Deep learning models have been widely used for anomaly detection in surveillance videos. Typical models are equipped with the capability to reconstruct normal videos and evaluate the reconstruction errors on anomalous videos to indicate the extent of abnormalities. However, existing approaches suffer from two disadvantages. Firstly, they can only encode the movements of each identity independently, without considering the interactions among identities which may also indicate anomalies. Secondly, they leverage inflexible models whose structures are fixed under different scenes, this configuration disables the understanding of scenes. In this paper, we propose a Hierarchical Spatio-Temporal Graph Convolutional Neural Network (HSTGCNN) to address these problems, the HSTGCNN is composed of multiple branches that correspond to different levels of graph representations. High-level graph representations encode the trajectories of people and the interactions among multiple identities while low-level graph representations encode the local body postures of each person. Furthermore, we propose to weightedly combine multiple branches that are better at different scenes. An improvement over single-level graph representations is achieved in this way. An understanding of scenes is achieved and serves anomaly detection. High-level graph representations are assigned higher weights to encode moving speed and directions of people in low-resolution videos while low-level graph representations are assigned higher weights to encode human skeletons in high-resolution videos. Experimental results show that the proposed HSTGCNN significantly outperforms current state-of-the-art models on four benchmark datasets (UCSD Pedestrian, ShanghaiTech, CUHK Avenue and IITB-Corridor) by using much less learnable parameters.

Mid-to-high altitude Unmanned Aerial Vehicle (UAV) imagery can provide important remote sensing information between satellite and low altitude platforms, and vehicle detection in mid-to-high altitude UAV images plays a crucial role in land monitoring and disaster relief. However, the high background complexity of images and limited pixels of objects challenge the performance of tiny vehicle detection. Traditional methods suffer from poor adaptation ability to complex backgrounds, while deep neural networks (DNNs) have inherent defects in feature extraction of tiny objects with finite pixels. To address the issue above, this paper puts forward a vehicle detection method combining the DNNs-based and traditional methods for mid-to-high altitude UAV images. We first employ the deep segmentation network to exploit the co-occurrence of the road and vehicles, then detect tiny vehicles based on visual attention mechanism with spatial-temporal constraint information. Experimental results show that the proposed method achieves effective detection of tiny vehicles in complex backgrounds. In addition, ablation experiments are performed to inspect the effectiveness of each component, and comparative experiments on tinier objects are carried out to prove the superior generalization performance of our method in detecting vehicles with a limited size of 5 × 5 pixels or less.

In this paper, a deep learning model with an optimal capacity is proposed to improve the performance of person part segmentation. Previous efforts in optimizing the capacity of a CNN model suffer from a lack of large datasets as well as the over-dependence on a single-modality CNN which is not effective in learning. We make several efforts in addressing these problems. Firstly, other datasets are utilized to train a CNN module for pre-processing image data and a segmentation performance improvement is achieved without a time-consuming annotation process. Secondly, we propose a novel way of integrating two complementary modules to enrich the feature representations for more reliable inferences. Thirdly, the factors to determine the capacity of a CNN model are studied and two novel methods are proposed to adjust (optimize) the capacity of a CNN to match it to the complexity of a task. The over-fitting and under-fitting problems are eased by using our methods. Experimental results show that our model outperforms the state-of-the-art deep learning models with a better generalization ability and a lower computational complexity.

Thyroid nodule segmentation in ultrasound images is crucial for accurate diagnosis and treatment planning. However, existing methods struggle with segmentation accuracy, interpretability, and generalization. This letter proposes CLIP-TNseg, a novel framework that integrates a multimodal large model with a neural network architecture to address these challenges. We innovatively divide visual features into coarse-grained and fine-grained components, leveraging textual integration with coarse-grained features for enhanced semantic understanding. Specifically, the Coarse-grained Branch extracts high-level semantic features from a frozen CLIP model, while the Fine-grained Branch refines spatial details using U-Net-style residual blocks. Extensive experiments on the newly collected PKTN dataset and other public datasets demonstrate the competitive performance of CLIP-TNseg. Additional ablation experiments confirm the critical contribution of textual inputs, particularly highlighting the effectiveness of our carefully designed textual prompts compared to fixed or absent textual information. Our code and the original dataset are available at https://github.com/jayxjsun/CLIP-TNseg.

In this paper, we propose a novel framework for multi-person pose estimation and tracking on challenging scenarios. In view of occlusions and motion blurs which hinder the performance of pose tracking, we proposed to model humans as graphs and perform pose estimation and tracking by concentrating on the visible parts of human bodies which are informative about complete skeletons under incomplete observations. Specifically, the proposed framework involves three parts: (i) A Sparse Key-point Flow Estimating Module (SKFEM) and a Hierarchical Graph Distance Minimizing Module (HGMM) for estimating pixel-level and human-level motion, respectively; (ii) Pixel-level appearance consistency and human-level structural consistency are combined in measuring the visibility scores of body joints. The scores guide the pose estimator to predict complete skeletons by observing high-visibility parts, under the assumption that visible and invisible parts are inherently correlated in human part graphs. The pose estimator is iteratively fine-tuned to achieve this capability; (iii) Multiple historical frames are combined to benefit tracking which is implemented using HGMM. The proposed approach not only achieves state-of-the-art performance on PoseTrack datasets but also contributes to significant improvements in other tasks such as human-related anomaly detection.