Imagen de Portada

Video-QTR: Query-Driven Temporal Reasoning Framework for Lightweight Video Understanding

Fuente: arXiv

Guardado en:

Detalles Bibliográficos
Autores principales:	Zhao, Xinkui, Wang, Zuxin, Zhang, Yifan, Cheng, Guanjie, Xu, Yueshen, Deng, Shuiguang, Liu, Chang, Wang, Naibo, Yin, Jianwei
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

LightRouter: Towards Efficient LLM Collaboration with Minimal Overhead
por: Zhang, Yifan, et al.
Publicado: (2025)

A Robust Incomplete Multimodal Low-Rank Adaptation Approach for Emotion Recognition
por: Zhao, Xinkui, et al.
Publicado: (2025)

Completion by Comprehension: Guiding Code Generation with Multi-Granularity Understanding
por: Zhao, Xinkui, et al.
Publicado: (2025)

Walking the Schrödinger Bridge: A Direct Trajectory for Text-to-3D Generation
por: Li, Ziying, et al.
Publicado: (2025)

SortingHat: Redefining Operating Systems Education with a Tailored Digital Teaching Assistant
por: Zhang, Yifan, et al.
Publicado: (2026)

SatFusion: A Unified Framework for Enhancing Remote Sensing Images via Multi-Frame and Multi-Source Images Fusion
por: Tong, Yufei, et al.
Publicado: (2025)

Next-Gen Computing Systems with Compute Express Link: a Comprehensive Survey
por: Chen, Chen, et al.
Publicado: (2024)

TRAIL: Joint Inference and Refinement of Knowledge Graphs with Large Language Models
por: Zhao, Xinkui, et al.
Publicado: (2025)

Is Collaboration Worth It? A Decision-Oriented Survey in Multi-Agent Systems
por: Cheng, Guanjie, et al.
Publicado: (2026)

AME: An Efficient Heterogeneous Agentic Memory Engine for Smartphones
por: Zhao, Xinkui, et al.
Publicado: (2025)

ProMAS: Proactive Error Forecasting for Multi-Agent Systems Using Markov Transition Dynamics
por: Zhao, Xinkui, et al.
Publicado: (2026)

TenonOS: A Self-Generating LibOS-on-LibOS Framework for Time-Critical Embedded Operating Systems
por: Zhao, Xinkui, et al.
Publicado: (2025)

CADRef: Robust Out-of-Distribution Detection via Class-Aware Decoupled Relative Feature Leveraging
por: Ling, Zhiwei, et al.
Publicado: (2025)

GRAB-ANNS: High-Throughput Indexing and Hybrid Search via GPU-Native Bucketing
por: Zhao, Xinkui, et al.
Publicado: (2026)

Can Vision-Language Models Handle Long-Context Code? An Empirical Study on Visual Compression
por: Zhong, Jianping, et al.
Publicado: (2026)

StackPilot: Autonomous Function Agents for Scalable and Environment-Free Code Execution
por: Zhao, Xinkui, et al.
Publicado: (2025)

DyC-STG: Dynamic Causal Spatio-Temporal Graph Network for Real-time Data Credibility Analysis in IoT
por: Cheng, Guanjie, et al.
Publicado: (2025)

LVC: A Lightweight Compression Framework for Enhancing VLMs in Long Video Understanding
por: Wang, Ziyi, et al.
Publicado: (2025)

Thinking with Drafts: Speculative Temporal Reasoning for Efficient Long Video Understanding
por: Hu, Pengfei, et al.
Publicado: (2025)

Pseudo-labeling with Keyword Refining for Few-Supervised Video Captioning
por: Li, Ping, et al.
Publicado: (2024)

Data-Free Federated Class Incremental Learning with Diffusion-Based Generative Memory
por: Wang, Naibo, et al.
Publicado: (2024)

Revisiting Vulnerability Patch Localization: An Empirical Study and LLM-Based Solution
por: Xu, Haoran, et al.
Publicado: (2025)

VADTree: Explainable Training-Free Video Anomaly Detection via Hierarchical Granularity-Aware Tree
por: Li, Wenlong, et al.
Publicado: (2025)

Perceive, Query & Reason: Enhancing Video QA with Question-Guided Temporal Queries
por: Amoroso, Roberto, et al.
Publicado: (2024)

Quality-Aware Robust Multi-View Clustering for Heterogeneous Observation Noise
por: Wu, Peihan, et al.
Publicado: (2026)

Flow of Truth: Proactive Temporal Forensics for Image-to-Video Generation
por: Chen, Yuzhuo, et al.
Publicado: (2026)

Temporal2Seq: A Unified Framework for Temporal Video Understanding Tasks
por: Yang, Min, et al.
Publicado: (2024)

VideoPro: Adaptive Program Reasoning for Long Video Understanding
por: Li, Chenglin, et al.
Publicado: (2025)

GRACE: Graph-Guided Repository-Aware Code Completion through Hierarchical Code Fusion
por: Wang, Xingliang, et al.
Publicado: (2025)

V-CORE: Temporally Consistent Video Understanding for Video-LLM
por: Kang, Zhengjian, et al.
Publicado: (2026)

Temporal Residual Guided Diffusion Framework for Event-Driven Video Reconstruction
por: Zhu, Lin, et al.
Publicado: (2024)

VIDEOP2R: Video Understanding from Perception to Reasoning
por: Jiang, Yifan, et al.
Publicado: (2025)

VideoINSTA: Zero-shot Long Video Understanding via Informative Spatial-Temporal Reasoning with LLMs
por: Liao, Ruotong, et al.
Publicado: (2024)

One-Shot Sequential Federated Learning for Non-IID Data by Enhancing Local Model Diversity
por: Wang, Naibo, et al.
Publicado: (2024)

TADS: Task-Aware Data Selection for Multi-Task Multimodal Pre-Training
por: Cheng, Guanjie, et al.
Publicado: (2026)

BPI: A Novel Efficient and Reliable Search Structure for Hybrid Storage Blockchain
por: Zhao, Xinkui, et al.
Publicado: (2025)

VideoExpert: Augmented LLM for Temporal-Sensitive Video Understanding
por: Zhao, Henghao, et al.
Publicado: (2025)

Integrating Artificial Intelligence into Operating Systems: A Survey on Techniques, Applications, and Future Directions
por: Zhang, Yifan, et al.
Publicado: (2024)

VTimeCoT: Thinking by Drawing for Video Temporal Grounding and Reasoning
por: Zhang, Jinglei, et al.
Publicado: (2025)

TemporalVLM: Video LLMs for Temporal Reasoning in Long Videos
por: Fateh, Fawad Javed, et al.
Publicado: (2024)