Imagen de Portada

Vista: Scene-Aware Optimization for Streaming Video Question Answering under Post-Hoc Queries

Fuente: arXiv

Guardado en:

Detalles Bibliográficos
Autores principales:	Lu, Haocheng, Zhang, Nan, Tao, Wei, Qu, Xiaoyang, Li, Guokuan, Wan, Jiguang, Wang, Jianzong
Formato:	Preprint
Publicado:	2026
Materias:	Computer Vision and Pattern Recognition Artificial Intelligence
Acceso en línea:	Acceder al recurso
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

Ejemplares similares

Triage: Hierarchical Visual Budgeting for Efficient Video Reasoning in Vision-Language Models
por: Wang, Anmin, et al.
Publicado: (2026)

RATE-Nav: Region-Aware Termination Enhancement for Zero-shot Object Navigation with Vision-Language Models
por: Li, Junjie, et al.
Publicado: (2025)

VisTa: Visual-contextual and Text-augmented Zero-shot Object-level OOD Detection
por: Zhang, Bin, et al.
Publicado: (2025)

WindowQuant: Mixed-Precision KV Cache Quantization based on Window-Level Similarity for VLMs Inference Optimization
por: Tao, Wei, et al.
Publicado: (2026)

MoQAE: Mixed-Precision Quantization for Long-Context LLM Inference via Mixture of Quantization-Aware Experts
por: Tao, Wei, et al.
Publicado: (2025)

PRENet: A Plane-Fit Redundancy Encoding Point Cloud Sequence Network for Real-Time 3D Action Recognition
por: He, Shenglin, et al.
Publicado: (2024)

Value-Driven Mixed-Precision Quantization for Patch-Based Inference on Microcontrollers
por: Tao, Wei, et al.
Publicado: (2024)

BAGNet: A Boundary-Aware Graph Attention Network for 3D Point Cloud Semantic Segmentation
por: Tao, Wei, et al.
Publicado: (2025)

RUNA: Object-level Out-of-Distribution Detection via Regional Uncertainty Alignment of Multimodal Representations
por: Zhang, Bin, et al.
Publicado: (2025)

MADLLM: Multivariate Anomaly Detection via Pre-trained LLMs
por: Tao, Wei, et al.
Publicado: (2025)

Streaming Video Question-Answering with In-context Video KV-Cache Retrieval
por: Di, Shangzhe, et al.
Publicado: (2025)

Hierarchical-Task-Aware Multi-modal Mixture of Incremental LoRA Experts for Embodied Continual Learning
por: Jia, Ziqi, et al.
Publicado: (2025)

CogStream: Context-guided Streaming Video Question Answering
por: Zhao, Zicheng, et al.
Publicado: (2025)

StreamKV: Streaming Video Question-Answering with Segment-based KV Cache Retrieval and Compression
por: Chen, Yilong, et al.
Publicado: (2025)

EgoTextVQA: Towards Egocentric Scene-Text Aware Video Question Answering
por: Zhou, Sheng, et al.
Publicado: (2025)

From Inheritance to Saturation: Disentangling the Evolution of Visual Redundancy for Architecture-Aware MLLM Inference Acceleration
por: Shi, Jiaqi, et al.
Publicado: (2026)

Federated Domain Generalization with Domain-specific Soft Prompts Generation
por: Wu, Jianhan, et al.
Publicado: (2025)

Enhancing Multi-Agent Systems via Reinforcement Learning with LLM-based Planner and Graph-based Policy
por: Jia, Ziqi, et al.
Publicado: (2025)

MIRRORTALK: Forging Personalized Avatars Via Disentangled Style and Hierarchical Motion Control
por: Lu, Renjie, et al.
Publicado: (2026)

DIVA: Harnessing the Representation Divergence in Unified Multimodal Models for Mutual Reinforcement
por: Lu, Renjie, et al.
Publicado: (2026)

CARE: Multi-Task Pretraining for Latent Continuous Action Representation in Robot Control
por: Shi, Jiaqi, et al.
Publicado: (2026)

Scene-Text Grounding for Text-Based Video Question Answering
por: Zhou, Sheng, et al.
Publicado: (2024)

Static or Dynamic: Towards Query-Adaptive Token Selection for Video Question Answering
por: Shi, Yumeng, et al.
Publicado: (2025)

Answering from Sure to Uncertain: Uncertainty-Aware Curriculum Learning for Video Question Answering
por: Li, Haopeng, et al.
Publicado: (2024)

Combining Knowledge Graph and LLMs for Enhanced Zero-shot Visual Question Answering
por: Tao, Qian, et al.
Publicado: (2025)

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

SurgViVQA: Temporally-Grounded Video Question Answering for Surgical Scene Understanding
por: Drago, Mauro Orazio, et al.
Publicado: (2025)

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

VLA-InfoEntropy: A Training-Free Vision-Attention Information Entropy Approach for Vision-Language-Action Models Inference Acceleration and Success
por: Liu, Chuhang, et al.
Publicado: (2026)

CLIP-Powered TASS: Target-Aware Single-Stream Network for Audio-Visual Question Answering
por: Jiang, Yuanyuan, et al.
Publicado: (2024)

Enhancing Scene Transition Awareness in Video Generation via Post-Training
por: Shen, Hanwen, et al.
Publicado: (2025)

3D Question Answering for City Scene Understanding
por: Sun, Penglei, et al.
Publicado: (2024)

Cocktail: Chunk-Adaptive Mixed-Precision Quantization for Long-Context LLM Inference
por: Tao, Wei, et al.
Publicado: (2025)

Compositional 4D Dynamic Scenes Understanding with Physics Priors for Video Question Answering
por: Wang, Xingrui, et al.
Publicado: (2024)

Question-Aware Gaussian Experts for Audio-Visual Question Answering
por: Kim, Hongyeob, et al.
Publicado: (2025)

POVQA: Preference-Optimized Video Question Answering with Rationales for Data Efficiency
por: Dahal, Ashim, et al.
Publicado: (2025)

DriveXQA: Cross-modal Visual Question Answering for Adverse Driving Scene Understanding
por: Tao, Mingzhe, et al.
Publicado: (2026)

NoisyEQA: Benchmarking Embodied Question Answering Against Noisy Queries
por: Wu, Tao, et al.
Publicado: (2024)

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

Agentic Keyframe Search for Video Question Answering
por: Fan, Sunqi, et al.
Publicado: (2025)