Human motion prediction has achieved a brilliant performance with the help of CNNs, which facilitates human-machine cooperation. However, currently, there is no work evaluating the potential risk in human motion prediction when facing adversarial attacks, which may cause danger in real applications. The adversarial attack will face two problems against human motion prediction: 1. For naturalness, pose data is highly related to the physical dynamics of human skeletons where Lp norm constraints cannot constrain the adversarial example well; 2. Unlike the pixel value in images, pose data is diverse at scale because of the different acquisition equipment and the data processing, which makes it hard to set fixed parameters to perform attacks. To solve the problems above, we propose a new adversarial attack method that perturbs the input human motion sequence by maximizing the prediction error with physical constraints. Specifically, we introduce a novel adaptable scheme that facilitates the attack to suit the scale of the target pose and two physical constraints to enhance the imperceptibility of the adversarial example. The evaluating experiments on three datasets show that the prediction errors of all target models are enlarged significantly, which means current convolution-based human motion prediction models can be easily disturbed under the proposed attack. The quantitative analysis shows that prior knowledge and semantic information modeling can be the key to the adversarial robustness of human motion predictors. The qualitative results indicate that the adversarial sample is hard to be noticed when compared frame by frame but is relatively easy to be detected when the sample is animated.
Human motion prediction has achieved a brilliant performance with the help of CNNs, which facilitates human-machine cooperation. However, currently, there is no work evaluating the potential risk in human motion prediction when facing adversarial attacks, which may cause danger in real applications. The adversarial attack will face two problems against human motion prediction: 1. For naturalness, pose data is highly related to the physical dynamics of human skeletons where Lp norm constraints cannot constrain the adversarial example well; 2. Unlike the pixel value in images, pose data is diverse at scale because of the different acquisition equipment and the data processing, which makes it hard to set fixed parameters to perform attacks. To solve the problems above, we propose a new adversarial attack method that perturbs the input human motion sequence by maximizing the prediction error with physical constraints. Specifically, we introduce a novel adaptable scheme that facilitates the attack to suit the scale of the target pose and two physical constraints to enhance the imperceptibility of the adversarial example. The evaluating experiments on three datasets show that the prediction errors of all target models are enlarged significantly, which means current convolution-based human motion prediction models can be easily disturbed under the proposed attack. The quantitative analysis shows that prior knowledge and semantic information modeling can be the key to the adversarial robustness of human motion predictors. The qualitative results indicate that the adversarial sample is hard to be noticed when compared frame by frame but is relatively easy to be detected when the sample is animated.
Audio-visual question answering (AVQA) is a challenging task that requires multistep spatio-temporal reasoning over multimodal contexts. To achieve scene understanding ability similar to humans, the AVQA task presents specific challenges, including effectively fusing audio and visual information and capturing question-relevant audio-visual features while maintaining temporal synchronization. This paper proposes a Target-aware Joint Spatio-Temporal Grounding Network for AVQA to address these challenges. The proposed approach has two main components: the Target-aware Spatial Grounding module, the Tri-modal consistency loss and corresponding Joint audio-visual temporal grounding module. The Target-aware module enables the model to focus on audio-visual cues relevant to the inquiry subject by exploiting the explicit semantics of text modality. The Tri-modal consistency loss facilitates the interaction between audio and video during question-aware temporal grounding and incorporates fusion within a simpler single-stream architecture. Experimental results on the MUSIC-AVQA dataset demonstrate the effectiveness and superiority of the proposed method over existing state-of-the-art methods. Our code will be availiable soon.
In the perception task of autonomous driving, multi-modal methods have become a trend due to the complementary characteristics of LiDAR point clouds and image data. However, the performance of previous methods is usually limited by the sparsity of the point cloud or the noise problem caused by the misalignment between LiDAR and the camera. To solve these two problems, we present a new concept, Voxel Region (VR), which is obtained by projecting the sparse local point clouds in each voxel dynamically. And we propose a novel fusion method, named Sparse-to-Dense Voxel Region Fusion (SDVRF). Specifically, more pixels of the image feature map inside the VR are gathered to supplement the voxel feature extracted from sparse points and achieve denser fusion. Meanwhile, different from prior methods, which project the size-fixed grids, our strategy of generating dynamic regions achieves better alignment and avoids introducing too much background noise. Furthermore, we propose a multi-scale fusion framework to extract more contextual information and capture the features of objects of different sizes. Experiments on the KITTI dataset show that our method improves the performance of different baselines, especially on classes of small size, including Pedestrian and Cyclist.
The task of Group Activity Recognition (GAR) aims to predict the activity category of the group by learning the actor spatial-temporal interaction relation in the group. Therefore, an effective actor relation learning method is crucial for the GAR task. The previous works mainly learn the interaction relation by the well-designed GCNs or Transformers. For example, to infer the actor interaction relation, GCNs need a learnable adjacency, and Transformers need to calculate the self-attention. Although the above methods can model the interaction relation effectively, they also increase the complexity of the model (the number of parameters and computations). In this paper, we design a novel MLP-based method for Actor Interaction Relation learning (MLP-AIR) in GAR. Compared with GCNs and Transformers, our method has a competitive but conceptually and technically simple alternative, significantly reducing the complexity. Specifically, MLP-AIR includes three sub-modules: MLP-based Spatial relation modeling module (MLP-S), MLP-based Temporal relation modeling module (MLP-T), and MLP-based Relation refining module (MLP-R). MLP-S is used to model the spatial relation between different actors in each frame. MLP-T is used to model the temporal relation between different frames for each actor. MLP-R is used further to refine the relation between different dimensions of relation features to improve the feature's expression ability. To evaluate the MLP-AIR, we conduct extensive experiments on two widely used benchmarks, including the Volleyball and Collective Activity datasets. Experimental results demonstrate that MLP-AIR can get competitive results but with low complexity.
In this paper, we concern on the bottom-up paradigm in multi-person pose estimation (MPPE). Most previous bottom-up methods try to consider the relation of instances to identify different body parts during the post processing, while ignoring to model the relation among instances or environment in the feature learning process. In addition, most existing works adopt the operations of upsampling and downsampling. During the sampling process, there will be a problem of misalignment with the source features, resulting in deviations in the keypoint features learned by the model. To overcome the above limitations, we propose a convolutional neural network for bottom-up human pose estimation. It invovles two basic modules: (i) Global Relation Modeling (GRM) module globally learns relation (e.g., environment context, instance interactive information) among region of image by fusing multiple stages features in the feature learning process. It combines with the spatial-channel attention mechanism, which focuses on achieving adaptability in spatial and channel dimensions. (ii) Multi-branch Feature Align (MFA) module aggregates features from multiple branches to align fused feature and obtain refined local keypoint representation. Our model has the ability to focus on different granularity from local to global regions, which significantly boosts the performance of the multi-person pose estimation. Our results on the COCO and CrowdPose datasets demonstrate that it is an efficient framework for multi-person pose estimation.
This technical report describes our first-place solution to the pose estimation challenge at ECCV 2022 Visual Perception for Navigation in Human Environments Workshop. In this challenge, we aim to estimate human poses from in-the-wild stitched panoramic images. Our method is built based on Faster R-CNN for human detection, and HRNet for human pose estimation. We describe technical details for the JRDB-Pose dataset, together with some experimental results. In the competition, we achieved 0.303 $\text{OSPA}_{\text{IOU}}$ and 64.047\% $\text{AP}_{\text{0.5}}$ on the test set of JRDB-Pose.
This work introduces a new task of instance-incremental scene graph generation: Given an empty room of the point cloud, representing it as a graph and automatically increasing novel instances. A graph denoting the object layout of the scene is finally generated. It is an important task since it helps to guide the insertion of novel 3D objects into a real-world scene in vision-based applications like augmented reality. It is also challenging because the complexity of the real-world point cloud brings difficulties in learning object layout experiences from the observation data (non-empty rooms with labeled semantics). We model this task as a conditional generation problem and propose a 3D autoregressive framework based on normalizing flows (3D-ANF) to address it. We first represent the point cloud as a graph by extracting the containing label semantics and contextual relationships. Next, a model based on normalizing flows is introduced to map the conditional generation of graphic elements into the Gaussian process. The mapping is invertible. Thus, the real-world experiences represented in the observation data can be modeled in the training phase, and novel instances can be sequentially generated based on the Gaussian process in the testing phase. We implement this new task on the dataset of 3D point-based scenes (3DSSG and 3RScan) and evaluate the performance of our method. Experiments show that our method generates reliable novel graphs from the real-world point cloud and achieves state-of-the-art performance on the benchmark dataset.
In this paper, we develop an efficient multi-scale network to predict action classes in partial videos in an end-to-end manner. Unlike most existing methods with offline feature generation, our method directly takes frames as input and further models motion evolution on two different temporal scales.Therefore, we solve the complexity problems of the two stages of modeling and the problem of insufficient temporal and spatial information of a single scale. Our proposed End-to-End MultiScale Network (E2EMSNet) is composed of two scales which are named segment scale and observed global scale. The segment scale leverages temporal difference over consecutive frames for finer motion patterns by supplying 2D convolutions. For observed global scale, a Long Short-Term Memory (LSTM) is incorporated to capture motion features of observed frames. Our model provides a simple and efficient modeling framework with a small computational cost. Our E2EMSNet is evaluated on three challenging datasets: BIT, HMDB51, and UCF101. The extensive experiments demonstrate the effectiveness of our method for action prediction in videos.