Deep learning has achieved great success in video recognition, yet still struggles to recognize novel actions when faced with only a few examples. To tackle this challenge, few-shot action recognition methods have been proposed to transfer knowledge from a source dataset to a novel target dataset with only one or a few labeled videos. However, existing methods mainly focus on modeling the temporal relations between the query and support videos while ignoring the spatial relations. In this paper, we find that the spatial misalignment between objects also occurs in videos, notably more common than the temporal inconsistency. We are thus motivated to investigate the importance of spatial relations and propose a more accurate few-shot action recognition method that leverages both spatial and temporal information. Particularly, a novel Spatial Alignment Cross Transformer (SA-CT) which learns to re-adjust the spatial relations and incorporates the temporal information is contributed. Experiments reveal that, even without using any temporal information, the performance of SA-CT is comparable to temporal based methods on 3/4 benchmarks. To further incorporate the temporal information, we propose a simple yet effective Temporal Mixer module. The Temporal Mixer enhances the video representation and improves the performance of the full SA-CT model, achieving very competitive results. In this work, we also exploit large-scale pretrained models for few-shot action recognition, providing useful insights for this research direction.

Robotic ultrasound scanning has excellent potential to reduce physician workload, obtain higher-quality imaging, and reduce costs. However, the traditional admittance control strategy for robotics cannot meet the high-precision force control requirements for robots, which are critical for improving image quality and ensuring patient safety. In this study, an integral adaptive admittance control strategy is proposed for contact force control between an ultrasound probe and human skin to enhance the accuracy of force tracking. First, a robotic ultrasound scanning system is proposed, and the system’s overall workflow is introduced. Second, an adaptive admittance control strategy is designed to estimate the uncertain environmental information online, and the estimated parameters are used to modify the reference trajectory. On the basis of ensuring the stability of the system, an integral controller is then introduced to improve the steady-state response. Subsequently, the stability of the proposed strategy is analysed. In addition, a gravity compensation process is proposed to obtain the actual contact force. Finally, through a simulation analysis, the effectiveness of the strategy is discussed. Simultaneously, a series of experiments are carried out on the robotic ultrasound scanning system, and the results show that the strategy can successfully maintain a constant contact force under soft uncertain environments, which effectively improves the efficiency of scanning.

Aerial image object detection remains rather challenging, due to the small object gathering and confusion of inter-class similarities and intra-class diversity. Confronting such challenges, we propose a two-stage framework, ‘Zoom&Reasoning Det’, which performs detection in a foreground highlight manner and leverages contextual relations to assist detection. In the coarse foreground zoom stage, different from earlier works that divide original images into patches and perform detection on each patch separately, we design Foreground Zoom Strategy (FZS), which zooms foreground dense regions from a coarse detector and packs them into one image. In the fine reasoning detect stage, motivated by a human visual mechanism that can achieve correct recognition by reasoning through context, we present Visual-Semantic Reasoning Network (VSRNet), consisting of Visual Reasoning Graph (VRG) and Semantic Reasoning Graph (SRG), simultaneously considering local visual and global semantic contextual relational information for each instance. Each instance feature representation is further refined by aggregating the outputs of VSRNet. Comprehensive experiments conducted on two challenging aerial image datasets, VisDrone and UAVDT, demonstrate the advantage of our method over the state-of-the-art.

Data-Free Knowledge Distillation (DFKD) is a novel task that aims to train high-performance student models using only the pre-trained teacher network without original training data. Most of the existing DFKD methods rely heavily on additional generation modules to synthesize the substitution data resulting in high computational costs and ignoring the massive amounts of easily accessible, low-cost, unlabeled open-world data. Meanwhile, existing methods ignore the domain shift issue between the substitution data and the original data, resulting in knowledge from teachers not always trustworthy and structured knowledge from data becoming a crucial supplement. To tackle the issue, we propose a novel Open-world Data Sampling Distillation (ODSD) method for the DFKD task without the redundant generation process. First, we try to sample open-world data close to the original data's distribution by an adaptive sampling module and introduce a low-noise representation to alleviate the domain shift issue. Then, we build structured relationships of multiple data examples to exploit data knowledge through the student model itself and the teacher's structured representation. Extensive experiments on CIFAR-10, CIFAR-100, NYUv2, and ImageNet show that our ODSD method achieves state-of-the-art performance with lower FLOPs and parameters. Especially, we improve 1.50%-9.59% accuracy on the ImageNet dataset and avoid training the separate generator for each class.