Imagen de Portada

Affordance-First Decomposition for Continual Learning in Video-Language Understanding

Fuente: arXiv

Guardado en:

Detalles Bibliográficos
Autores principales:	Xu, Mengzhu, Liu, Hanzhi, Peng, Ningkang, Chen, Qianyu, Xiao, Canran
Formato:	Preprint
Publicado:	2025
Materias:	Computer Vision and Pattern Recognition
Acceso en línea:	Acceder al recurso
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

Ejemplares similares

How to Achieve Prototypical Birth and Death for OOD Detection?
por: Peng, Ningkang, et al.
Publicado: (2026)

Holistic Reliability Propagation: Decoupling Annotation and Prediction for Robust Noisy-Label
por: Mao, Jingyang, et al.
Publicado: (2026)

Is Complex Training Necessary for Long-Tailed OOD Detection? A Re-think from Feature Geometry
por: Peng, Ningkang, et al.
Publicado: (2026)

Learning Visual Affordance from Audio
por: Lu, Lidong, et al.
Publicado: (2025)

HamBR: Active Decision Boundary Restoration Based on Hamiltonian Dynamics for Learning with Noisy Labels
por: Peng, Ningkang, et al.
Publicado: (2026)

AffordanceLLM: Grounding Affordance from Vision Language Models
por: Qian, Shengyi, et al.
Publicado: (2024)

VideoAfford: Grounding 3D Affordance from Human-Object-Interaction Videos via Multimodal Large Language Model
por: Wang, Hanqing, et al.
Publicado: (2026)

Affordance-R1: Reinforcement Learning for Generalizable Affordance Reasoning in Multimodal Large Language Model
por: Wang, Hanqing, et al.
Publicado: (2025)

FuncGrasp: Learning Object-Centric Neural Grasp Functions from Single Annotated Example Object
por: Chen, Hanzhi, et al.
Publicado: (2024)

Efficient Continual Learning through Frequency Decomposition and Integration
por: Liu, Ruiqi, et al.
Publicado: (2025)

TB-HSU: Hierarchical 3D Scene Understanding with Contextual Affordances
por: Xu, Wenting, et al.
Publicado: (2024)

PAVLM: Advancing Point Cloud based Affordance Understanding Via Vision-Language Model
por: Liu, Shang-Ching, et al.
Publicado: (2024)

Populate-A-Scene: Affordance-Aware Human Video Generation
por: Shan, Mengyi, et al.
Publicado: (2025)

Radial-Angular Geometry for Reliable Update Diagnosis in Noisy-Label Learning
por: Peng, Ningkang, et al.
Publicado: (2026)

RRNet: Configurable Real-Time Video Enhancement with Arbitrary Local Lighting Variations
por: Yang, Wenlong, et al.
Publicado: (2026)

Long Video Understanding with Learnable Retrieval in Video-Language Models
por: Xu, Jiaqi, et al.
Publicado: (2023)

GAMR: Geometric-Aware Manifold Regularization with Virtual Outlier Synthesis for Learning with Noisy Labels
por: Peng, Ningkang, et al.
Publicado: (2026)

Learning Precise Affordances from Egocentric Videos for Robotic Manipulation
por: Li, Gen, et al.
Publicado: (2024)

Bisecle: Binding and Separation in Continual Learning for Video Language Understanding
por: Tan, Yue, et al.
Publicado: (2025)

arg-VU: Affordance Reasoning with Physics-Aware 3D Geometry for Visual Understanding in Robotic Surgery
por: Xiao, Nan, et al.
Publicado: (2026)

Low-light Image Enhancement with Retinex Decomposition in Latent Space
por: Zheng, Bolun, et al.
Publicado: (2026)

Learning 2D Invariant Affordance Knowledge for 3D Affordance Grounding
por: Gao, Xianqiang, et al.
Publicado: (2024)

Early High-Frequency Injection for Geometry-Sensitive OOD Detection
por: Cheng, Chuanjie, et al.
Publicado: (2026)

Multi-View Synergistic Learning with Vision-Language Adaption for Low-Resource Biomedical Image Classification
por: Luo, Xiaoliu, et al.
Publicado: (2026)

CL-VISTA: Benchmarking Continual Learning in Video Large Language Models
por: Guo, Haiyang, et al.
Publicado: (2026)

RoboPCA: Pose-centered Affordance Learning from Human Demonstrations for Robot Manipulation
por: Xiao, Zhanqi, et al.
Publicado: (2026)

VAGNet: Grounding 3D Affordance from Human-Object Interactions in Videos
por: Mao, Aihua, et al.
Publicado: (2026)

Learning with Adaptive Prototype Manifolds for Out-of-Distribution Detection
por: Peng, Ningkang, et al.
Publicado: (2026)

When Accuracy Is Not Enough: Uncertainty Collapse between Noisy Label Learning and Out-of-Distribution Detection
por: Peng, Ningkang, et al.
Publicado: (2026)

BOLT: Boost Large Vision-Language Model Without Training for Long-form Video Understanding
por: Liu, Shuming, et al.
Publicado: (2025)

DepthSSC: Monocular 3D Semantic Scene Completion via Depth-Spatial Alignment and Voxel Adaptation
por: Yao, Jiawei, et al.
Publicado: (2023)

HarmonicNeRF: Geometry-Informed Synthetic View Augmentation for 3D Scene Reconstruction in Driving Scenarios
por: Pan, Xiaochao, et al.
Publicado: (2023)

STOP: Integrated Spatial-Temporal Dynamic Prompting for Video Understanding
por: Liu, Zichen, et al.
Publicado: (2025)

LongVU: Spatiotemporal Adaptive Compression for Long Video-Language Understanding
por: Shen, Xiaoqian, et al.
Publicado: (2024)

Panoramic Affordance Prediction
por: Zhang, Zixin, et al.
Publicado: (2026)

VidBot: Learning Generalizable 3D Actions from In-the-Wild 2D Human Videos for Zero-Shot Robotic Manipulation
por: Chen, Hanzhi, et al.
Publicado: (2025)

SurveillanceVQA-589K: A Benchmark for Comprehensive Surveillance Video-Language Understanding with Large Models
por: Liu, Bo, et al.
Publicado: (2025)

EgoExoBench: A Benchmark for First- and Third-person View Video Understanding in MLLMs
por: He, Yuping, et al.
Publicado: (2025)

HyperTokens: Controlling Token Dynamics for Continual Video-Language Understanding
por: Nguyen, Toan, et al.
Publicado: (2026)

AffordanceGrasp-R1:Leveraging Reasoning-Based Affordance Segmentation with Reinforcement Learning for Robotic Grasping
por: Zhou, Dingyi, et al.
Publicado: (2026)