Data augmentation is an effective technique for regularizing deep networks, which helps to enhance the generalizability and robustness of the model. However, in the field of medical imaging, traditional data augmentation techniques such as cropping, rotation, and degradation may inadvertently alter the critical characteristics of pathological lesions. Conventional semantic augmentation methods, such as altering the color and contrast of the object background, may also affect the structural features of medical images in uncontrolled semantic directions. Such operational conditions compromise the model's diagnostic reliability in medical contexts. To address this issue, we propose a surprisingly efficient implicit augmentation-invariant learning strategy (AILS) via variational Bayesian inference on differentially constrained feature manifolds. Parameterizing probability measures over tangent space through deep networks enables precise estimation of semantic direction distributions. Subsequently, geodesic-aware semantic features are sampled from the reparameterized variational posterior, achieving semantic-consistent augmentation. Simultaneously, to mine augmentation distribution invariance, we design the AiHLoss, which constrains the augmentation distribution to facilitate the network to learn augmentation invariance. Extensive experiments demonstrate that AILS exhibits high performance on public medical image datasets, outperforming existing augmentation methods.

Recent studies have made great progress on skeleton-based action recognition. However, most of them are developed with relatively clean skeletons without the presence of intensive noise. We argue that the models learned from relatively clean data are not well generalizable to handle noisy skeletons commonly appeared in the real world. In this paper, we address the challenge of recognizing human actions from noisy skeletons, which is seldom explored by previous methods. Beyond exploring the new problem, we further take a new perspective to address it, \textit{i.e.}, noise adaptation, which gets rid of explicit skeleton noise modeling and reliance on skeleton ground truths. Specifically, we develop regression-based and generation-based adaptation models according to whether pairs of noisy skeletons are available. The regression-based model aims to learn noise-suppressed intrinsic feature representations by mapping pairs of noisy skeletons into a noise-robust space. When only unpaired skeletons are accessible, the generation-based model aims to adapt the features from noisy skeletons to a low-noise space by adversarial learning. To verify our proposed model and facilitate research on noisy skeletons, we collect a new dataset Noisy Skeleton Dataset (NSD), the skeletons of which are with much noise and more similar to daily-life data than previous datasets. Extensive experiments are conducted on the NSD, VV-RGBD and N-UCLA datasets, and results consistently show the outstanding performance of our proposed model.

In this paper, we address the problem of referring expression comprehension in videos, which is challenging due to complex expression and scene dynamics. Unlike previous methods which solve the problem in multiple stages (i.e., tracking, proposal-based matching), we tackle the problem from a novel perspective, co-grounding, with an elegant one-stage framework. We enhance the single-frame grounding accuracy by semantic attention learning and improve the cross-frame grounding consistency with co-grounding feature learning. Semantic attention learning explicitly parses referring cues in different attributes to reduce the ambiguity in the complex expression. Co-grounding feature learning boosts visual feature representations by integrating temporal correlation to reduce the ambiguity caused by scene dynamics. Experiment results demonstrate the superiority of our framework on the video grounding datasets VID and LiOTB in generating accurate and stable results across frames. Our model is also applicable to referring expression comprehension in images, illustrated by the improved performance on the RefCOCO dataset. Our project is available at https://sijiesong.github.io/co-grounding.

In this paper, we tackle the problem of pose-guided person image generation with unpaired data, which is a challenging problem due to non-rigid spatial deformation. Instead of learning a fixed mapping directly between human bodies as previous methods, we propose a new pathway to decompose a single fixed mapping into two subtasks, namely, semantic parsing transformation and appearance generation. First, to simplify the learning for non-rigid deformation, a semantic generative network is developed to transform semantic parsing maps between different poses. Second, guided by semantic parsing maps, we render the foreground and background image, respectively. A foreground generative network learns to synthesize semantic-aware textures, and another background generative network learns to predict missing background regions caused by pose changes. Third, we enable pseudo-label training with unpaired data, and demonstrate that end-to-end training of the overall network further refines the semantic map prediction and final results accordingly. Moreover, our method is generalizable to other person image generation tasks defined on semantic maps, e.g., clothing texture transfer, controlled image manipulation, and virtual try-on. Experimental results on DeepFashion and Market-1501 datasets demonstrate the superiority of our method, especially in keeping better body shapes and clothing attributes, as well as rendering structure-coherent backgrounds.

In this paper, we address self-supervised representation learning from human skeletons for action recognition. Previous methods, which usually learn feature presentations from a single reconstruction task, may come across the overfitting problem, and the features are not generalizable for action recognition. Instead, we propose to integrate multiple tasks to learn more general representations in a self-supervised manner. To realize this goal, we integrate motion prediction, jigsaw puzzle recognition, and contrastive learning to learn skeleton features from different aspects. Skeleton dynamics can be modeled through motion prediction by predicting the future sequence. And temporal patterns, which are critical for action recognition, are learned through solving jigsaw puzzles. We further regularize the feature space by contrastive learning. Besides, we explore different training strategies to utilize the knowledge from self-supervised tasks for action recognition. We evaluate our multi-task self-supervised learning approach with action classifiers trained under different configurations, including unsupervised, semi-supervised and fully-supervised settings. Our experiments on the NW-UCLA, NTU RGB+D, and PKUMMD datasets show remarkable performance for action recognition, demonstrating the superiority of our method in learning more discriminative and general features. Our project website is available at https://langlandslin.github.io/projects/MSL/.

With the prevalence of RGB-D cameras, multimodal video data have become more available for human action recognition. One main challenge for this task lies in how to effectively leverage their complementary information. In this work, we propose a Modality Compensation Network (MCN) to explore the relationships of different modalities, and boost the representations for human action recognition. We regard RGB/ optical flow videos as source modalities, skeletons as auxiliary modality. Our goal is to extract more discriminative features from source modalities, with the help of auxiliary modality. Built on deep Convolutional Neural Networks (CNN) and Long Short Term Memory (LSTM) networks, our model bridges data from source and auxiliary modalities by a modality adaptation block to achieve adaptive representation learning, that the network learns to compensate for the loss of skeletons at test time and even at training time. We explore multiple adaptation schemes to narrow the distance between source and auxiliary modal distributions from different levels, according to the alignment of source and auxiliary data in training. In addition, skeletons are only required in the training phase. Our model is able to improve the recognition performance with source data when testing. Experimental results reveal that MCN outperforms stateof- the-art approaches on four widely-used action recognition benchmarks.

Large-scale benchmarks provide a solid foundation for the development of action analytics. Most of the previous activity benchmarks focus on analyzing actions in RGB videos. There is a lack of large-scale and high-quality benchmarks for multi-modal action analytics. In this article, we introduce PKU Multi-Modal Dataset (PKU-MMD), a new large-scale benchmark for multi-modal human action analytics. It consists of about 28,000 action instances and 6.2 million frames in total and provides high-quality multi-modal data sources, including RGB, depth, infrared radiation (IR), and skeletons. To make PKU-MMD more practical, our dataset comprises two subsets under different settings for action understanding, namely Part I and Part II. Part I contains 1,076 untrimmed video sequences with 51 action classes performed by 66 subjects, while Part II contains 1,009 untrimmed video sequences with 41 action classes performed by 13 subjects. Compared to Part I, Part II is more challenging due to short action intervals, concurrent actions and heavy occlusion. PKU-MMD can be leveraged in two scenarios: action recognition with trimmed video clips and action detection with untrimmed video sequences. For each scenario, we provide benchmark performance on both subsets by conducting different methods with different modalities under two evaluation protocols, respectively. Experimental results show that PKU-MMD is a significant challenge to many state-of-the-art methods. We further illustrate that the features learned on PKU-MMD can be well transferred to other datasets. We believe this large-scale dataset will boost the research in the field of action analytics for the community.

Temporal modeling in videos is a fundamental yet challenging problem in computer vision. In this paper, we propose a novel Temporal Bilinear (TB) model to capture the temporal pairwise feature interactions between adjacent frames. Compared with some existing temporal methods which are limited in linear transformations, our TB model considers explicit quadratic bilinear transformations in the temporal domain for motion evolution and sequential relation modeling. We further leverage the factorized bilinear model in linear complexity and a bottleneck network design to build our TB blocks, which also constrains the parameters and computation cost. We consider two schemes in terms of the incorporation of TB blocks and the original 2D spatial convolutions, namely wide and deep Temporal Bilinear Networks (TBN). Finally, we perform experiments on several widely adopted datasets including Kinetics, UCF101 and HMDB51. The effectiveness of our TBNs is validated by comprehensive ablation analyses and comparisons with various state-of-the-art methods.

In this paper, we address unsupervised pose-guided person image generation, which is known challenging due to non-rigid deformation. Unlike previous methods learning a rock-hard direct mapping between human bodies, we propose a new pathway to decompose the hard mapping into two more accessible subtasks, namely, semantic parsing transformation and appearance generation. Firstly, a semantic generative network is proposed to transform between semantic parsing maps, in order to simplify the non-rigid deformation learning. Secondly, an appearance generative network learns to synthesize semantic-aware textures. Thirdly, we demonstrate that training our framework in an end-to-end manner further refines the semantic maps and final results accordingly. Our method is generalizable to other semantic-aware person image generation tasks, e.g., clothing texture transfer and controlled image manipulation. Experimental results demonstrate the superiority of our method on DeepFashion and Market-1501 datasets, especially in keeping the clothing attributes and better body shapes.

Online action detection is a brand new challenge and plays a critical role in visual surveillance analytics. It goes one step further than a conventional action recognition task, which recognizes human actions from well-segmented clips. Online action detection is desired to identify the action type and localize action positions on the fly from the untrimmed stream data. In this paper, we propose a multi-modality multi-task recurrent neural network, which incorporates both RGB and Skeleton networks. We design different temporal modeling networks to capture specific characteristics from various modalities. Then, a deep long short-term memory subnetwork is utilized effectively to capture the complex long-range temporal dynamics, naturally avoiding the conventional sliding window design and thus ensuring high computational efficiency. Constrained by a multi-task objective function in the training phase, this network achieves superior detection performance and is capable of automatically localizing the start and end points of actions more accurately. Furthermore, embedding subtask of regression provides the ability to forecast the action prior to its occurrence. We evaluate the proposed method and several other methods in action detection and forecasting on the online action detection data set and gaming action data set datasets. Experimental results demonstrate that our model achieves the state-of-the-art performance on both tasks.

This paper presents a new framework for action recognition with multi-modal data. A skeleton-indexed feature learning procedure is developed to further exploit the detailed local features from RGB and optical flow videos. In particular, the proposed framework is built based on a deep Convolutional Network (ConvNet) and a Recurrent Neural Network (RNN) with Long Short Term Memory (LSTM). A skeleton-indexed transform layer is designed to automatically extract visual features around key joints, and a part-aggregated pooling is developed to uniformly regulate the visual features from different body parts and actors. Besides, several fusion schemes are explored to take advantage of multi-modal data. The proposed deep architecture is end-to-end trainable and can better incorporate different modalities to learn effective feature representations. Quantitative experiment results on two datasets, the NTU RGB+D dataset and the MSR dataset, demonstrate the excellent performance of our scheme over other state-of-the-arts. To our knowledge, the performance obtained by the proposed framework is currently the best on the challenging NTU RGB+D dataset.

Human action analytics has attracted a lot of attention for decades in computer vision. It is important to extract discriminative spatio-temporal features to model the spatial and temporal evolutions of different actions. In this paper, we propose a spatial and temporal attention model to explore the spatial and temporal discriminative features for human action recognition and detection from skeleton data. We build our networks based on the recurrent neural networks with long short-term memory units. The learned model is capable of selectively focusing on discriminative joints of skeletons within each input frame and paying different levels of attention to the outputs of different frames. To ensure effective training of the network for action recognition, we propose a regularized cross-entropy loss to drive the learning process and develop a joint training strategy accordingly. Moreover, based on temporal attention, we develop a method to generate the action temporal proposals for action detection. We evaluate the proposed method on the SBU Kinect Interaction data set, the NTU RGB + D data set, and the PKU-MMD data set, respectively. Experiment results demonstrate the effectiveness of our proposed model on both action recognition and action detection.

Human action recognition is an important task in computer vision. Extracting discriminative spatial and temporal features to model the spatial and temporal evolutions of different actions plays a key role in accomplishing this task. In this work, we propose an end-to-end spatial and temporal attention model for human action recognition from skeleton data. We build our model on top of the Recurrent Neural Networks (RNNs) with Long Short-Term Memory (LSTM), which learns to selectively focus on discriminative joints of skeleton within each frame of the inputs and pays different levels of attention to the outputs of different frames. Furthermore, to ensure effective training of the network, we propose a regularized cross-entropy loss to drive the model learning process and develop a joint training strategy accordingly. Experimental results demonstrate the effectiveness of the proposed model, both on the small human action recognition dataset of SBU and the currently largest NTU dataset.

In this paper, we propose a novel neighbor embedding method based on joint sub-bands for image super-resolution. Rather than directly reconstructing the total spatial variations of the input image, we restore each frequency component separately. The input LR image is decomposed into sub-bands defined by steerable filters to capture structural details on different directional frequency components. Then the neighbor embedding principle is employed to reconstruct each band, respectively. Moreover, taken the diverse characteristics of each band into account, we adopt adaptive similarity criteri-ons for searching nearest neighbors. Finally, we recombine the generated HR sub-bands by applying the inverting subband decomposition to get the final super-resolved result. Experimental results demonstrate the effectiveness of our method both in objective and subjective qualities comparing with other state-of-the-art methods.

In this paper, we propose a novel hierarchical image completion approach using regularity statistics, considering structure features. Guided by dominant structures, the target image is used to generate reference images in a self-reproductive way by image data enhancement. The structure-guided image data enhancement allows us to expand the search space for samples. A Markov Random Field model is used to guide the enhanced image data combination to globally reconstruct the target image. For lower computational complexity and more accurate structure estimation, a hierarchical process is implemented. Experiments demonstrate the effectiveness of our method comparing to several state-of-the-art image completion techniques.

The simple yet subtle structures of faces make it difficult to capture the fine differences between different facial regions in the depth map, especially for consumer devices like Kinect. To address this issue, we present a novel method to super-solve and recover the facial depth map nicely. The key idea of our approach is to exploit the learning-based method to obtain the reliable face priors from high quality facial depth map to further improve the depth image. Specifically, we utilize the neighbor embedding framework. First, face components are decomposed to train specialized dictionaries and reconstructed, respectively. Joint features, i.e. color, depth and position cues, are put forward for robust patch similarity measurement. The neighbor embedding results form high frequency cues of facial depth details and gradients. Finally, an optimization function is defined to combine these high frequency information to yield depth maps that fit the actual face structures better. Experimental results demonstrate the superiority of our method compared to state-of-the-art techniques in recovering both synthetic data and real world data from Kinect.