Search

The image-text retrieval task aims to retrieve relevant information from a given image or text. The main challenge is to unify multimodal representation and distinguish fine-grained differences across modalities, thereby finding similar contents and filtering irrelevant contents. However, existing methods mainly focus on unified semantic representation and concept alignment for multi-modalities, while the fine-grained differences across modalities have rarely been studied before, making it difficult to solve the information asymmetry problem. In this paper, we propose a novel asymmetry-sensitive contrastive learning method. By generating corresponding positive and negative samples for different asymmetry types, our method can simultaneously ensure fine-grained semantic differentiation and unified semantic representation between multi-modalities. Additionally, a hierarchical cross-modal fusion method is proposed, which integrates global and local-level features through a multimodal attention mechanism to achieve concept alignment. Extensive experiments performed on MSCOCO and Flickr30K, demonstrate the effectiveness and superiority of our proposed method., Comment: This work has been strong-accepted as the oral conference paper by IEEE International Conference on Multimedia & Expo (ICME) 2024

Distribution matching can be used to learn invariant representations with applications in fairness and robustness. Most prior works resort to adversarial matching methods but the resulting minimax problems are unstable and challenging to optimize. Non-adversarial likelihood-based approaches either require model invertibility, impose constraints on the latent prior, or lack a generic framework for distribution matching. To overcome these limitations, we propose a non-adversarial VAE-based matching method that can be applied to any model pipeline. We develop a set of alignment upper bounds for distribution matching (including a noisy bound) that have VAE-like objectives but with a different perspective. We carefully compare our method to prior VAE-based matching approaches both theoretically and empirically. Finally, we demonstrate that our novel matching losses can replace adversarial losses in standard invariant representation learning pipelines without modifying the original architectures -- thereby significantly broadening the applicability of non-adversarial matching methods., Comment: 9 pages, AISTATS 2024

This paper aims to detect the potential injury risk of the anterior cruciate ligament (ACL) by proposing an ACL potential injury risk assessment algorithm based on key points of the human body detected using computer vision technology. To obtain the key points data of the human body in each frame, OpenPose, an open source computer vision algorithm, was employed. The obtained data underwent preprocessing and were then fed into an ACL potential injury feature extraction model based on the Landing Error Evaluation System (LESS). This model extracted several important parameters, including the knee flexion angle, the trunk flexion on the sagittal plane, trunk flexion angle on the frontal plane, the ankle knee horizontal distance, and the ankle shoulder horizontal distance. Each of these features was assigned a threshold interval, and a segmented evaluation function was utilized to score them accordingly. To calculate the final score of the participant, the score values were input into a weighted scoring model designed based on the Analytic Hierarchy Process (AHP). The AHP based model takes into account the relative importance of each feature in the overall assessment. The results demonstrate that the proposed algorithm effectively detects the potential risk of ACL injury. The proposed algorithm demonstrates its effectiveness in detecting ACL injury risk, offering valuable insights for injury prevention and intervention strategies in sports and related fields. Code is available at: https://github.com/ZiyuGong-proj/Assessment-of-ACL-Injury-Risk-Based-on-Openpose, Comment: 17 pages,and 6 figures

Unsupervised distribution alignment estimates a transformation that maps two or more source distributions to a shared aligned distribution given only samples from each distribution. This task has many applications including generative modeling, unsupervised domain adaptation, and socially aware learning. Most prior works use adversarial learning (i.e., min-max optimization), which can be challenging to optimize and evaluate. A few recent works explore non-adversarial flow-based (i.e., invertible) approaches, but they lack a unified perspective and are limited in efficiently aligning multiple distributions. Therefore, we propose to unify and generalize previous flow-based approaches under a single non-adversarial framework, which we prove is equivalent to minimizing an upper bound on the Jensen-Shannon Divergence (JSD). Importantly, our problem reduces to a min-min, i.e., cooperative, problem and can provide a natural evaluation metric for unsupervised distribution alignment. We show empirical results on both simulated and real-world datasets to demonstrate the benefits of our approach. Code is available at https://github.com/inouye-lab/alignment-upper-bound., Comment: Accepted for publication in Advances in Neural Information Processing Systems 36 (NeurIPS 2022)

The unsupervised task of aligning two or more distributions in a shared latent space has many applications including fair representations, batch effect mitigation, and unsupervised domain adaptation. Existing flow-based approaches estimate multiple flows independently, which is equivalent to learning multiple full generative models. Other approaches require adversarial learning, which can be computationally expensive and challenging to optimize. Thus, we aim to jointly align multiple distributions while avoiding adversarial learning. Inspired by efficient alignment algorithms from optimal transport (OT) theory for univariate distributions, we develop a simple iterative method to build deep and expressive flows. Our method decouples each iteration into two subproblems: 1) form a variational approximation of a distribution divergence and 2) minimize this variational approximation via closed-form invertible alignment maps based on known OT results. Our empirical results give evidence that this iterative algorithm achieves competitive distribution alignment at low computational cost while being able to naturally handle more than two distributions.