Lichen Wang

Yi Xu, Lichen Wang, Yizhou Wang et al.

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 (T-GNN) framework, 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.

Taotao Jing, Lichen Wang, Naji Khosravan et al.

Room layout estimation predicts layouts from a single panorama. It requires datasets with large-scale and diverse room shapes to train the models. However, there are significant imbalances in real-world datasets including the dimensions of layout complexity, camera locations, and variation in scene appearance. These issues considerably influence the model training performance. In this work, we propose the imBalance-Aware Room Layout Estimation (iBARLE) framework to address these issues. iBARLE consists of (1) Appearance Variation Generation (AVG) module, which promotes visual appearance domain generalization, (2) Complex Structure Mix-up (CSMix) module, which enhances generalizability w.r.t. room structure, and (3) a gradient-based layout objective function, which allows more effective accounting for occlusions in complex layouts. All modules are jointly trained and help each other to achieve the best performance. Experiments and ablation studies based on ZInD~\cite{cruz2021zillow} dataset illustrate that iBARLE has state-of-the-art performance compared with other layout estimation baselines.

Haichao Zhang, Yao Lu, Lichen Wang et al.

Video Large Language Models (VLLMs) unlock world-knowledge-aware video understanding through pretraining on internet-scale data and have already shown promise on tasks such as movie analysis and video question answering. However, deploying VLLMs for downstream tasks such as video recommendation remains challenging, since real systems require multi-video inputs, lightweight backbones, low-latency sequential inference, and rapid response. In practice, (1) decode-only generation yields high latency for sequential inference, (2) typical interfaces do not support multi-video inputs, and (3) constraining outputs to language discards fine-grained visual details that matter for downstream vision tasks. We argue that these limitations stem from the absence of a representation that preserves pixel-level detail while leveraging world knowledge. We present LinkedOut, a representation that extracts VLLM world knowledge directly from video to enable fast inference, supports multi-video histories, and removes the language bottleneck. LinkedOut extracts semantically grounded, knowledge-aware tokens from raw frames using VLLMs, guided by promptable queries and optional auxiliary modalities. We introduce a cross-layer knowledge fusion MoE that selects the appropriate level of abstraction from the rich VLLM features, enabling personalized, interpretable, and low-latency recommendation. To our knowledge, LinkedOut is the first VLLM-based video recommendation method that operates on raw frames without handcrafted labels, achieving state-of-the-art results on standard benchmarks. Interpretability studies and ablations confirm the benefits of layer diversity and layer-wise fusion, pointing to a practical path that fully leverages VLLM world-knowledge priors and visual reasoning for downstream vision tasks such as recommendation.

Songyao Jiang, Bin Sun, Lichen Wang et al.

Sign language is commonly used by deaf or mute people to communicate but requires extensive effort to master. It is usually performed with the fast yet delicate movement of hand gestures, body posture, and even facial expressions. Current Sign Language Recognition (SLR) methods usually extract features via deep neural networks and suffer overfitting due to limited and noisy data. Recently, skeleton-based action recognition has attracted increasing attention due to its subject-invariant and background-invariant nature, whereas skeleton-based SLR is still under exploration due to the lack of hand annotations. Some researchers have tried to use off-line hand pose trackers to obtain hand keypoints and aid in recognizing sign language via recurrent neural networks. Nevertheless, none of them outperforms RGB-based approaches yet. To this end, we propose a novel Skeleton Aware Multi-modal Framework with a Global Ensemble Model (GEM) for isolated SLR (SAM-SLR-v2) to learn and fuse multi-modal feature representations towards a higher recognition rate. Specifically, we propose a Sign Language Graph Convolution Network (SL-GCN) to model the embedded dynamics of skeleton keypoints and a Separable Spatial-Temporal Convolution Network (SSTCN) to exploit skeleton features. The skeleton-based predictions are fused with other RGB and depth based modalities by the proposed late-fusion GEM to provide global information and make a faithful SLR prediction. Experiments on three isolated SLR datasets demonstrate that our proposed SAM-SLR-v2 framework is exceedingly effective and achieves state-of-the-art performance with significant margins. Our code will be available at https://github.com/jackyjsy/SAM-SLR-v2

Songyao Jiang, Bin Sun, Lichen Wang et al.

Sign language is commonly used by deaf or speech impaired people to communicate but requires significant effort to master. Sign Language Recognition (SLR) aims to bridge the gap between sign language users and others by recognizing signs from given videos. It is an essential yet challenging task since sign language is performed with the fast and complex movement of hand gestures, body posture, and even facial expressions. Recently, skeleton-based action recognition attracts increasing attention due to the independence between the subject and background variation. However, skeleton-based SLR is still under exploration due to the lack of annotations on hand keypoints. Some efforts have been made to use hand detectors with pose estimators to extract hand key points and learn to recognize sign language via Neural Networks, but none of them outperforms RGB-based methods. To this end, we propose a novel Skeleton Aware Multi-modal SLR framework (SAM-SLR) to take advantage of multi-modal information towards a higher recognition rate. Specifically, we propose a Sign Language Graph Convolution Network (SL-GCN) to model the embedded dynamics and a novel Separable Spatial-Temporal Convolution Network (SSTCN) to exploit skeleton features. RGB and depth modalities are also incorporated and assembled into our framework to provide global information that is complementary to the skeleton-based methods SL-GCN and SSTCN. As a result, SAM-SLR achieves the highest performance in both RGB (98.42\%) and RGB-D (98.53\%) tracks in 2021 Looking at People Large Scale Signer Independent Isolated SLR Challenge. Our code is available at https://github.com/jackyjsy/CVPR21Chal-SLR

Can Qin, Lichen Wang, Qianqian Ma et al.

Semi-supervised domain adaptation (SSDA) is quite a challenging problem requiring methods to overcome both 1) overfitting towards poorly annotated data and 2) distribution shift across domains. Unfortunately, a simple combination of domain adaptation (DA) and semi-supervised learning (SSL) methods often fail to address such two objects because of training data bias towards labeled samples. In this paper, we introduce an adaptive structure learning method to regularize the cooperation of SSL and DA. Inspired by the multi-views learning, our proposed framework is composed of a shared feature encoder network and two classifier networks, trained for contradictory purposes. Among them, one of the classifiers is applied to group target features to improve intra-class density, enlarging the gap of categorical clusters for robust representation learning. Meanwhile, the other classifier, serviced as a regularizer, attempts to scatter the source features to enhance the smoothness of the decision boundary. The iterations of target clustering and source expansion make the target features being well-enclosed inside the dilated boundary of the corresponding source points. For the joint address of cross-domain features alignment and partially labeled data learning, we apply the maximum mean discrepancy (MMD) distance minimization and self-training (ST) to project the contradictory structures into a shared view to make the reliable final decision. The experimental results over the standard SSDA benchmarks, including DomainNet and Office-home, demonstrate both the accuracy and robustness of our method over the state-of-the-art approaches.

Jiahua Dong, Yang Cong, Gan Sun et al.

3D object classification has attracted appealing attentions in academic researches and industrial applications. However, most existing methods need to access the training data of past 3D object classes when facing the common real-world scenario: new classes of 3D objects arrive in a sequence. Moreover, the performance of advanced approaches degrades dramatically for past learned classes (i.e., catastrophic forgetting), due to the irregular and redundant geometric structures of 3D point cloud data. To address these challenges, we propose a new Incremental 3D Object Learning (i.e., I3DOL) model, which is the first exploration to learn new classes of 3D object continually. Specifically, an adaptive-geometric centroid module is designed to construct discriminative local geometric structures, which can better characterize the irregular point cloud representation for 3D object. Afterwards, to prevent the catastrophic forgetting brought by redundant geometric information, a geometric-aware attention mechanism is developed to quantify the contributions of local geometric structures, and explore unique 3D geometric characteristics with high contributions for classes incremental learning. Meanwhile, a score fairness compensation strategy is proposed to further alleviate the catastrophic forgetting caused by unbalanced data between past and new classes of 3D object, by compensating biased prediction for new classes in the validation phase. Experiments on 3D representative datasets validate the superiority of our I3DOL framework.

Denghui Zhang, Junming Liu, Hengshu Zhu et al.

Job Title Benchmarking (JTB) aims at matching job titles with similar expertise levels across various companies. JTB could provide precise guidance and considerable convenience for both talent recruitment and job seekers for position and salary calibration/prediction. Traditional JTB approaches mainly rely on manual market surveys, which is expensive and labor-intensive. Recently, the rapid development of Online Professional Graph has accumulated a large number of talent career records, which provides a promising trend for data-driven solutions. However, it is still a challenging task since (1) the job title and job transition (job-hopping) data is messy which contains a lot of subjective and non-standard naming conventions for the same position (e.g., Programmer, Software Development Engineer, SDE, Implementation Engineer), (2) there is a large amount of missing title/transition information, and (3) one talent only seeks limited numbers of jobs which brings the incompleteness and randomness modeling job transition patterns. To overcome these challenges, we aggregate all the records to construct a large-scale Job Title Benchmarking Graph (Job-Graph), where nodes denote job titles affiliated with specific companies and links denote the correlations between jobs. We reformulate the JTB as the task of link prediction over the Job-Graph that matched job titles should have links. Along this line, we propose a collective multi-view representation learning method (Job2Vec) by examining the Job-Graph jointly in (1) graph topology view, (2)semantic view, (3) job transition balance view, and (4) job transition duration view. We fuse the multi-view representations in the encode-decode paradigm to obtain a unified optimal representation for the task of link prediction. Finally, we conduct extensive experiments to validate the effectiveness of our proposed method.

Yue Bai, Zhiqiang Tao, Lichen Wang et al.

Multi-view action recognition (MVAR) leverages complementary temporal information from different views to improve the learning performance. Obtaining informative view-specific representation plays an essential role in MVAR. Attention has been widely adopted as an effective strategy for discovering discriminative cues underlying temporal data. However, most existing MVAR methods only utilize attention to extract representation for each view individually, ignoring the potential to dig latent patterns based on mutual-support information in attention space. To this end, we propose a collaborative attention mechanism (CAM) for solving the MVAR problem in this paper. The proposed CAM detects the attention differences among multi-view, and adaptively integrates frame-level information to benefit each other. Specifically, we extend the long short-term memory (LSTM) to a Mutual-Aid RNN (MAR) to achieve the multi-view collaboration process. CAM takes advantages of view-specific attention pattern to guide another view and discover potential information which is hard to be explored by itself. It paves a novel way to leverage attention information and enhances the multi-view representation learning. Extensive experiments on four action datasets illustrate the proposed CAM achieves better results for each view and also boosts multi-view performance.

Can Qin, Lichen Wang, Qianqian Ma et al.

Current adversarial adaptation methods attempt to align the cross-domain features, whereas two challenges remain unsolved: 1) the conditional distribution mismatch and 2) the bias of the decision boundary towards the source domain. To solve these challenges, we propose a novel framework for semi-supervised domain adaptation by unifying the learning of opposite structures (UODA). UODA consists of a generator and two classifiers (i.e., the source-scattering classifier and the target-clustering classifier), which are trained for contradictory purposes. The target-clustering classifier attempts to cluster the target features to improve intra-class density and enlarge inter-class divergence. Meanwhile, the source-scattering classifier is designed to scatter the source features to enhance the decision boundary's smoothness. Through the alternation of source-feature expansion and target-feature clustering procedures, the target features are well-enclosed within the dilated boundary of the corresponding source features. This strategy can make the cross-domain features to be precisely aligned against the source bias simultaneously. Moreover, to overcome the model collapse through training, we progressively update the measurement of feature's distance and their representation via an adversarial training paradigm. Extensive experiments on the benchmarks of DomainNet and Office-home datasets demonstrate the superiority of our approach over the state-of-the-art methods.

Yue Bai, Lichen Wang, Zhiqiang Tao et al.

Multi-view time series classification (MVTSC) aims to improve the performance by fusing the distinctive temporal information from multiple views. Existing methods mainly focus on fusing multi-view information at an early stage, e.g., by learning a common feature subspace among multiple views. However, these early fusion methods may not fully exploit the unique temporal patterns of each view in complicated time series. Moreover, the label correlations of multiple views, which are critical to boost-ing, are usually under-explored for the MVTSC problem. To address the aforementioned issues, we propose a Correlative Channel-Aware Fusion (C2AF) network. First, C2AF extracts comprehensive and robust temporal patterns by a two-stream structured encoder for each view, and captures the intra-view and inter-view label correlations with a graph-based correlation matrix. Second, a channel-aware learnable fusion mechanism is implemented through convolutional neural networks to further explore the global correlative patterns. These two steps are trained end-to-end in the proposed C2AF network. Extensive experimental results on three real-world datasets demonstrate the superiority of our approach over the state-of-the-art methods. A detailed ablation study is also provided to show the effectiveness of each model component.

Can Qin, Haoxuan You, Lichen Wang et al.

Domain Adaptation (DA) approaches achieved significant improvements in a wide range of machine learning and computer vision tasks (i.e., classification, detection, and segmentation). However, as far as we are aware, there are few methods yet to achieve domain adaptation directly on 3D point cloud data. The unique challenge of point cloud data lies in its abundant spatial geometric information, and the semantics of the whole object is contributed by including regional geometric structures. Specifically, most general-purpose DA methods that struggle for global feature alignment and ignore local geometric information are not suitable for 3D domain alignment. In this paper, we propose a novel 3D Domain Adaptation Network for point cloud data (PointDAN). PointDAN jointly aligns the global and local features in multi-level. For local alignment, we propose Self-Adaptive (SA) node module with an adjusted receptive field to model the discriminative local structures for aligning domains. To represent hierarchically scaled features, node-attention module is further introduced to weight the relationship of SA nodes across objects and domains. For global alignment, an adversarial-training strategy is employed to learn and align global features across domains. Since there is no common evaluation benchmark for 3D point cloud DA scenario, we build a general benchmark (i.e., PointDA-10) extracted from three popular 3D object/scene datasets (i.e., ModelNet, ShapeNet and ScanNet) for cross-domain 3D objects classification fashion. Extensive experiments on PointDA-10 illustrate the superiority of our model over the state-of-the-art general-purpose DA methods.

Lichen Wang, Bin Sun, Joseph Robinson et al.

Multi-modal human action analysis is a critical and attractive research topic. However, the majority of the existing datasets only provide visual modalities (i.e., RGB, depth and skeleton). To make up this, we introduce a new, large-scale EV-Action dataset in this work, which consists of RGB, depth, electromyography (EMG), and two skeleton modalities. Compared with the conventional datasets, EV-Action dataset has two major improvements: (1) we deploy a motion capturing system to obtain high quality skeleton modality, which provides more comprehensive motion information including skeleton, trajectory, acceleration with higher accuracy, sampling frequency, and more skeleton markers. (2) we introduce an EMG modality which is usually used as an effective indicator in the biomechanics area, also it has yet to be well explored in motion related research. To the best of our knowledge, this is the first action dataset with EMG modality. The details of EV-Action dataset are clarified, meanwhile, a simple yet effective framework for EMG-based action recognition is proposed. Moreover, state-of-the-art baselines are applied to evaluate the effectiveness of all the modalities. The obtained result clearly shows the validity of EMG modality in human action analysis tasks. We hope this dataset can make significant contributions to human motion analysis, computer vision, machine learning, biomechanics, and other interdisciplinary fields.

Lichen Wang, Jiaxiang Wu, Shao-Lun Huang et al.

One primary focus in multimodal feature extraction is to find the representations of individual modalities that are maximally correlated. As a well-known measure of dependence, the Hirschfeld-Gebelein-Rényi (HGR) maximal correlation becomes an appealing objective because of its operational meaning and desirable properties. However, the strict whitening constraints formalized in the HGR maximal correlation limit its application. To address this problem, this paper proposes Soft-HGR, a novel framework to extract informative features from multiple data modalities. Specifically, our framework prevents the "hard" whitening constraints, while simultaneously preserving the same feature geometry as in the HGR maximal correlation. The objective of Soft-HGR is straightforward, only involving two inner products, which guarantees the efficiency and stability in optimization. We further generalize the framework to handle more than two modalities and missing modalities. When labels are partially available, we enhance the discriminative power of the feature representations by making a semi-supervised adaptation. Empirical evaluation implies that our approach learns more informative feature mappings and is more efficient to optimize.

Yulun Zhang, Kunpeng Li, Kai Li et al.

Convolutional neural network (CNN) depth is of crucial importance for image super-resolution (SR). However, we observe that deeper networks for image SR are more difficult to train. The low-resolution inputs and features contain abundant low-frequency information, which is treated equally across channels, hence hindering the representational ability of CNNs. To solve these problems, we propose the very deep residual channel attention networks (RCAN). Specifically, we propose a residual in residual (RIR) structure to form very deep network, which consists of several residual groups with long skip connections. Each residual group contains some residual blocks with short skip connections. Meanwhile, RIR allows abundant low-frequency information to be bypassed through multiple skip connections, making the main network focus on learning high-frequency information. Furthermore, we propose a channel attention mechanism to adaptively rescale channel-wise features by considering interdependencies among channels. Extensive experiments show that our RCAN achieves better accuracy and visual improvements against state-of-the-art methods.