This paper considers the challenging problem of 3D Human Pose Estimation (HPE) from a sparse set of Inertial Measurement Units (IMUs). Existing efforts typically reconstruct a pose sequence by either directly tackling whole-body motions or focusing on distinctive spatio-temporal features of local body parts. Unfortunately, these methods ignore existing interdependent motor synergies amongst body parts, which may lead to pose estimation with ambiguous local parts. This observation motivates us to propose a hierarchical learning-based approach, HiPoser, which utilizes a hierarchical shared structure using Mamba blocks as the backbone to focus on the following estimation tasks, involving: 1) torso pose, 2) lower limbs pose, 3) upper limbs pose, and finally 4) global translation. These tasks selectively incorporate body motion states and are to be carried out sequentially in reconstructing part-based poses, which are amalgamated to estimate the final full-body pose with the global translation that satisfies inter-part consistencies. Our hierarchical structure allows HiPoser the flexibility in prioritizing different aspects of pose estimation, to emphasize more on detail or stability. Empirical evaluations over three benchmark datasets demonstrate the superiority of HiPoser over existing state-of-the-art models, suggesting that analyzing the synergistic movement of body parts is indeed important for advancing IMU-based 3D HPE.

Fashion image editing is a valuable tool for designers to convey their creative ideas by visualizing design concepts. With the recent advances in text editing methods, significant progress has been made in fashion image editing. However, they face two key challenges: spurious correlations in training data often induce changes in other areas when editing an area representing the intended editing concept, and these models typically lack the ability to edit multiple concepts simultaneously. To address the above challenges, we propose a novel Text-driven Fashion Image ediTing framework called T-FIT to mitigate the impact of spurious correlation by integrating counterfactual reasoning with compositional concept learning to precisely ensure compositional multi-concept fashion image editing relying solely on text descriptions. Specifically, T-FIT includes three key components. (i) Counterfactual abduction module, which learns an exogenous variable of the source image by a denoising U-Net model. (ii) Concept learning module, which identifies concepts in fashion image editing—such as clothing types and colors and projects a target concept into the space spanned from a series of textual prompts. (iii) Concept composition module, which enables simultaneous adjustments of multiple concepts by aggregating each concept’s direction vector obtained from the concept learning module. Extensive experiments show that our method can achieve state-of-the-art performance on various fashion image editing tasks, including single-concept editing (e.g., sleeve length, clothing type) and multi-concept editing (e.g., color & sleeve length).

A key challenge for controllable image editing is that visual attributes with semantic meanings are not always independent, resulting in spurious correlations in model training. However, most existing methods ignore such issues, leading to biased causal visual representation learning and unintended changes to unrelated regions or attributes in the edited images. To bridge this gap, we propose a diffusion-based causal visual representation learning framework called CIDiffuser to capture causal representations of visual attributes based on structural causal models to address the spurious correlation. Specifically, we first decompose the image representation into a high-level semantic representation for core attributes of the image and a low-level stochastic representation for other random or less structured aspects, with the former extracted by a semantic encoder and the latter derived via a stochastic encoder. We then introduce a causal effect learning module to capture the direct causal effect, that is, the difference of potential outcomes before and after intervening on the visual attributes. In addition, a diffusion-based learning strategy is designed to optimize the representation learning process. Empirical evaluations on two benchmark datasets demonstrate that our approach significantly outperforms state-of-the-art methods, enabling highly controllable image editing by modifying learned visual representations.

Imbalanced Time-Series Classification is a critical, yet challenging task across a spectrum of real-world applications. Previous oversampling and generative approaches primarily target the minority class and often rely on static decision boundaries or similarity-based heuristics. However, these methods overlook the underlying causal factors that govern the distinction between majority and minority classes, particularly in scenarios with ambiguous class boundaries. As a result, the generated samples may fail to enhance class separability, thereby limiting improvements in classification performance. To this end, we propose a CounterFactual Augmentation Minority Generation (CFAMG) method based on generative models that aims to discover the causal factors that determine different classes from a causality perspective. Specifically, our method first utilizes a disentangled classifier to distinguish between causal and non-causal factors. Next, we perform counterfactual intervention by replacing the causal factors of majority class samples with those from minority class samples, creating an intervened latent representation that reflects minority characteristics while preserving essential structures. Finally, the trained minority class decoder generates counterfactual minority samples that resemble real minority instances yet remain distinguishable from the original majority class. Extensive experiments demonstrate that our method outperforms state-of-the-art methods in both univariate and multivariate imbalanced time-series classification tasks. The code is published at https://github.com/WangLei-CQU/CFAMG.

A significant challenge in air quality index (AQI) prediction is to accurately evaluate the potential outcomes after conducting interventions in pollutant factors such as industrial emissions for each enterprise. Existed methods often suffer from spurious correlations caused by unmeasured confounders and are lack of interpretability of the model, leading to sub-optimal prediction performance. This motivates us to propose a causal AQI prediction framework (CAP) that employs a structural causal model (SCM) to characterize the causal structural variability of various AQI factors for robust AQI prediction. Specifically, we employ the front-door adjustment to explicitly eliminate unmeasured confounders by intervening in industrial emissions from the target enterprise. Meanwhile, we take industrial emissions of neighboring enterprises into account when intervening in the target enterprise and simulate the dispersion of industrial emissions through a Gaussian plume model based on meteorological factors. Experiments on two real-world datasets validate the superior performance of our model on AQI prediction compared to the state-of-the-art baselines.

The primary challenge in cognitive load recognition is the inherent diversity and causality of multivariate physiological changes, as each instance exhibits a distinctive configuration of physiological events and their spatio-temporal causal dependencies. This leads us to define a causal graph designed by prior knowledge about cognitive load to identify the latent factors hidden in the multi-instance bags constructed by the observed instances of multiple physiological channels. In particular, our model introduces the multi-instance causal representation to explicitly disentangle the unique causal configurations of a particular cognitive load state as a variable number of temporal causal variables and spurious causal variables. In addition, GADF maps are constructed to capture the inherent spatio-temporal dependency among multivariate signals in a 2D structural space. A domain adapter is employed to reduce domain bias by effectively transferring the train domain to the test domain in such continuous latent space. Empirical evaluations on two benchmark datasets and two in-house datasets collected by ourselves suggest our model significantly outperforms the state- of-the-art approaches.

Artificial intelligence generated content (AIGC) has emerged as an indispensable tool for producing large-scale content in various forms, such as images, thanks to the significant role that AI plays in imitation and production. However, interpretability and controllability remain challenges. Existing AI methods often face challenges in producing images that are both flexible and controllable while considering causal relationships within the images. To address this issue, we have developed a novel method for causal controllable image generation (CCIG) that combines causal representation learning with bi-directional generative adversarial networks (GANs). This approach enables humans to control image attributes while considering the rationality and interpretability of the generated images and also allows for the generation of counterfactual images. The key of our approach, CCIG, lies in the use of a causal structure learning module to learn the causal relationships between image attributes and joint optimization with the encoder, generator, and joint discriminator in the image generation module. By doing so, we can learn causal representations in image’s latent space and use causal intervention operations to control image generation. We conduct extensive experiments on a real-world dataset, CelebA. The experimental results illustrate the effectiveness of CCIG.

The primary goal of cancer risk prediction is to find dominant features, with each being responsible for cancer diagnosis. As a result, selected feature sets often converge to inexplicable and implausible results. Existing score-based causal models adopt a score function to learn a local causal structure to explicitly characterize a unique causal configuration as a variable number of nodes and links, which however suffer from nonconvex optimization and global incompleteness. This leads us to present a score-based approach to construct a causal network by optimizing a score function with a convex solution under the constraint of causal Markov property. It can be analytically shown that the resulting causal network satisfies the causal Markov property, and as a result, all cause-effect dependencies can be retained and are globally consistent. An additional node selector is introduced to choose the most dominant causal features. Empirical evaluations on three benchmarks and one in-house cancer risk datasets suggest our approach significantly outperforms the state-of-the-arts.

Multimedia recommendation involves personalized ranking tasks, where multimedia content is usually represented using a generic encoder. However, these generic representations introduce spurious correlations that fail to reveal users' true preferences. Existing works attempt to alleviate this problem by learning invariant representations, but overlook the balance between independent and identically distributed (IID) and out-of-distribution (OOD) generalization. In this paper, we propose a framework called Pareto Invariant Representation Learning (PaInvRL) to mitigate the impact of spurious correlations from an IID-OOD multi-objective optimization perspective, by learning invariant representations (intrinsic factors that attract user attention) and variant representations (other factors) simultaneously. Specifically, PaInvRL includes three iteratively executed modules: (i) heterogeneous identification module, which identifies the heterogeneous environments to reflect distributional shifts for user-item interactions; (ii) invariant mask generation module, which learns invariant masks based on the Pareto-optimal solutions that minimize the adaptive weighted Invariant Risk Minimization (IRM) and Empirical Risk (ERM) losses; (iii) convert module, which generates both variant representations and item-invariant representations for training a multi-modal recommendation model that mitigates spurious correlations and balances the generalization performance within and cross the environmental distributions. We compare the proposed PaInvRL with state-of-the-art recommendation models on three public multimedia recommendation datasets (Movielens, Tiktok, and Kwai), and the experimental results validate the effectiveness of PaInvRL for both within-and cross-environmental learning.