Recently, 2D convolution has been found unqualified in sound event detection (SED). It enforces translation equivariance on sound events along frequency axis, which is not a shift-invariant dimension. To address this issue, dynamic convolution is used to model the frequency dependency of sound events. In this paper, we proposed the first full-dynamic method named \emph{full-frequency dynamic convolution} (FFDConv). FFDConv generates frequency kernels for every frequency band, which is designed directly in the structure for frequency-dependent modeling. It physically furnished 2D convolution with the capability of frequency-dependent modeling. FFDConv outperforms not only the baseline by 6.6\% in DESED real validation dataset in terms of PSDS1, but outperforms the other full-dynamic methods. In addition, by visualizing features of sound events, we observed that FFDConv could effectively extract coherent features in specific frequency bands, consistent with the vocal continuity of sound events. This proves that FFDConv has great frequency-dependent perception ability.
Skeleton-based action recognition is a central task of human-computer interaction. However, most of the previous methods suffer from two issues: (i) semantic ambiguity arising from spatiotemporal information mixture; and (ii) overlooking the explicit exploitation of the latent data distributions (i.e., the intra-class variations and inter-class relations), thereby leading to local optimum solutions of the skeleton encoders. To mitigate this, we propose a spatial-temporal decoupling contrastive learning (STD-CL) framework to obtain discriminative and semantically distinct representations from the sequences, which can be incorporated into almost all previous skeleton encoders and have no impact on the skeleton encoders when testing. Specifically, we decouple the global features into spatial-specific and temporal-specific features to reduce the spatiotemporal coupling of features. Furthermore, to explicitly exploit the latent data distributions, we employ the attentive features to contrastive learning, which models the cross-sequence semantic relations by pulling together the features from the positive pairs and pushing away the negative pairs. Extensive experiments show that STD-CL with four various skeleton encoders (HCN, 2S-AGCN, CTR-GCN, and Hyperformer) achieves solid improvement on NTU60, NTU120, and NW-UCLA benchmarks. The code will be released.
Human Pose Estimation (HPE) plays a crucial role in computer vision applications. However, it is difficult to deploy state-of-the-art models on resouce-limited devices due to the high computational costs of the networks. In this work, a binary human pose estimator named BiHRNet(Binary HRNet) is proposed, whose weights and activations are expressed as $\pm$1. BiHRNet retains the keypoint extraction ability of HRNet, while using fewer computing resources by adapting binary neural network (BNN). In order to reduce the accuracy drop caused by network binarization, two categories of techniques are proposed in this work. For optimizing the training process for binary pose estimator, we propose a new loss function combining KL divergence loss with AWing loss, which makes the binary network obtain more comprehensive output distribution from its real-valued counterpart to reduce information loss caused by binarization. For designing more binarization-friendly structures, we propose a new information reconstruction bottleneck called IR Bottleneck to retain more information in the initial stage of the network. In addition, we also propose a multi-scale basic block called MS-Block for information retention. Our work has less computation cost with few precision drop. Experimental results demonstrate that BiHRNet achieves a PCKh of 87.9 on the MPII dataset, which outperforms all binary pose estimation networks. On the challenging of COCO dataset, the proposed method enables the binary neural network to achieve 70.8 mAP, which is better than most tested lightweight full-precision networks.
Graph convolution networks (GCNs) have achieved remarkable performance in skeleton-based action recognition. However, existing previous GCN-based methods have relied excessively on elaborate human body priors and constructed complex feature aggregation mechanisms, which limits the generalizability of networks. To solve these problems, we propose a novel Spatial Topology Gating Unit (STGU), which is an MLP-based variant without extra priors, to capture the co-occurrence topology features that encode the spatial dependency across all joints. In STGU, to model the sample-specific and completely independent point-wise topology attention, a new gate-based feature interaction mechanism is introduced to activate the features point-to-point by the attention map generated from the input. Based on the STGU, in this work, we propose the first topology-aware MLP-based model, Ta-MLP, for skeleton-based action recognition. In comparison with existing previous methods on three large-scale datasets, Ta-MLP achieves competitive performance. In addition, Ta-MLP reduces the parameters by up to 62.5% with favorable results. Compared with previous state-of-the-art (SOAT) approaches, Ta-MLP pushes the frontier of real-time action recognition. The code will be available at https://github.com/BUPTSJZhang/Ta-MLP.
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.
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.
Audio-visual event localization has attracted much attention in recent years. Most existing methods are often limited to independently encoding and classifying each video segment separated from the full video (which can be regarded as the segment-level representations of events). However, they ignore the semantic consistency of the event within the same full video (which can be considered as the video-level representations of events). In contrast to existing methods, we propose a novel video-level semantic consistency guidance network for the AVE task. Specifically, we propose an event semantic consistency modeling (ESCM) module to explore the video-level semantic consistency of events. It consists of two components: cross-modal event representation extractor (CERE) and intra-modal semantic consistency enhancer (ISCE). CERE is proposed to obtain the event semantic representation at the video level including, audio and visual modules. Furthermore, ISCE takes the video-level event semantic representation as the prior knowledge to guide the model to focus on the semantic continuity of the event within each modality. Moreover, we propose a new negative pair filter loss to encourage the network to filter out the irrelevant segment pairs and a new smooth loss to further increase the gap between different categories of events under the weakly-supervised setting. We perform extensive experiments on the public AVE dataset and outperform the state-of-the-art methods in both fully and weakly supervised settings, thus verifying the effectiveness of our method.