Image de couverture de livre

Video Detective: Seek Critical Clues Recurrently to Answer Question from Long Videos

Fuente: arXiv

Enregistré dans:

Détails bibliographiques
Auteurs principaux:	Du, Henghui, Zhang, Chunjie, Chen, Xi, Zhou, Chang, Hu, Di
Format:	Preprint
Publié:	2025
Sujets:	Computer Vision and Pattern Recognition
Accès en ligne:	Acceder al recurso
Tags:	Ajouter un tag Pas de tags, Soyez le premier à ajouter un tag!

Documents similaires

APPO: Attention-guided Perception Policy Optimization for Video Reasoning
par: Du, Henghui, et autres
Publié: (2026)

Video-o3: Native Interleaved Clue Seeking for Long Video Multi-Hop Reasoning
par: Zeng, Xiangyu, et autres
Publié: (2026)

Crab: A Unified Audio-Visual Scene Understanding Model with Explicit Cooperation
par: Du, Henghui, et autres
Publié: (2025)

Track the Answer: Extending TextVQA from Image to Video with Spatio-Temporal Clues
par: Zhang, Yan, et autres
Publié: (2024)

CG-Bench: Clue-grounded Question Answering Benchmark for Long Video Understanding
par: Chen, Guo, et autres
Publié: (2024)

An Empirical Study on How Video-LLMs Answer Video Questions
par: Gou, Chenhui, et autres
Publié: (2025)

VideoDetective: Clue Hunting via both Extrinsic Query and Intrinsic Relevance for Long Video Understanding
par: Yang, Ruoliu, et autres
Publié: (2026)

Boosting Audio Visual Question Answering via Key Semantic-Aware Cues
par: Li, Guangyao, et autres
Publié: (2024)

Grounded Question-Answering in Long Egocentric Videos
par: Di, Shangzhe, et autres
Publié: (2023)

Align and Aggregate: Compositional Reasoning with Video Alignment and Answer Aggregation for Video Question-Answering
par: Liao, Zhaohe, et autres
Publié: (2024)

LLMs Meet Long Video: Advancing Long Video Question Answering with An Interactive Visual Adapter in LLMs
par: Li, Yunxin, et autres
Publié: (2024)

MOVE: Motion-Guided Few-Shot Video Object Segmentation
par: Ying, Kaining, et autres
Publié: (2025)

Looking Beyond Visible Cues: Implicit Video Question Answering via Dual-Clue Reasoning
par: Chen, Tieyuan, et autres
Publié: (2025)

SAM3-DMS: Decoupled Memory Selection for Multi-target Video Segmentation of SAM3
par: Shen, Ruiqi, et autres
Publié: (2026)

Admitting Ignorance Helps the Video Question Answering Models to Answer
par: Li, Haopeng, et autres
Publié: (2025)

Clue Matters: Leveraging Latent Visual Clues to Empower Video Reasoning
par: zhang, Kaixin, et autres
Publié: (2026)

MovieChat+: Question-aware Sparse Memory for Long Video Question Answering
par: Song, Enxin, et autres
Publié: (2024)

Decoupling Static and Hierarchical Motion Perception for Referring Video Segmentation
par: He, Shuting, et autres
Publié: (2024)

VideoSeek: Long-Horizon Video Agent with Tool-Guided Seeking
par: Lin, Jingyang, et autres
Publié: (2026)

A Benchmark and Multi-Agent System for Instruction-driven Cinematic Video Compilation
par: Zhang, Peixuan, et autres
Publié: (2026)

Mode Seeking meets Mean Seeking for Fast Long Video Generation
par: Cai, Shengqu, et autres
Publié: (2026)

AffectSeek: Agentic Affective Understanding in Long Videos under Vague User Queries
par: Zhang, Zhen, et autres
Publié: (2026)

StreamReady: Learning What to Answer and When in Long Streaming Videos
par: Azad, Shehreen, et autres
Publié: (2026)

Grounded Multi-Hop VideoQA in Long-Form Egocentric Videos
par: Chen, Qirui, et autres
Publié: (2024)

Active Video Perception: Iterative Evidence Seeking for Agentic Long Video Understanding
par: Wang, Ziyang, et autres
Publié: (2025)

VideoSEAL: Mitigating Evidence Misalignment in Agentic Long Video Understanding by Decoupling Answer Authority
par: Qiu, Chenhao, et autres
Publié: (2026)

ClueTracer: Question-to-Vision Clue Tracing for Training-Free Hallucination Suppression in Multimodal Reasoning
par: Xi, Gongli, et autres
Publié: (2026)

VideoOdyssey: A Benchmark for Ultra-Long-Context and Omni-Modal Video Understanding
par: He, Haichen, et autres
Publié: (2026)

VideoLLaMB: Long Streaming Video Understanding with Recurrent Memory Bridges
par: Wang, Yuxuan, et autres
Publié: (2024)

LongCaptioning: Unlocking the Power of Long Video Caption Generation in Large Multimodal Models
par: Wei, Hongchen, et autres
Publié: (2025)

Narrative Aligned Long Form Video Question Answering
par: Jain, Rahul, et autres
Publié: (2026)

Can Video LLMs Refuse to Answer? Alignment for Answerability in Video Large Language Models
par: Yoon, Eunseop, et autres
Publié: (2025)

Crab$^{+}$: A Scalable and Unified Audio-Visual Scene Understanding Model with Explicit Cooperation
par: Cai, Dongnuan, et autres
Publié: (2026)

Streaming Video Question-Answering with In-context Video KV-Cache Retrieval
par: Di, Shangzhe, et autres
Publié: (2025)

Seek-and-Solve: Benchmarking MLLMs for Visual Clue-Driven Reasoning in Daily Scenarios
par: Li, Xiaomin, et autres
Publié: (2026)

Video-as-Answer: Predict and Generate Next Video Event with Joint-GRPO
par: Cheng, Junhao, et autres
Publié: (2025)

A Simple LLM Framework for Long-Range Video Question-Answering
par: Zhang, Ce, et autres
Publié: (2023)

Unsupervised Video Highlight Detection by Learning from Audio and Visual Recurrence
par: Islam, Zahidul, et autres
Publié: (2024)

Long-Form Answers to Visual Questions from Blind and Low Vision People
par: Huh, Mina, et autres
Publié: (2024)

MeViS: A Multi-Modal Dataset for Referring Motion Expression Video Segmentation
par: Ding, Henghui, et autres
Publié: (2025)