Related papers: SCALE: Semantic- and Confidence-Aware Conditional …
Zero-shot learning (ZSL) algorithms typically work by exploiting attribute correlations to be able to make predictions in unseen classes. However, these correlations do not remain intact at test time in most practical settings and the…
Existing generative Zero-Shot Learning (ZSL) methods only consider the unidirectional alignment from the class semantics to the visual features while ignoring the alignment from the visual features to the class semantics, which fails to…
Variational Autoencoders (VAEs) are powerful generative models for learning latent representations. Standard VAEs generate dispersed and unstructured latent spaces by utilizing all dimensions, which limits their interpretability, especially…
Zero-shot learning (ZSL) endeavors to transfer knowledge from seen categories to recognize unseen categories, which mostly relies on the semantic-visual interactions between image and attribute tokens. Recently, prompt learning has emerged…
Benefiting from strong generalization ability, pre-trained vision language models (VLMs), e.g., CLIP, have been widely utilized in zero-shot scene understanding. Unlike simple recognition tasks, grounded situation recognition (GSR) requires…
Zero-shot learning (ZSL) enables solving a task without the need to see its examples. In this paper, we propose two ZSL frameworks that learn to synthesize parameters for novel unseen classes. First, we propose to cast the problem of ZSL as…
Unlike conventional zero-shot classification, zero-shot semantic segmentation predicts a class label at the pixel level instead of the image level. When solving zero-shot semantic segmentation problems, the need for pixel-level prediction…
Skeleton-based human action recognition aims to classify human skeletal sequences, which are spatiotemporal representations of actions, into predefined categories. To reduce the reliance on costly annotations of skeletal sequences while…
It is a recognized fact that the classification accuracy of unseen classes in the setting of Generalized Zero-Shot Learning (GZSL) is much lower than that of traditional Zero-Shot Leaning (ZSL). One of the reasons is that an instance is…
Zero-shot learning (ZSL) aims to classify objects that are not observed or seen during training. It relies on class semantic description to transfer knowledge from the seen classes to the unseen classes. Existing methods of obtaining class…
To recognize objects of the unseen classes, most existing Zero-Shot Learning(ZSL) methods first learn a compatible projection function between the common semantic space and the visual space based on the data of source seen classes, then…
We present a novel problem setting in zero-shot learning, zero-shot object recognition and detection in the context. Contrary to the traditional zero-shot learning methods, which simply infers unseen categories by transferring knowledge…
Zero-shot Learning (ZSL) aims to enable image classifiers to recognize images from unseen classes that were not included during training. Unlike traditional supervised classification, ZSL typically relies on learning a mapping from visual…
Vision-language models (VLMs) have demonstrated strong cross-modal capabilities, yet most work remains limited to 2D data and assumes binary supervision (i.e., positive vs. negative pairs), overlooking the continuous and structured…
Action recognition via 3D skeleton data is an emerging important topic in these years. Most existing methods either extract hand-crafted descriptors or learn action representations by supervised learning paradigms that require massive…
Zero-Shot Temporal Action Localization (ZS-TAL) seeks to identify and locate actions in untrimmed videos unseen during training. Existing ZS-TAL methods involve fine-tuning a model on a large amount of annotated training data. While…
Compositional Zero-Shot Learning (CZSL) aims to recognize novel attribute-object compositions based on the knowledge learned from seen ones. Existing methods suffer from performance degradation caused by the distribution shift of label…
Multi-label image recognition with partial labels (MLR-PL) is designed to train models using a mix of known and unknown labels. Traditional methods rely on semantic or feature correlations to create pseudo-labels for unidentified labels…
Learning a common latent embedding by aligning the latent spaces of cross-modal autoencoders is an effective strategy for Generalized Zero-Shot Classification (GZSC). However, due to the lack of fine-grained instance-wise annotations, it…
Cross-embodiment learning from human demonstrations is hindered by the visual gap between human and robot embodiments. While self-supervised learning (SSL) backbones encode rich inter-class semantics of general objects, we show they fail to…