Syntactically Guided Generative Embeddings for Zero-Shot Skeleton Action Recognition

2021-01-27 · Pranay Gupta, Divyanshu Sharma, Ravi Kiran Sarvadevabhatla

We introduce SynSE, a novel syntactically guided generative approach for Zero-Shot Learning (ZSL). Our end-to-end approach learns progressively refined generative embedding spaces constrained within and across the involved modalities (visual, language). The inter-modal constraints are defined between action sequence embedding and embeddings of Parts of Speech (PoS) tagged words in the corresponding action description. We deploy SynSE for the task of skeleton-based action sequence recognition. Our design choices enable SynSE to generalize compositionally, i.e., recognize sequences whose action descriptions contain words not encountered during training. We also extend our approach to the more challenging Generalized Zero-Shot Learning (GZSL) problem via a confidence-based gating mechanism. We are the first to present zero-shot skeleton action recognition results on the large-scale NTU-60 and NTU-120 skeleton action datasets with multiple splits. Our results demonstrate SynSE's state of the art performance in both ZSL and GZSL settings compared to strong baselines on the NTU-60 and NTU-120 datasets. The code and pretrained models are available at https://github.com/skelemoa/synse-zsl

📄 PDF Abstract BibTeX arXiv:2101.11530

Code (1)

skelemoa/synse-zsl 공식 구현 pytorch

Tasks

Action Recognition Generalized Zero-Shot Learning Generalized Zero Shot skeletal action recognitionPOSZero-Shot Learning Zero Shot Skeletal Action Recognition

Disentangled Ontology Embedding for Zero-shot Learning

2022-06-08 · Yuxia Geng, Jiaoyan Chen, Wen Zhang, Yajing Xu 외

Knowledge Graph (KG) and its variant of ontology have been widely used for knowledge representation, and have shown to be quite effective in augmenting Zero-shot Learning (ZSL). However, existing ZSL methods that utilize…

image-classification Image Classification Ontology Embedding Zero-Shot Image Classification+1

Just Pass Twice: Efficient Token Classification with LLMs for Zero-Shot NER

2026-04-06 · Ahmed Ewais, Ahmed Hashish, Amr Ali arxiv

Large language models encode extensive world knowledge valuable for zero-shot named entity recognition. However, their causal attention mechanism, where tokens attend only to preceding context, prevents effective token c…

Zero-shot Generalization

Text-guided Synthetic Geometric Augmentation for Zero-shot 3D Understanding

2025-01-16 · Kohei Torimi, Ryosuke Yamada, Daichi Otsuka, Kensho Hara 외

Zero-shot recognition models require extensive training data for generalization. However, in zero-shot 3D classification, collecting 3D data and captions is costly and laborintensive, posing a significant barrier compare…

3D Classification Zero-shot 3D classification Zero-Shot Learning

AGFT: Alignment-Guided Fine-Tuning for Zero-Shot Adversarial Robustness of Vision-Language Models

2026-03-31 · Yubo Cui, Xianchao Guan, Zijun Xiong, Zheng Zhang arxiv

Pre-trained vision-language models (VLMs) exhibit strong zero-shot generalization but remain vulnerable to adversarial perturbations. Existing classification-guided adversarial fine-tuning methods often disrupt pre-train…

Zero-shot Generalization Adversarial Robustness

Motion-Guided Semantic Alignment with Negative Prompts for Zero-Shot Video Action Recognition

2026-04-18 · Yiming Wang, Frederick W. B. Li, Jingyun Wang arxiv

Zero-shot action recognition is challenging due to the semantic gap between seen and unseen classes. We present a novel framework that enhances CLIP with disentangled embeddings and semantic-guided interaction. A Motion …

Zero-Shot Action Recognition