Copertina

ToG-Bench: Task-Oriented Spatio-Temporal Grounding in Egocentric Videos

Fuente: arXiv

Salvato in:

Dettagli Bibliografici
Autori principali:	Xu, Qi'ao, Qian, Tianwen, Fu, Yuqian, Li, Kailing, Jiao, Yang, Zhang, Jiacheng, Wang, Xiaoling, He, Liang
Natura:	Preprint
Pubblicazione:	2025
Soggetti:	Computer Vision and Pattern Recognition Artificial Intelligence
Accesso online:	Acceder al recurso
Tags:	Aggiungi Tag Nessun Tag, puoi essere il primo ad aggiungerne!!

Documenti analoghi

CLiViS: Unleashing Cognitive Map through Linguistic-Visual Synergy for Embodied Visual Reasoning
di: Li, Kailing, et al.
Pubblicazione: (2025)

EgoCross: Benchmarking Multimodal Large Language Models for Cross-Domain Egocentric Video Question Answering
di: Li, Yanjun, et al.
Pubblicazione: (2025)

Bridging the 2D-3D Gap: A Hierarchical Semantic-Geometric Map for Vision Language Navigation
di: Li, Kailing, et al.
Pubblicazione: (2026)

HSACNet: Hierarchical Scale-Aware Consistency Regularized Semi-Supervised Change Detection
di: Xu, Qi'ao, et al.
Pubblicazione: (2025)

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

TS-P$^2$CL: Plug-and-Play Dual Contrastive Learning for Vision-Guided Medical Time Series Classification
di: Xu, Qi'ao, et al.
Pubblicazione: (2025)

StreamEQA: Towards Streaming Video Understanding for Embodied Scenarios
di: Wang, Yifei, et al.
Pubblicazione: (2025)

EgoThinker: Unveiling Egocentric Reasoning with Spatio-Temporal CoT
di: Pei, Baoqi, et al.
Pubblicazione: (2025)

TimeScope: Towards Task-Oriented Temporal Grounding In Long Videos
di: Liu, Xiangrui, et al.
Pubblicazione: (2025)

TS-HTFA: Advancing Time Series Forecasting via Hierarchical Text-Free Alignment with Large Language Models
di: Wang, Pengfei, et al.
Pubblicazione: (2024)

Prompt as Free Lunch: Enhancing Diversity in Source-Free Cross-domain Few-shot Learning through Semantic-Guided Prompting
di: Zhuo, Linhai, et al.
Pubblicazione: (2024)

OmniGenBench: A Benchmark for Omnipotent Multimodal Generation across 50+ Tasks
di: Wang, Jiayu, et al.
Pubblicazione: (2025)

VideoZeroBench: Probing the Limits of Video MLLMs with Spatio-Temporal Evidence Verification
di: Meng, Jiahao, et al.
Pubblicazione: (2026)

Video-GroundingDINO: Towards Open-Vocabulary Spatio-Temporal Video Grounding
di: Wasim, Syed Talal, et al.
Pubblicazione: (2023)

CaST-Bench: Benchmarking Causal Chain-Grounded Spatio-Temporal Reasoning for Video Question Answering
di: Zhang, Mingfang, et al.
Pubblicazione: (2026)

Context-Guided Spatio-Temporal Video Grounding
di: Gu, Xin, et al.
Pubblicazione: (2024)

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

StreamingEval: A Unified Evaluation Protocol towards Realistic Streaming Video Understanding
di: Tang, Guowei, et al.
Pubblicazione: (2026)

Fine-grained Spatiotemporal Grounding on Egocentric Videos
di: Liang, Shuo, et al.
Pubblicazione: (2025)

Towards Long-Form Spatio-Temporal Video Grounding
di: Gu, Xin, et al.
Pubblicazione: (2026)

VideoMolmo: Spatio-Temporal Grounding Meets Pointing
di: Ahmad, Ghazi Shazan, et al.
Pubblicazione: (2025)

UrbanFM: Scaling Urban Spatio-Temporal Foundation Models
di: Chen, Wei, et al.
Pubblicazione: (2026)

EOC-Bench: Can MLLMs Identify, Recall, and Forecast Objects in an Egocentric World?
di: Yuan, Yuqian, et al.
Pubblicazione: (2025)

CEBSNet: Change-Excited and Background-Suppressed Network with Temporal Dependency Modeling for Bitemporal Change Detection
di: Xu, Qi'ao, et al.
Pubblicazione: (2025)

Unleashing the Potential of Multimodal LLMs for Zero-Shot Spatio-Temporal Video Grounding
di: Yang, Zaiquan, et al.
Pubblicazione: (2025)

IntentVCNet: Bridging Spatio-Temporal Gaps for Intention-Oriented Controllable Video Captioning
di: Qiu, Tianheng, et al.
Pubblicazione: (2025)

Learning to Recognize Correctly Completed Procedure Steps in Egocentric Assembly Videos through Spatio-Temporal Modeling
di: Schoonbeek, Tim J., et al.
Pubblicazione: (2025)

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

Learning from Complexity: Exploring Dynamic Sample Pruning of Spatio-Temporal Training
di: Chen, Wei, et al.
Pubblicazione: (2026)

OmniSTVG: Toward Spatio-Temporal Omni-Object Video Grounding
di: Yao, Jiali, et al.
Pubblicazione: (2025)

Bridging Time and Space: Decoupled Spatio-Temporal Alignment for Video Grounding
di: Tu, Xuezhen, et al.
Pubblicazione: (2026)

Open-o3-Video: Grounded Video Reasoning with Explicit Spatio-Temporal Evidence
di: Meng, Jiahao, et al.
Pubblicazione: (2025)

Ego2Web: A Web Agent Benchmark Grounded in Egocentric Videos
di: Yu, Shoubin, et al.
Pubblicazione: (2026)

SpatioTemporal Learning for Human Pose Estimation in Sparsely-Labeled Videos
di: Jiao, Yingying, et al.
Pubblicazione: (2025)

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

Incentivizing Temporal-Awareness in Egocentric Video Understanding Models
di: Xu, Zhiyang, et al.
Pubblicazione: (2026)

TubeRMC: Tube-conditioned Reconstruction with Mutual Constraints for Weakly-supervised Spatio-Temporal Video Grounding
di: Li, Jinxuan, et al.
Pubblicazione: (2025)

Contextual Self-paced Learning for Weakly Supervised Spatio-Temporal Video Grounding
di: Kumar, Akash, et al.
Pubblicazione: (2025)

Know-Show: Benchmarking Video-Language Models on Spatio-Temporal Grounded Reasoning
di: Sugandhika, Chinthani, et al.
Pubblicazione: (2025)

Detector-Empowered Video Large Language Model for Efficient Spatio-Temporal Grounding
di: Gao, Shida, et al.
Pubblicazione: (2025)