Imagen de Portada

Gaze-Regularized VLMs for Ego-Centric Behavior Understanding

Fuente: arXiv

Guardado en:

Detalles Bibliográficos
Autores principales:	Pani, Anupam, Yang, Yanchao
Formato:	Preprint
Publicado:	2026
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

Gaze-VLM:Bridging Gaze and VLMs through Attention Regularization for Egocentric Understanding
por: Pani, Anupam, et al.
Publicado: (2025)

Gaze-Regularized Vision-Language-Action Models for Robotic Manipulation
por: Pani, Anupam, et al.
Publicado: (2026)

ObjectRelator: Enabling Cross-View Object Relation Understanding Across Ego-Centric and Exo-Centric Perspectives
por: Fu, Yuqian, et al.
Publicado: (2024)

EgoExOR: An Ego-Exo-Centric Operating Room Dataset for Surgical Activity Understanding
por: Özsoy, Ege, et al.
Publicado: (2025)

Understanding Dynamic Scenes in Ego Centric 4D Point Clouds
por: Huang, Junsheng, et al.
Publicado: (2025)

From My View to Yours: Ego-to-Exo Transfer in VLMs for Understanding Activities of Daily Living
por: Reilly, Dominick, et al.
Publicado: (2025)

Eye Gaze Tells You Where to Compute: Gaze-Driven Efficient VLMs
por: Chen, Qinyu, et al.
Publicado: (2025)

EgoSound: Benchmarking Sound Understanding in Egocentric Videos
por: Zhu, Bingwen, et al.
Publicado: (2026)

Ego-InBetween: Generating Object State Transitions in Ego-Centric Videos
por: Ge, Mengmeng, et al.
Publicado: (2026)

EgoDyn-Bench: Evaluating Ego-Motion Understanding in Vision-Centric Foundation Models for Autonomous Driving
por: Schäfer, Finn Rasmus, et al.
Publicado: (2026)

EgoCampus: Egocentric Pedestrian Eye Gaze Model and Dataset
por: John, Ronan, et al.
Publicado: (2025)

ECHO: Ego-Centric modeling of Human-Object interactions
por: Petrov, Ilya A., et al.
Publicado: (2025)

VLMs-in-the-Wild: Bridging the Gap Between Academic Benchmarks and Enterprise Reality
por: Bandraupalli, Srihari, et al.
Publicado: (2025)

From Synchrony to Sequence: Exo-to-Ego Generation via Interpolation
por: Mahdi, Mohammad, et al.
Publicado: (2026)

GazeNLQ @ Ego4D Natural Language Queries Challenge 2025
por: Lin, Wei-Cheng, et al.
Publicado: (2025)

ENIGMA-360: An Ego-Exo Dataset for Human Behavior Understanding in Industrial Scenarios
por: Ragusa, Francesco, et al.
Publicado: (2026)

A Review of Driver Gaze Estimation and Application in Gaze Behavior Understanding
por: Sharma, Pavan Kumar, et al.
Publicado: (2023)

EgoFSD: Ego-Centric Fully Sparse Paradigm with Uncertainty Denoising and Iterative Refinement for Efficient End-to-End Self-Driving
por: Su, Haisheng, et al.
Publicado: (2024)

EgoNight: Towards Egocentric Vision Understanding at Night with a Challenging Benchmark
por: Zhang, Deheng, et al.
Publicado: (2025)

EgoIntrospect: An Egocentric Dataset and Benchmark for User-Centric Internal State Reasoning
por: Wang, Zeyu, et al.
Publicado: (2026)

Spatial Reasoning with Vision-Language Models in Ego-Centric Multi-View Scenes
por: Gholami, Mohsen, et al.
Publicado: (2025)

EgoAVU: Egocentric Audio-Visual Understanding
por: Seth, Ashish, et al.
Publicado: (2026)

Leveraging Driver Field-of-View for Multimodal Ego-Trajectory Prediction
por: Akbiyik, M. Eren, et al.
Publicado: (2023)

Contour Errors: An Ego-Centric Metric for Reliable 3D Multi-Object Tracking
por: Kaul, Sharang, et al.
Publicado: (2025)

Thinking with Gaze: Sequential Eye-Tracking as Visual Reasoning Supervision for Medical VLMs
por: Li, Yiwei, et al.
Publicado: (2026)

Event-Free Moving Object Segmentation from Moving Ego Vehicle
por: Zhou, Zhuyun, et al.
Publicado: (2023)

On the Perception Bottleneck of VLMs for Chart Understanding
por: Liu, Junteng, et al.
Publicado: (2025)

CIVET: Systematic Evaluation of Understanding in VLMs
por: Rizzoli, Massimo, et al.
Publicado: (2025)

Exo2EgoSyn: Unlocking Foundation Video Generation Models for Exocentric-to-Egocentric Video Synthesis
por: Mahdi, Mohammad, et al.
Publicado: (2025)

Linear Scaling Video VLMs for Long Video Understanding
por: Eyzaguirre, Cristobal, et al.
Publicado: (2026)

EgoGraph: Temporal Knowledge Graph for Egocentric Video Understanding
por: Sun, Shitong, et al.
Publicado: (2026)

DenseGrounding: Improving Dense Language-Vision Semantics for Ego-Centric 3D Visual Grounding
por: Zheng, Henry, et al.
Publicado: (2025)

EgoCoT-Bench: Benchmarking Grounded and Verifiable Operation-Centric Chain of Thought Reasoning for MLLMs
por: Dai, Yang, et al.
Publicado: (2026)

Omni-Scene: Omni-Gaussian Representation for Ego-Centric Sparse-View Scene Reconstruction
por: Wei, Dongxu, et al.
Publicado: (2024)

EgoSpot:Egocentric Multimodal Control for Hands-Free Mobile Manipulation
por: Zhang, Ganlin, et al.
Publicado: (2023)

Improving Domain Generalization on Gaze Estimation via Branch-out Auxiliary Regularization
por: Zhao, Ruijie, et al.
Publicado: (2024)

EgoInteract: Synthetic Egocentric Videos Generation for Interaction Understanding and Anticipation
por: Leonardi, Rosario, et al.
Publicado: (2026)

Cross-View Multi-Modal Segmentation @ Ego-Exo4D Challenges 2025
por: Fu, Yuqian, et al.
Publicado: (2025)

Understanding and Modeling the Effects of Task and Context on Drivers' Gaze Allocation
por: Kotseruba, Iuliia, et al.
Publicado: (2023)

MomentSeg: Moment-Centric Sampling for Enhanced Video Pixel Understanding
por: Dai, Ming, et al.
Publicado: (2025)