Understanding anomalous human behaviors at a fine-grained level remains a major challenge in complex scenarios. Existing video anomaly understanding (VAU) methods often rely on coarse frame-level cues or overlook structured modeling of individual actions, limiting their capacity for reasoning about human interactions and accountability. To address these challenges, we propose TargetVAU, a multimodal anomaly-aware reasoning framework designed for individual-level anomaly recognition and explanation. TargetVAU first extracts both global-level and human-centric visual features using a frozen Vision Transformer (ViT) encoder. An Anomaly-focused Temporal Sampler is then employed to select behaviorally informative frames via a density-aware strategy guided by predicted anomaly scores. A Spatio-Temporal Interaction Graph is constructed to explicitly model interactions among individuals across time and space. These structured representations are fused with prompt embeddings via a frozen Q-Former to form a unified semantic representation. Finally, a large language model fine-tuned with low-rank adaptation (LoRA) performs instruction-guided reasoning to identify anomalous individuals and generate natural language explanations. Extensive experiments on UCCD and HIVAU-70K demonstrate that TargetVAU significantly outperforms existing methods in both accuracy and interpretability, advancing the state of individual-level anomaly understanding in surveillance videos.

Compositional Zero-Shot Learning (CZSL) aims to recognize unseen compositional concepts composed of seen single concepts. One of the problems of CZSL is to model attributes interacting with objects and objects interacting with attributes. In this work, we focus on this problem and propose Dual-Stream Conditional Network (DSCNet) that learns dual-stream conditional concepts as a solution, where the conditional visual and semantic embeddings of attributes and objects are learned. First, we argue that the condition of the attribute or object is supposed to contain the recognized object and input image, or the recognized attribute and input image. Next, for each concept which can either be an attribute or object, in the semantic stream, we propose to encode the recognized object or attribute semantic features and the input image visual features as the encoded condition, which is then injected into all concept semantic embeddings by a semantic cross encoder to acquire conditional semantic embeddings. In the visual stream, the conditional attribute or object visual embeddings are acquired by injecting the semantic features of the recognized object or attribute into the mapped attribute or object visual features. Experimental results on CZSL benchmarks demonstrate the superiority of our proposed method.

Compositional Zero-Shot Learning (CZSL) aims to train models to recognize novel compositional concepts based on learned concepts such as attribute-object combinations. One of the challenges is to model attributes interacted with different objects, e.g., the attribute “wet” in “wet apple” and “wet cat” is different. As a solution, we provide analysis and argue that attributes are conditioned on the recognized object and input image and explore learning conditional attribute embeddings by a proposed attribute learning framework containing an attribute hyper learner and an attribute base learner. By encoding conditional attributes, our model enables to generate flexible attribute embeddings for generalization from seen to unseen compositions. Experiments on CZSL benchmarks, including the more challenging C-GQA dataset, demonstrate better performances compared with other state-of-the-art approaches and validate the importance of learning conditional attributes. Code‡1Gllee:https://gitee.com/wqshmzh/canet-czsl is available at https://github.com/wqshmzh/CANet-CZSL.

Abstract For region growing image segmentation, seed selection and image noise are two major concerns causing negative segmentation performance. This paper proposes a regional growth algorithm based on the Gaussian pyramid (GPRG), which automatically selects seed points and optimizes the growth path. To achieve automatic seed selection, Gaussian difference pyramid generated by the Gaussian pyramid is required. The growing seed of the salient target in an image is acquired by searching for extremums in each image of the Gaussian difference pyramid. For growing path optimization, edge changing direction is updated according to different Gaussian difference pyramid images with sizes from small to large. The edge of region growing is determined by the edge of the salient target in an image. Segmentation experiments show that this algorithm is able to automatically select seeds and accurately segment the salient target in an image with and without image noise. Performances in terms of segmentation accuracy (SA), mean intersection‐over‐union (mIoU) and E‐measure are superior compared with other methods.

This paper designs a robotic system for floor-tiling, which is aiming to replace the labor-intensive and repetitive tile-laying work. Firstly, the current manual tile paving process is analyzed; then according to the step of measuring and positioning of tiles in the manual process, the system framework of the robotic floor-tiling platform is designed; after that, the hardware and software are designed and the tile measuring and positioning algorithm is written to finish the robotic floor-tiling platform; finally, the platform is verified by experiments that the accuracy level can meet the requirements of tile installation well.

Modeling and Analysis of Real-Time and Embedded systems (MARTE) is a profile of United Modeling Language (UML), which provides support for specification, design and verification for Real-Time Embedded Systems (RTES). MARTE sequence diagram can deal with both discrete and dense time in which a clock can be either chronometric or logical. However it lacks the ability to describe the continuous behavior of a hybrid system. We propose a new method named Hybrid MARTE Sequence Diagram (HSD) to describe the communication between participants and the continuous evolution within the execution occurrence of a hybrid system. HSD combines the time model from MARTE and specification of the time-continuous behavior aspects from hybrid automata with MARTE sequence diagram. It improves the MARTE sequence diagram in that: the logical time and the chronometric time are unified. Besides, the description of continuous evolution of a hybrid system is provided. We firstly extend the basic MARTE elements to support both discrete and continuous aspects. Then we define the formal syntax and semantics of HSD based on hybrid transition system. Using this new method, we model an industrial application named Train Position Determination (TPD).