Zero-shot skeleton action recognition endeavors to classify novel action categories by transferring previously learned seen skeleton-semantic priors to unseen categories. However, current methods struggle to distinguish highly similar action categories, primarily due to the coarse-grained cross-modal alignment and non-discriminative representation space. To address these issues, we proposeSTAR++, a novel framework that aligns skeleton and semantics in a fine-grained and conditional manner. The key idea is to first establish region-level correspondences between body parts and semantic cues, and then utilize these local alignments to inform a global alignment process. This design is inspired by human visual cognition, which first attends to crucial local details before perceiving the broader scene. Concretely, we refine both skeleton and semantic representations with a dual-prompt attention mechanism driven by the structural decomposition of the human body and side information generated by a large language model (LLM). This encourages skeleton representations to be more compact within each class and semantic embeddings to be more separable across classes, which helps resolve ambiguity between highly similar actions and provides better interpretability of how unseen actions are perceived. Furthermore, we construct a region-aware holistic fusion module that aggregates these fine-grained features into a unified representation, yielding more discriminative holistic representations. Finally, the global alignment is conditioned on region-aware semantics feedback derived from fine-grained alignment, forming a conditional process that achieves more effective cross-modal alignment. Extensive experiments on four mainstream benchmarks demonstrate that our method achieves state-of-the-art performance in the zero-shot learning (ZSL) and generalized zero-shot learning (GZSL) settings.

Compositional Zero-Shot Learning (CZSL) aims to recognize novel state-object compositions by leveraging the shared knowledge of their primitive components. Despite considerable progress, effectively calibrating the bias between semantically similar multimodal representations, as well as generalizing pre-trained knowledge to novel compositional contexts, remains an enduring challenge. In this paper, our interest is to revisit the conditional transport (CT) theory and its homology to the visual-semantics interaction in CZSL and further, propose a novel Trisets Consistency Alignment framework (dubbed TsCA) that well-addresses these issues. Concretely, we utilize three distinct yet semantically homologous sets, i.e., patches, primitives, and compositions, to construct pairwise CT costs to minimize their semantic discrepancies. To further ensure the consistency transfer within these sets, we implement a cycle-consistency constraint that refines the learning by guaranteeing the feature consistency of the self-mapping during transport flow, regardless of modality. Moreover, we extend the CT plans to an open-world setting, which enables the model to effectively filter out unfeasible pairs, thereby speeding up the inference as well as increasing the accuracy. Extensive experiments are conducted to verify the effectiveness of the proposed method. The code is available at https://github.com/keepgoingjkg/TsCA.

Conditional dependency present one of the trickiest problems in Compositional Zero-Shot Learning, leading to significant property variations of the same state (object) across different objects (states). To address this problem, existing approaches often adopt either all-to-one or one-to-one representation paradigms. However, these extremes create an imbalance in the seesaw between transferability and discriminability, favoring one at the expense of the other. Comparatively, humans are adept at analogizing and reasoning in a hierarchical clustering manner, intuitively grouping categories with similar properties to form cohesive concepts. Motivated by this, we propose Homogeneous Group Representation Learning (HGRL), a new perspective formulates state (object) representation learning as multiple homogeneous sub-group representation learning. HGRL seeks to achieve a balance between semantic transferability and discriminability by adaptively discovering and aggregating categories with shared properties, learning distributed group centers that retain group-specific discriminative features. Our method integrates three core components designed to simultaneously enhance both the visual and prompt representation capabilities of the model. Extensive experiments on three benchmark datasets validate the effectiveness of our method. Code is available at https://github.com/zjrao/HGRL.

Recent advances in Generalized Zero-Shot Learning have demonstrated promising results by leveraging cross-modal attention mechanisms to model the nuanced relationships between semantic attributes and visual regions. However, we find that inherent attribute imbalance leads to significant attention disparities, i.e., those attributes with less sample weights often exhibit lower attention confidence and poorer localization accuracy. This attention illusion obviously leads to potential degraded or even counterproductive contributions to category determination. Conventional rebalancing approaches like resampling or reweighting are ineffective for attention calibration due to the complex interdependencies among attributes in one object and the absence of region-level annotation guidance. In this paper, we propose a novel coarse-to-fine framework termed Hierarchical Progressive Attention Network (HPAN), which leverages latent attention consistency across attributes to rectify the focus deviation of minor attributes. HPAN comprises two synergistic components, Super-Attribute Guided Generable Attention (SGGA) and Rebalanced Attribute Attention Calibration (RAAC). SGGA employs super-attributes to establish unified attention regions for both major and minor attributes, subsequently propagating these attention masks to RAAC for calibration. RAAC specializes in capturing fine-grained attribute-region interaction relations, with its output attention masks serving as supervisory signals to iteratively optimize the coarse attention of SGGA. Extensive experiments on three benchmark datasets verify the effectiveness of the proposed method. Code is available at github.com/zjrao/HPAN.

This article provides a novel framework for single-domain generalized object detection (i.e., Single-DGOD), where we are interested in learning and maintaining the semantic structures of self-augmented compound cross-domain samples to enhance the model's generalization ability. Different from domain generalized object detection (DGOD) trained on multiple source domains, Single-DGOD is far more challenging to generalize well to multiple target domains with only one single source domain. Existing methods mostly adopt a similar treatment from DGOD to learn domain-invariant features by decoupling or compressing the semantic space. However, there may exist two potential limitations: 1) pseudo attribute-label correlation due to extremely scarce single-domain data and 2) the semantic structural information is usually ignored, i.e., we found the affinities of instance-level semantic relations in samples are crucial to model generalization. In this article, we introduce semantic reasoning with compound domains (SRCD) for Single-DGOD. Specifically, our SRCD contains two main components, namely, the texture-based self-augmentation (TBSA) module and the local-global semantic reasoning (LGSR) module. TBSA aims to eliminate the effects of irrelevant attributes associated with labels, such as light, shadow, and color, at the image level by a light-yet-efficient self-augmentation. Moreover, LGSR is used to further model the semantic relationships on instance features to uncover and maintain the intrinsic semantic structures. Extensive experiments on multiple benchmarks demonstrate the effectiveness of the proposed SRCD. Code is available at github.com/zjrao/SRCD.

Recent advances in Synthetic Aperture Radar (SAR) ship detection have witnessed remarkable success by using large-scale annotated datasets. However, the annotation of SAR images requires strong domain-specific expertise, significantly hindering the prompt adoption of modern object detectors in this regime. Compared to SAR data, the optical data in geoscience are considerably easier to label. Motivated by this, we investigate a new and challenging problem – adaptive ship detection – with the goal of enhancing ship detection performance on SAR images by leveraging knowledge transferred from optical images. Considering the large distributional discrepancy between the source (optical) and target (SAR) domains, we presentOmniAdapt, a novel framework that progressively narrows the distance between the two types of images at the pixel, feature, and classifier levels. Specifically, OmniAdapt consists of three main modules, Target-like Generation Module (TLGM), Multi-feature Alignment Module (MFAM), and Common Specific Decomposition Module (CSDM). TLGM minimizes the visual disparity by infusing the target domain style into the source domain. MFAM aligns local- and global-level feature representations in an adversarial manner. Finally, CSDM decomposes the classifier into two independent components,i.e., the domain-common component and the domain-specific component, and promotes the recognition ability of the former via regularization learning. Experimental results demonstrate the effectiveness of the proposed method.