paper-with-me

홈 › Papers

C2C: Component-to-Composition Learning for Zero-Shot Compositional Action Recognition

2024-07-08 · Rongchang Li, ZhenHua Feng, Tianyang Xu, Linze Li, Xiao-Jun Wu, Muhammad Awais, Sara Atito, Josef Kittler

Compositional actions consist of dynamic (verbs) and static (objects) concepts. Humans can easily recognize unseen compositions using the learned concepts. For machines, solving such a problem requires a model to recognize unseen actions composed of previously observed verbs and objects, thus requiring so-called compositional generalization ability. To facilitate this research, we propose a novel Zero-Shot Compositional Action Recognition (ZS-CAR) task. For evaluating the task, we construct a new benchmark, Something-composition (Sth-com), based on the widely used Something-Something V2 dataset. We also propose a novel Component-to-Composition (C2C) learning method to solve the new ZS-CAR task. C2C includes an independent component learning module and a composition inference module. Last, we devise an enhanced training strategy to address the challenges of component variations between seen and unseen compositions and to handle the subtle balance between learning seen and unseen actions. The experimental results demonstrate that the proposed framework significantly surpasses the existing compositional generalization methods and sets a new state-of-the-art. The new Sth-com benchmark and code are available at https://github.com/RongchangLi/ZSCAR_C2C.

📄 PDF Abstract BibTeX arXiv:2407.06113

Code (1)

rongchangli/zscar_c2c 공식 구현 pytorch

Tasks

Action Recognition

Similar Papers 제목 키워드 기반

ComCLIP: Training-Free Compositional Image and Text Matching

2022-11-25 · Kenan Jiang, Xuehai He, Ruize Xu, Xin Eric Wang

Contrastive Language-Image Pretraining (CLIP) has demonstrated great zero-shot performance for matching images and text. However, it is still challenging to adapt vision-lanaguage pretrained models like CLIP to compositi…

Image-text matchingImage-text RetrievalRetrievalText Matching+1

Why Can't I Open My Drawer? Mitigating Object-Driven Shortcuts in Zero-Shot Compositional Action Recognition

2026-01-22 · Geo Ahn, Inwoong Lee, Taeoh Kim, Minho Shim 외 arxiv

Zero-Shot Compositional Action Recognition (ZS-CAR) requires recognizing novel verb-object combinations composed of previously observed primitives. In this work, we tackle a key failure mode: models predict verbs via obj…

Action Recognition

A causal view of compositional zero-shot recognition

2020-06-25 · NeurIPS 2020 12 · Yuval Atzmon, Felix Kreuk, Uri Shalit, Gal Chechik

People easily recognize new visual categories that are new combinations of known components. This compositional generalization capacity is critical for learning in real-world domains like vision and language because the …

AttributeCompositional Zero-Shot LearningZero-Shot Learning

HOMOE: A Memory-Based and Composition-Aware Framework for Zero-Shot Learning with Hopfield Network and Soft Mixture of Experts

2023-11-23 · Do Huu Dat, Po Yuan Mao, Tien Hoang Nguyen, Wray Buntine 외

Compositional Zero-Shot Learning (CZSL) has emerged as an essential paradigm in machine learning, aiming to overcome the constraints of traditional zero-shot learning by incorporating compositional thinking into its meth…

Compositional Zero-Shot LearningMixture-of-ExpertsZero-Shot Learning

Iterative Compositional Data Generation for Robot Control

2025-12-11 · Anh-Quan Pham, Marcel Hussing, Shubhankar P. Patankar, Dani S. Bassett 외 arxiv

Collecting robotic manipulation data is expensive, making it impractical to acquire demonstrations for the combinatorially large space of tasks that arise in multi-object, multi-robot, and multi-environment settings. Whi…

Reinforcement Learning