Cover Image

FocusGraph: Graph-Structured Frame Selection for Embodied Long Video Question Answering

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Zemskova, Tatiana, Andryushenko, Solomon, Obrubov, Ilya, Khoruzhaia, Viktoriia, Eroshenko, Ekaterina, Derevyanka, Ekaterina, Yudin, Dmitry
Format:	Preprint
Published:	2026
Subjects:	Computer Vision and Pattern Recognition
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

3DGraphLLM: Combining Semantic Graphs and Large Language Models for 3D Scene Understanding
by: Zemskova, Tatiana, et al.
Published: (2024)

KM-ViPE: Online Tightly Coupled Vision-Language-Geometry Fusion for Open-Vocabulary Semantic SLAM
by: Nasser, Zaid, et al.
Published: (2025)

Beyond Bare Queries: Open-Vocabulary Object Grounding with 3D Scene Graph
by: Linok, Sergey, et al.
Published: (2024)

SceneGraphVLM: Dynamic Scene Graph Generation from Video with Vision-Language Models
by: Makarov, Vladislav, et al.
Published: (2026)

HiMu: Hierarchical Multimodal Frame Selection for Long Video Question Answering
by: Ben-Ami, Dan, et al.
Published: (2026)

Semantic Event Graphs for Long-Form Video Question Answering
by: Dixit, Aradhya, et al.
Published: (2026)

OVSegDT: Segmenting Transformer for Open-Vocabulary Object Goal Navigation
by: Zemskova, Tatiana, et al.
Published: (2025)

Enhancing Long Video Question Answering with Scene-Localized Frame Grouping
by: Yang, Xuyi, et al.
Published: (2025)

DyGEnc: Encoding a Sequence of Textual Scene Graphs to Reason and Answer Questions in Dynamic Scenes
by: Linok, Sergey, et al.
Published: (2025)

HORNet: Task-Guided Frame Selection for Video Question Answering with Vision-Language Models
by: Bai, Xiangyu, et al.
Published: (2026)

GraphEQA: Using 3D Semantic Scene Graphs for Real-time Embodied Question Answering
by: Saxena, Saumya, et al.
Published: (2024)

BIMBA: Selective-Scan Compression for Long-Range Video Question Answering
by: Islam, Md Mohaiminul, et al.
Published: (2025)

M3DMap: Object-aware Multimodal 3D Mapping for Dynamic Environments
by: Yudin, Dmitry
Published: (2025)

A.I.R.: Enabling Adaptive, Iterative, and Reasoning-based Frame Selection For Video Question Answering
by: Zou, Yuanhao, et al.
Published: (2025)

Grounded Question-Answering in Long Egocentric Videos
by: Di, Shangzhe, et al.
Published: (2023)

Glance and Focus: Memory Prompting for Multi-Event Video Question Answering
by: Bai, Ziyi, et al.
Published: (2024)

GHR-VQA: Graph-guided Hierarchical Relational Reasoning for Video Question Answering
by: Brilli, Dionysia Danai, et al.
Published: (2025)

Narrative Aligned Long Form Video Question Answering
by: Jain, Rahul, et al.
Published: (2026)

End-to-End Video Question Answering with Frame Scoring Mechanisms and Adaptive Sampling
by: Liang, Jianxin, et al.
Published: (2024)

MovieChat+: Question-aware Sparse Memory for Long Video Question Answering
by: Song, Enxin, et al.
Published: (2024)

DriveLM: Driving with Graph Visual Question Answering
by: Sima, Chonghao, et al.
Published: (2023)

RCDINO: Enhancing Radar-Camera 3D Object Detection with DINOv2 Semantic Features
by: Matykina, Olga, et al.
Published: (2025)

CRAFT: Critic-Refined Adaptive Key-Frame Targeting for Multimodal Video Question Answering
by: Bhosale, Mahesh, et al.
Published: (2026)

Learning Question-Aware Keyframe Selection with Synthetic Supervision for Video Question Answering
by: Kwon, Minchan, et al.
Published: (2026)

MA-EgoQA: Question Answering over Egocentric Videos from Multiple Embodied Agents
by: Kim, Kangsan, et al.
Published: (2026)

A Simple LLM Framework for Long-Range Video Question-Answering
by: Zhang, Ce, et al.
Published: (2023)

SurgLQA: Scalable Long-Horizon Surgical Video Question Answering
by: Guo, Diandian, et al.
Published: (2026)

Visual Environment-Interactive Planning for Embodied Complex-Question Answering
by: Lan, Ning, et al.
Published: (2025)

Talk2SAM: Text-Guided Semantic Enhancement for Complex-Shaped Object Segmentation
by: Vetoshkin, Luka, et al.
Published: (2025)

OFMPNet: Deep End-to-End Model for Occupancy and Flow Prediction in Urban Environment
by: Murhij, Youshaa, et al.
Published: (2024)

IndustryEQA: Pushing the Frontiers of Embodied Question Answering in Industrial Scenarios
by: Li, Yifan, et al.
Published: (2025)

SPIDER: A Comprehensive Multi-Organ Supervised Pathology Dataset and Baseline Models
by: Nechaev, Dmitry, et al.
Published: (2025)

HISTAI: An Open-Source, Large-Scale Whole Slide Image Dataset for Computational Pathology
by: Nechaev, Dmitry, et al.
Published: (2025)

Hibou: A Family of Foundational Vision Transformers for Pathology
by: Nechaev, Dmitry, et al.
Published: (2024)

Encoding and Controlling Global Semantics for Long-form Video Question Answering
by: Nguyen, Thong Thanh, et al.
Published: (2024)

LLMs Meet Long Video: Advancing Long Video Question Answering with An Interactive Visual Adapter in LLMs
by: Li, Yunxin, et al.
Published: (2024)

Selectively Answering Visual Questions
by: Eisenschlos, Julian Martin, et al.
Published: (2024)

CG-Bench: Clue-grounded Question Answering Benchmark for Long Video Understanding
by: Chen, Guo, et al.
Published: (2024)

Event-Anchored Frame Selection for Effective Long-Video Understanding
by: Chen, Wang, et al.
Published: (2026)

Map-based Modular Approach for Zero-shot Embodied Question Answering
by: Sakamoto, Koya, et al.
Published: (2024)