, regression, and forecasting tasks demonstrate that our approach achieves consistent and superior performance over competitive baselines.

Understanding multi-agent movement is critical across various fields. The conventional approaches typically focus on separate tasks such as trajectory prediction, imputation, or spatial-temporal recovery. Considering the unique formulation and constraint of each task, most existing methods are tailored for only one, limiting the ability to handle multiple tasks simultaneously, which is a common requirement in real-world scenarios. Another limitation is that widely used public datasets mainly focus on pedestrian movements with casual, loosely connected patterns, where interactions between individuals are not always present, especially at a long distance, making them less representative of more structured environments. To overcome these limitations, we propose a Unified Trajectory Generation model, UniTraj, that processes arbitrary trajectories as masked inputs, adaptable to diverse scenarios in the domain of sports games. Specifically, we introduce a Ghost Spatial Masking (GSM) module, embedded within a Transformer encoder, for spatial feature extraction. We further extend recent State Space Models (SSMs), known as the Mamba model, into a Bidirectional Temporal Mamba (BTM) to better capture temporal dependencies. Additionally, we incorporate a Bidirectional Temporal Scaled (BTS) module to thoroughly scan trajectories while preserving temporal missing relationships. Furthermore, we curate and benchmark three practical sports datasets, Basketball-U, Football-U, and Soccer-U, for evaluation. Extensive experiments demonstrate the superior performance of our model. We hope that our work can advance the understanding of human movement in real-world applications, particularly in sports. Our datasets, code, and model weights are available here https://github.com/colorfulfuture/UniTraj-pytorch.

Trajectory prediction is fundamental in computer Vision and autonomous driving, particularly for understanding pedestrian behavior and enabling proactive decision-making. Existing approaches in this field often assume precise and complete observational data, neglecting the challenges associated with out-of-view objects and the noise in-herent in sensor data due to limited camera range, physical obstructions, and the absence of ground truth for denoised sensor data. Such oversights are critical safety concerns, as they can result in missing essential, non-visible objects. To bridge this gap, we present a novel method for out-of-sight trajectory prediction that leverages a vision-positioning technique. Our approach denoises noisy sensor observations in an unsupervised manner and precisely maps sensor-based trajectories of out-of-sight objects into visual trajectories. This method has demonstrated state-of-the-art performance in out-of-sight noisy sensor trajectory denoising and prediction on the Vi-Fi and JRDB datasets. By enhancing trajectory prediction accuracy and addressing the challenges of out-of-sight objects, our work significantly contributes to improving the safety and reliability of autonomous driving in complex environments. Our work represents the first initiative towards Out-Of-Sight Trajectory prediction (OOSTraj), setting a new benchmark for future research.

Trajectory prediction plays an important role in various applications, including autonomous driving, robotics, and scene understanding. Existing approaches mainly focus on developing compact neural networks to increase prediction precision on public datasets, typically employing a stan-dardized input duration. However, a notable issue arises when these models are evaluated with varying observation lengths, leading to a significant performance drop, a phe-nomenon we term the Observation Length Shift. To address this issue, we introduce a general and effective framework, the FlexiLength Network (FLN), to enhance the robustness of existing trajectory prediction techniques against varying observation periods. Specifically, FLN integrates tra-jectory data with diverse observation lengths, incorporates FlexiLength Calibration (FLC) to acquire temporal invari-ant representations, and employs FlexiLength Adaptation (FLA) to further refine these representations for more ac-curate future trajectory predictions. Comprehensive exper-iments on multiple datasets, i.e., ETH/UCY, nuScenes, and Argoverse 1, demonstrate the effectiveness and flexibility of our proposed FLN framework.

Anomaly detection is a foundational yet difficult problem in machine learning. In this work, we propose a new and effective framework, dubbed as SLA2P, for unsupervised anomaly detection. Following the extraction of delegate embeddings from raw data, we implement random projections on the features and consider features transformed by disparate projections as being associated with separate pseudo-classes. We then train a neural network for classification on these transformed features to conduct self-supervised learning. Subsequently, we introduce adversarial disturbances to the modified attributes, and we develop anomaly scores built on the classifier's predictive uncertainties concerning these disrupted features. Our approach is motivated by the fact that as anomalies are relatively rare and decentralized, 1) the training of the pseudo-label classifier concentrates more on acquiring the semantic knowledge of regular data instead of anomalous data; 2) the altered attributes of the normal data exhibit greater resilience to disturbances compared to those of the anomalous data. Therefore, the disrupted modified attributes of anomalies can not be well classified and correspondingly tend to attain lesser anomaly scores. The results of experiments on various benchmark datasets for images, text, and inherently tabular data demonstrate that SLA2P achieves state-of-the-art performance consistently.

Predicting future action locations is vital for applications like human-robot collaboration. While some computer vision tasks have made progress in predicting human actions, accurately localizing these actions in future frames remains an area with room for improvement. We introduce a new task called spatial action localization in the future (SALF), which aims to predict action locations in both observed and future frames. SALF is challenging because it requires understanding the underlying physics of video observations to predict future action locations accurately. To address SALF, we use the concept of NeuralODE, which models the latent dynamics of sequential data by solving ordinary differential equations (ODE) with neural networks. We propose a novel architecture, AdamsFormer, which extends observed frame features to future time horizons by modeling continuous temporal dynamics through ODE solving. Specifically, we employ the Adams method, a multi-step approach that efficiently uses information from previous steps without discarding it. Our extensive experiments on UCF101-24 and JHMDB-21 datasets demonstrate that our proposed model outperforms existing long-range temporal modeling methods by a significant margin in terms of frame-mAP.

Trajectory prediction is a crucial undertaking in understanding entity movement or human behavior from observed sequences. However, current methods often assume that the observed sequences are complete while ignoring the potential for missing values caused by object occlusion, scope limitation, sensor failure, etc. This limitation inevitably hinders the accuracy of trajectory prediction. To address this issue, our paper presents a unified framework, the Graph-based Conditional Variational Recurrent Neural Network (GC-VRNN), which can perform trajectory imputation and prediction simultaneously. Specifically, we introduce a novel Multi-Space Graph Neural Network (MS-GNN) that can extract spatial features from incomplete observations and leverage missing patterns. Additionally, we employ a Conditional VRNN with a specifically designed Temporal Decay (TD) module to capture temporal dependencies and temporal missing patterns in incomplete trajectories. The inclusion of the TD module allows for valuable information to be conveyed through the temporal flow. We also curate and benchmark three practical datasets for the joint problem of trajectory imputation and prediction. Extensive experiments verify the exceptional performance of our proposed method. As far as we know, this is the first work to address the lack of benchmarks and techniques for trajectory imputation and prediction in a unified manner.

Adaptive gradient methods, e.g., ADAM, have achieved tremendous success in data-driven machine learning, especially deep learning. Employing adaptive learning rates according to the gradients, such methods are able to attain rapid training of modern deep neural networks. Nevertheless, they are observed to suffer from compromised generalization capacity compared with stochastic gradient descent (SGD) and tend to be trapped in local minima at an early stage during the training process. Intriguingly, we discover that the issue can be resolved by substituting the gradient in the second raw moment estimate term with its exponential moving average version in ADAM. The intuition is that the gradient with momentum contains more accurate directional information, and therefore its second-moment estimation is a more preferable option for learning rate scaling than that of the raw gradient. Thereby we propose ADAM$^{3}$ as a new optimizer reaching the goal of training quickly while generalizing much better. Extensive experiments on a variety of tasks and models demonstrate that ADAM$^{3}$ exhibits state-of-the-art performance and superior training stability consistently. Considering the simplicity and effectiveness of ADAM$^{3}$, we believe it has the potential to become a new standard method in deep learning. Code is provided at https://github.com/wyzjack/AdaM3.

Trajectory prediction plays a vital role in understanding pedestrian movement for applications such as autonomous driving and robotics. Current trajectory prediction models depend on long, complete, and accurately observed sequences from visual modalities. Nevertheless, real-world situations often involve obstructed cameras, missed objects, or objects out of sight due to environmental factors, leading to incomplete or noisy trajectories. To overcome these limitations, we propose LTrajDiff, a novel approach that treats objects obstructed or out of sight as equally important as those with fully visible trajectories. LTrajDiff utilizes sensor data from mobile phones to surmount out-of-sight constraints, albeit introducing new challenges such as modality fusion, noisy data, and the absence of spatial layout and object size information. We employ a denoising diffusion model to predict precise layout sequences from noisy mobile data using a coarse-to-fine diffusion strategy, incorporating the Random Mask Strategy, Siamese Masked Encoding Module, and Modality Fusion Module. Our model predicts layout sequences by implicitly inferring object size and projection status from a single reference timestamp or significantly obstructed sequences. Achieving state-of-the-art results in randomly obstructed experiments, our model outperforms other baselines in extremely short input experiments, illustrating the effectiveness of leveraging noisy mobile data for layout sequence prediction. In summary, our approach offers a promising solution to the challenges faced by layout sequence and trajectory prediction models in real-world settings, paving the way for utilizing sensor data from mobile phones to accurately predict pedestrian bounding box trajectories. To the best of our knowledge, this is the first work that addresses severely obstructed and extremely short layout sequences by combining vision with noisy mobile modality, making it the pioneering work in the field of layout sequence trajectory prediction.

Latent graph inference (LGI) aims to jointly learn the underlying graph structure and node representations from data features. However, existing LGI methods commonly suffer from the issue of supervision starvation, where massive edge weights are learned without semantic supervision and do not contribute to the training loss. Consequently, these supervision-starved weights, which determine the predictions of testing samples, cannot be semantically optimal, resulting in poor generalization. In this paper, we observe that this issue is actually caused by the graph sparsification operation, which severely destroys the important connections established between pivotal nodes and labeled ones. To address this, we propose to restore the corrupted affinities and replenish the missed supervision for better LGI. The key challenge then lies in identifying the critical nodes and recovering the corrupted affinities. We begin by defining the pivotal nodes as k-hop starved nodes, which can be identified based on a given adjacency matrix. Considering the high computational burden, we further present a more efficient alternative inspired by CUR matrix decomposition. Subsequently, we eliminate the starved nodes by reconstructing the destroyed connections. Extensive experiments on representative benchmarks demonstrate that reducing the starved nodes consistently improves the performance of state-of-the-art LGI methods, especially under extremely limited supervision (6.12% improvement on Pubmed with a labeling rate of only 0.3%).

Anomaly detection is a fundamental yet challenging problem in machine learning due to the lack of label information. In this work, we propose a novel and powerful framework, dubbed as SLA2P, for unsupervised anomaly detection. After extracting representative embeddings from raw data, we apply random projections to the features and regard features transformed by different projections as belonging to distinct pseudo-classes. We then train a classifier network on these transformed features to perform self-supervised learning. Next, we add adversarial perturbation to the transformed features to decrease their softmax scores of the predicted labels and design anomaly scores based on the predictive uncertainties of the classifier on these perturbed features. Our motivation is that because of the relatively small number and the decentralized modes of anomalies, 1) the pseudo label classifier's training concentrates more on learning the semantic information of normal data rather than anomalous data; 2) the transformed features of the normal data are more robust to the perturbations than those of the anomalies. Consequently, the perturbed transformed features of anomalies fail to be classified well and accordingly have lower anomaly scores than those of the normal samples. Extensive experiments on image, text, and inherently tabular benchmark datasets back up our findings and indicate that SLA2 achieves state-of-the-art anomaly detection performance consistently. Our code is made publicly available at https://github.com/wyzjack/SLA2P

Pedestrian trajectory prediction is an essential component in a wide range of AI applications such as autonomous driving and robotics. Existing methods usually assume the training and testing motions follow the same pattern while ignoring the potential distribution differences (e.g., shopping mall and street). This issue results in inevitable performance decrease. To address this issue, we propose a novel Transferable Graph Neural Network (TGNN) frame-work, which jointly conducts trajectory prediction as well as domain alignment in a unified framework. Specifically, a domain-invariant GNN is proposed to explore the structural motion knowledge where the domain-specific knowledge is reduced. Moreover, an attention-based adaptive knowledge learning module is further proposed to explore fine-grained individual-level feature representations for knowledge transfer. By this way, disparities across different trajectory domains will be better alleviated. More challenging while practical trajectory prediction experiments are designed, and the experimental results verify the superior performance of our proposed model. To the best of our knowledge, our work is the pioneer which fills the gap in benchmarks and techniques for practical pedestrian trajectory prediction across different domains.

Anomaly detection in videos is a significant yet challenging problem. Previous approaches based on deep neural networks employ either reconstruction-based or prediction-based approaches. Nevertheless, existing reconstruction-based methods 1) rely on old-fashioned convolutional autoencoders and are poor at modeling temporal dependency; 2) are prone to overfit the training samples, leading to indistinguishable reconstruction errors of normal and abnormal frames during the inference phase. To address such issues, firstly, we get inspiration from transformer and propose Spatio-Temporal Auto-Trans-Encoder, dubbed as STATE, as a new autoencoder model for enhanced consecutive frame reconstruction. Our STATE is equipped with a specifically designed learnable convolutional attention module for efficient temporal learning and reasoning. Secondly, we put forward a novel reconstruction-based input perturbation technique during testing to further differentiate anomalous frames. With the same perturbation magnitude, the testing reconstruction error of the normal frames lowers more than that of the abnormal frames, which contributes to mitigating the overfitting problem of reconstruction. Owing to the high relevance of the frame abnormality and the objects in the frame, we conduct object-level reconstruction using both the raw frame and the corresponding optical flow patches. Finally, the anomaly score is designed based on the combination of the raw and motion reconstruction errors using perturbed inputs. Extensive experiments on benchmark video anomaly detection datasets demonstrate that our approach outperforms previous reconstruction-based methods by a notable margin, and achieves state-of-the-art anomaly detection performance consistently. The code is available at https://github.com/wyzjack/MRMGA4VAD.

Few-shot learning aims to enable models generalize to new categories (query instances) with only limited labeled samples (support instances) from each category. Metric-based mechanism is a promising direction which compares feature embeddings via different metrics. However, it always fail to generalize to unseen domains due to the considerable domain gap challenge. In this paper, we propose a novel framework, MemREIN, which considers Memorized, Restitution, and Instance Normalization for cross-domain few-shot learning. Specifically, an instance normalization algorithm is explored to alleviate feature dissimilarity, which provides the initial model generalization ability. However, naively normalizing the feature would lose fine-grained discriminative knowledge between different classes. To this end, a memorized module is further proposed to separate the most refined knowledge and remember it. Then, a restitution module is utilized to restitute the discrimination ability from the learned knowledge. A novel reverse contrastive learning strategy is proposed to stabilize the distillation process. Extensive experiments on five popular benchmark datasets demonstrate that MemREIN well addresses the domain shift challenge, and significantly improves the performance up to 16.43% compared with state-of-the-art baselines.

Existing action recognition methods typically sample a few frames to represent each video to avoid the enormous computation, which often limits the recognition performance. To tackle this problem, we propose Ample and Focal Network (AFNet), which is composed of two branches to utilize more frames but with less computation. Specifically, the Ample Branch takes all input frames to obtain abundant information with condensed computation and provides the guidance for Focal Branch by the proposed Navigation Module; the Focal Branch squeezes the temporal size to only focus on the salient frames at each convolution block; in the end, the results of two branches are adaptively fused to prevent the loss of information. With this design, we can introduce more frames to the network but cost less computation. Besides, we demonstrate AFNet can utilize less frames while achieving higher accuracy as the dynamic selection in intermediate features enforces implicit temporal modeling. Further, we show that our method can be extended to reduce spatial redundancy with even less cost. Extensive experiments on five datasets demonstrate the effectiveness and efficiency of our method.

Trajectory prediction of multiple agents in a crowded scene is an essential component in many applications, including intelligent monitoring, autonomous robotics, and self-driving cars. Accurate agent trajectory prediction remains a significant challenge because of the complex dynamic interactions among the agents and between them and the surrounding scene. To address the challenge, we propose a decoupled attention-based spatial-temporal modeling strategy in the proposed trajectory prediction method. The past and current interactions among agents are dynamically and adaptively summarized by two separate attention-based networks and have proven powerful in improving the prediction accuracy. Moreover, it is optional in the proposed method to make use of the road map and the plan of the ego-agent for scene-compliant and accurate predictions. The road map feature is efficiently extracted by a convolutional neural network, and the features of the ego-agent’s plan is extracted by a gated recurrent network with an attention module based on the temporal characteristic. Experiments on benchmark trajectory prediction datasets demonstrate that the proposed method is effective when the ego-agent plan and the the surrounding scene information are provided and achieves state-of-the-art performance with only the observed trajectories.

Pedestrian trajectory prediction is an important but difficult task in self-driving or autonomous mobile robot field because there are complex unpredictable human-human interactions in crowded scenarios. There have been a large number of studies that attempt to understand humans' social behavior. However, most of these studies extract location features from previous one time step while neglecting the vital velocity features. In order to address this issue, we propose a novel feature-cascaded framework for long short-term network (CF-LSTM) without extra artificial settings or social rules. In this framework, feature information from previous two time steps are firstly extracted and then integrated as a cascaded feature to LSTM, which is able to capture the previous location information and dynamic velocity information, simultaneously. In addition, this scene-agnostic cascaded feature is the external manifestation of complex human-human interactions, which can also effectively capture dynamic interaction information in different scenes without any other pedestrians' information. Experiments on public benchmark datasets indicate that our model achieves better performance than the state-of-the-art methods and this feature-cascaded framework has the ability to implicitly learn human-human interactions.