3D human pose estimation captures the human joint points in three-dimensional space while keeping the depth information and physical structure. That is essential for applications that require precise pose information, such as human-computer interaction, scene understanding, and rehabilitation training. Due to the challenges in data collection, mainstream datasets of 3D human pose estimation are primarily composed of multi-view video data collected in laboratory environments, which contains rich spatial-temporal correlation information besides the image frame content. Given the remarkable self-attention mechanism of transformers, capable of capturing the spatial-temporal correlation from multi-view video datasets, we propose a multi-stage framework for 3D sequence-to-sequence (seq2seq) human pose detection. Firstly, the spatial module represents the human pose feature by intra-image content, while the frame-image relation module extracts temporal relationships and 3D spatial positional relationship features between the multi-perspective images. Secondly, the self-attention mechanism is adopted to eliminate the interference from non-human body parts and reduce computing resources. Our method is evaluated on Human3.6M, a popular 3D human pose detection dataset. Experimental results demonstrate that our approach achieves state-of-the-art performance on this dataset.
The essential of navigation, perception, and decision-making which are basic tasks for intelligent robots, is to estimate necessary system states. Among them, navigation is fundamental for other upper applications, providing precise position and orientation, by integrating measurements from multiple sensors. With observations of each sensor appropriately modelled, multi-sensor fusion tasks for navigation are reduced to the state estimation problem which can be solved by two approaches: optimization and filtering. Recent research has shown that optimization-based frameworks outperform filtering-based ones in terms of accuracy. However, both methods are based on maximum likelihood estimation (MLE) and should be theoretically equivalent with the same linearization points, observation model, measurements, and Gaussian noise assumption. In this paper, we deeply dig into the theories and existing strategies utilized in both optimization-based and filtering-based approaches. It is demonstrated that the two methods are equal theoretically, but this equivalence corrupts due to different strategies applied in real-time operation. By adjusting existing strategies of the filtering-based approaches, the Monte-Carlo simulation and vehicular ablation experiments based on visual odometry (VO) indicate that the strategy adjusted filtering strictly equals to optimization. Therefore, future research on sensor-fusion problems should concentrate on their own algorithms and strategies rather than state estimation approaches.
Predicting individual aesthetic preferences holds significant practical applications and academic implications for human society. However, existing studies mainly focus on learning and predicting the commonality of facial attractiveness, with little attention given to Personalized Facial Beauty Prediction (PFBP). PFBP aims to develop a machine that can adapt to individual aesthetic preferences with only a few images rated by each user. In this paper, we formulate this task from a meta-learning perspective that each user corresponds to a meta-task. To address such PFBP task, we draw inspiration from the human aesthetic mechanism that visual aesthetics in society follows a Gaussian distribution, which motivates us to disentangle user preferences into a commonality and an individuality part. To this end, we propose a novel MetaFBP framework, in which we devise a universal feature extractor to capture the aesthetic commonality and then optimize to adapt the aesthetic individuality by shifting the decision boundary of the predictor via a meta-learning mechanism. Unlike conventional meta-learning methods that may struggle with slow adaptation or overfitting to tiny support sets, we propose a novel approach that optimizes a high-order predictor for fast adaptation. In order to validate the performance of the proposed method, we build several PFBP benchmarks by using existing facial beauty prediction datasets rated by numerous users. Extensive experiments on these benchmarks demonstrate the effectiveness of the proposed MetaFBP method.
Agnostic domain shift is the main reason of model degradation on the unknown target domains, which brings an urgent need to develop Domain Generalization (DG). Recent advances at DG use dynamic networks to achieve training-free adaptation on the unknown target domains, termed Dynamic Domain Generalization (DDG), which compensates for the lack of self-adaptability in static models with fixed weights. The parameters of dynamic networks can be decoupled into a static and a dynamic component, which are designed to learn domain-invariant and domain-specific features, respectively. Based on the existing arts, in this work, we try to push the limits of DDG by disentangling the static and dynamic components more thoroughly from an optimization perspective. Our main consideration is that we can enable the static component to learn domain-invariant features more comprehensively by augmenting the domain-specific information. As a result, the more comprehensive domain-invariant features learned by the static component can then enforce the dynamic component to focus more on learning adaptive domain-specific features. To this end, we propose a simple yet effective Parameter Exchange (PE) method to perturb the combination between the static and dynamic components. We optimize the model using the gradients from both the perturbed and non-perturbed feed-forward jointly to implicitly achieve the aforementioned disentanglement. In this way, the two components can be optimized in a mutually-beneficial manner, which can resist the agnostic domain shifts and improve the self-adaptability on the unknown target domain. Extensive experiments show that PE can be easily plugged into existing dynamic networks to improve their generalization ability without bells and whistles.
We do not pursue a novel method in this paper, but aim to study if a modern text-to-image diffusion model can tailor any task-adaptive image classifier across domains and categories. Existing domain adaptive image classification works exploit both source and target data for domain alignment so as to transfer the knowledge learned from the labeled source data to the unlabeled target data. However, as the development of the text-to-image diffusion model, we wonder if the high-fidelity synthetic data from the text-to-image generator can serve as a surrogate of the source data in real world. In this way, we do not need to collect and annotate the source data for each domain adaptation task in a one-for-one manner. Instead, we utilize only one off-the-shelf text-to-image model to synthesize images with category labels derived from the corresponding text prompts, and then leverage the surrogate data as a bridge to transfer the knowledge embedded in the task-agnostic text-to-image generator to the task-oriented image classifier via domain adaptation. Such a one-for-all adaptation paradigm allows us to adapt anything in the world using only one text-to-image generator as well as the corresponding unlabeled target data. Extensive experiments validate the feasibility of the proposed idea, which even surpasses the state-of-the-art domain adaptation works using the source data collected and annotated in real world.
Due to the extremely low signal-to-noise ratio (SNR) and unknown poses (projection angles and image translation) in cryo-EM experiments, reconstructing 3D structures from 2D images is very challenging. On top of these challenges, heterogeneous cryo-EM reconstruction also has an additional requirement: conformation classification. An emerging solution to this problem is called amortized inference, implemented using the autoencoder architecture or its variants. Instead of searching for the correct image-to-pose/conformation mapping for every image in the dataset as in non-amortized methods, amortized inference only needs to train an encoder that maps images to appropriate latent spaces representing poses or conformations. Unfortunately, standard amortized-inference-based methods with entangled latent spaces have difficulty learning the distribution of conformations and poses from cryo-EM images. In this paper, we propose an unsupervised deep learning architecture called "ACE-HetEM" based on amortized inference. To explicitly enforce the disentanglement of conformation classifications and pose estimations, we designed two alternating training tasks in our method: image-to-image task and pose-to-pose task. Results on simulated datasets show that ACE-HetEM has comparable accuracy in pose estimation and produces even better reconstruction resolution than non-amortized methods. Furthermore, we show that ACE-HetEM is also applicable to real experimental datasets.
Cryo-electron microscopy (cryo-EM) is a technique for reconstructing the 3-dimensional (3D) structure of biomolecules (especially large protein complexes and molecular assemblies). As the resolution increases to the near-atomic scale, building protein structures de novo from cryo-EM maps becomes possible. Recently, recognition-based de novo building methods have shown the potential to streamline this process. However, it cannot build a complete structure due to the low signal-to-noise ratio (SNR) problem. At the same time, AlphaFold has led to a great breakthrough in predicting protein structures. This has inspired us to combine fragment recognition and structure prediction methods to build a complete structure. In this paper, we propose a new method named FFF that bridges protein structure prediction and protein structure recognition with flexible fitting. First, a multi-level recognition network is used to capture various structural features from the input 3D cryo-EM map. Next, protein structural fragments are generated using pseudo peptide vectors and a protein sequence alignment method based on these extracted features. Finally, a complete structural model is constructed using the predicted protein fragments via flexible fitting. Based on our benchmark tests, FFF outperforms the baseline methods for building complete protein structures.
Pre-trained language models (PLMs) have played an increasing role in multimedia research. In terms of vision-language (VL) tasks, they often serve as a language encoder and still require an additional fusion network for VL reasoning, resulting in excessive memory overhead. In this paper, we focus on exploring PLMs as a stand-alone model for VL reasoning tasks. Inspired by the recently popular prompt tuning, we first prove that the processed visual features can be also projected onto the semantic space of PLMs and act as prompt tokens to bridge the gap between single- and multi-modal learning. However, this solution exhibits obvious redundancy in visual information and model inference, and the placement of prompt tokens also greatly affects the final performance. Based on these observations, we further propose a novel transfer learning approach for PLMs, termed Dynamic Visual Prompting (DVP). Concretely, DVP first deploys a cross-attention module to obtain text-related and compact visual prompt tokens, thereby greatly reducing the input length of PLMs. To obtain the optimal placement, we also equip DVP with a reinforcement-learning based search algorithm, which can automatically merge DVP with PLMs for different VL tasks via a very short search process. In addition, we also experiment DVP with the recently popular adapter approach to keep the most parameters of PLMs intact when adapting to VL tasks, helping PLMs achieve a quick shift between single- and multi-modal tasks. We apply DVP to two representative PLMs, namely BERT and T5, and conduct extensive experiments on a set of VL reasoning benchmarks including VQA2.0, GQA and SNLIVE. The experimental results not only show the advantage of DVP on efficiency and performance, but also confirm its superiority in adapting pre-trained language models to VL tasks.
Large-scale vision-language pre-training has shown promising advances on various downstream tasks and achieved significant performance in multi-modal understanding and generation tasks. However, existing methods often perform poorly on image-text matching tasks that require a detailed semantics understanding of the text. Although there have been some works on this problem, they do not sufficiently exploit the structural knowledge present in sentences to enhance multi-modal language representations, which leads to poor performance. In this paper, we present an end-to-end framework Structure-CLIP, which integrates latent detailed semantics from the text to enhance fine-grained semantic representations. Specifically, (1) we use scene graphs in order to pay more attention to the detailed semantic learning in the text and fully explore structured knowledge between fine-grained semantics, and (2) we utilize the knowledge-enhanced framework with the help of the scene graph to make full use of representations of structured knowledge. To verify the effectiveness of our proposed method, we pre-trained our models with the aforementioned approach and conduct experiments on different downstream tasks. Numerical results show that Structure-CLIP can often achieve state-of-the-art performance on both VG-Attribution and VG-Relation datasets. Extensive experiments show its components are effective and its predictions are interpretable, which proves that our proposed method can enhance detailed semantic representation well.
We propose a twin support vector quantile regression (TSVQR) to capture the heterogeneous and asymmetric information in modern data. Using a quantile parameter, TSVQR effectively depicts the heterogeneous distribution information with respect to all portions of data points. Correspondingly, TSVQR constructs two smaller sized quadratic programming problems (QPPs) to generate two nonparallel planes to measure the distributional asymmetry between the lower and upper bounds at each quantile level. The QPPs in TSVQR are smaller and easier to solve than those in previous quantile regression methods. Moreover, the dual coordinate descent algorithm for TSVQR also accelerates the training speed. Experimental results on six artiffcial data sets, ffve benchmark data sets, two large scale data sets, two time-series data sets, and two imbalanced data sets indicate that the TSVQR outperforms previous quantile regression methods in terms of the effectiveness of completely capturing the heterogeneous and asymmetric information and the efffciency of the learning process.