Cover Image

An Empirical Study for Representations of Videos in Video Question Answering via MLLMs

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Li, Zhi, Wang, Yanan, Niu, Hao, Vizcarra, Julio, Taya, Masato
Format:	Preprint
Published:	2025
Subjects:	Information Retrieval I.2.10
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

ReCoVR: Closing the Loop in Interactive Composed Video Retrieval
by: Zhang, Bingqing, et al.
Published: (2026)

MIRA: Empowering One-Touch AI Services on Smartphones with MLLM-based Instruction Recommendation
by: Bian, Zhipeng, et al.
Published: (2025)

ZeShot-VQA: Zero-Shot Visual Question Answering Framework with Answer Mapping for Natural Disaster Damage Assessment
by: Karimi, Ehsan, et al.
Published: (2025)

Video-STR: Reinforcing MLLMs in Video Spatio-Temporal Reasoning with Relation Graph
by: Wang, Wentao, et al.
Published: (2025)

Evaluating Perspectival Biases in Cross-Modal Retrieval
by: Saengsukhiran, Teerapol, et al.
Published: (2025)

ReaderLM-v2: Small Language Model for HTML to Markdown and JSON
by: Wang, Feng, et al.
Published: (2025)

Robust Test-time Video-Text Retrieval: Benchmarking and Adapting for Query Shifts
by: Zhang, Bingqing, et al.
Published: (2026)

Multimedia Verification Through Multi-Agent Deep Research Multimodal Large Language Models
by: Le, Huy Hoan, et al.
Published: (2025)

TriAlignGR: Triangular Multitask Alignment with Multimodal Deep Interest Mining for Generative Recommendation
by: Zeng, Yangchen, et al.
Published: (2026)

Spatially-Grounded Document Retrieval via Patch-to-Region Relevance Propagation
by: Georgiou, Athos
Published: (2025)

DocRetriever: A Plug-and-Play Framework for Multimodal Document Retrieval with Comprehensive Benchmark
by: Hu, Ruofan, et al.
Published: (2026)

Fre-Res: Frequency-Residual Video Token Compression for Efficient Video MLLMs
by: Feng, Yigui, et al.
Published: (2026)

Fast 3D point clouds retrieval for Large-scale 3D Place Recognition
by: Zede, Chahine-Nicolas, et al.
Published: (2025)

Loom: Hybrid Retrieval-Scoring Outfit Recommendation with Semantic Material Compatibility and Occasion-Aware Embedding Priors
by: Berlia, Anushree
Published: (2026)

jina-clip-v2: Multilingual Multimodal Embeddings for Text and Images
by: Koukounas, Andreas, et al.
Published: (2024)

CLIP-Joint-Detect: End-to-End Joint Training of Object Detectors with Contrastive Vision-Language Supervision
by: Raoufi, Behnam, et al.
Published: (2025)

Look, Listen, and Answer: Overcoming Biases for Audio-Visual Question Answering
by: Ma, Jie, et al.
Published: (2024)

Cinéaste: A Fine-grained Contextual Movie Question Answering Benchmark
by: Shah, Nisarg A., et al.
Published: (2025)

RDPO: Real Data Preference Optimization for Physics Consistency Video Generation
by: Qian, Wenxu, et al.
Published: (2025)

EduFlow: Advancing MLLMs' Problem-Solving Proficiency through Multi-Stage, Multi-Perspective Critique
by: Zhu, Chenglin, et al.
Published: (2025)

Storing Less, Finding More: How Novelty Filtering Improves Cross-Modal Retrieval on Edge Cameras
by: Abdelwahab, Sherif
Published: (2026)

AdSum: Two-stream Audio-visual Summarization for Automated Video Advertisement Clipping
by: Xie, Wen, et al.
Published: (2025)

KARMA-MV: A Benchmark for Causal Question Answering on Music Videos
by: Ghosh, Archishman, et al.
Published: (2026)

EmoVerse: A MLLMs-Driven Emotion Representation Dataset for Interpretable Visual Emotion Analysis
by: Guo, Yijie, et al.
Published: (2025)

U-Net-Like Spiking Neural Networks for Single Image Dehazing
by: Li, Huibin, et al.
Published: (2025)

An Evaluation of a Visual Question Answering Strategy for Zero-shot Facial Expression Recognition in Still Images
by: Castrillón-Santana, Modesto, et al.
Published: (2025)

PhysVideoGenerator: Towards Physically Aware Video Generation via Latent Physics Guidance
by: Satish, Siddarth Nilol Kundur, et al.
Published: (2026)

Robust Visual Question Answering: Datasets, Methods, and Future Challenges
by: Ma, Jie, et al.
Published: (2023)

Context-Aware Network Based on Multi-scale Spatio-temporal Attention for Action Recognition in Videos
by: Li, Xiaoyang, et al.
Published: (2025)

Higher education assessment practice in the era of generative AI tools
by: Ogunleye, Bayode, et al.
Published: (2024)

Interpreting Video Representations with Spatio-Temporal Sparse Autoencoders
by: Dokme, Atahan, et al.
Published: (2026)

Cross-Modal Transfer from Memes to Videos: Addressing Data Scarcity in Hateful Video Detection
by: Wang, Han, et al.
Published: (2025)

Video-CoE: Reinforcing Video Event Prediction via Chain of Events
by: Su, Qile, et al.
Published: (2026)

Hierarchical Multi-Positive Contrastive Learning for Patent Image Retrieval
by: Kavimandan, Kshitij, et al.
Published: (2025)

SoccerLens: Grounded Soccer Video Understanding Beyond Accuracy
by: Elsharkawi, Ismael, et al.
Published: (2026)

FASH-iCNN: Making Editorial Fashion Identity Inspectable Through Multimodal CNN Probing
by: Adeyemi, Morayo Danielle, et al.
Published: (2026)

DynFocus: Dynamic Cooperative Network Empowers LLMs with Video Understanding
by: Han, Yudong, et al.
Published: (2024)

VidNum-1.4K: A Comprehensive Benchmark for Video-based Numerical Reasoning
by: Cui, Shaoyang, et al.
Published: (2026)

A Simple Baseline for Streaming Video Understanding
by: Shen, Yujiao, et al.
Published: (2026)

Computer Vision for Clinical Gait Analysis: A Gait Abnormality Video Dataset
by: Ranjan, Rahm, et al.
Published: (2024)