Image de couverture de livre

Team of One: Cracking Complex Video QA with Model Synergy

Fuente: arXiv

Enregistré dans:

Détails bibliographiques
Auteurs principaux:	Xie, Jun, Zhao, Zhaoran, Guan, Xiongjun, Zhu, Yingjian, Yi, Hongzhu, Wang, Xinming, Chen, Feng, Wang, Zhepeng
Format:	Preprint
Publié:	2025
Sujets:	Computer Vision and Pattern Recognition Artificial Intelligence
Accès en ligne:	Acceder al recurso
Tags:	Ajouter un tag Pas de tags, Soyez le premier à ajouter un tag!

Documents similaires

Four Eyes Are Better Than Two: Harnessing the Collaborative Potential of Large Models via Differentiated Thinking and Complementary Ensembles
par: Xie, Jun, et autres
Publié: (2025)

More Is Better: A MoE-Based Emotion Recognition Framework with Human Preference Alignment
par: Xie, Jun, et autres
Publié: (2025)

Multimodal Video Emotion Recognition with Reliable Reasoning Priors
par: Wang, Zhepeng, et autres
Publié: (2025)

Cross-Modal Registration Between 3D and 2D Fingerprints via Pose-Aware Unwrapping and Point-Cloud Fusion
par: Guan, Xiongjun, et autres
Publié: (2026)

Pose-Specific 3D Fingerprint Unfolding
par: Guan, Xiongjun, et autres
Publié: (2024)

Phase-aggregated Dual-branch Network for Efficient Fingerprint Dense Registration
par: Guan, Xiongjun, et autres
Publié: (2024)

Cross-Dataset Gaze Estimation by Evidential Inter-intra Fusion
par: Wang, Shijing, et autres
Publié: (2024)

PCIE_LAM Solution for Ego4D Looking At Me Challenge
par: Lertniphonphan, Kanokphan, et autres
Publié: (2024)

CVBench: Benchmarking Cross-Video Synergies for Complex Multimodal Reasoning
par: Zhu, Nannan, et autres
Publié: (2025)

WikiSeeker: Rethinking the Role of Vision-Language Models in Knowledge-Based Visual Question Answering
par: Zhu, Yingjian, et autres
Publié: (2026)

Finger Pose Estimation for Under-screen Fingerprint Sensor
par: Guan, Xiongjun, et autres
Publié: (2025)

BiFingerPose: Bimodal Finger Pose Estimation for Touch Devices
par: Guan, Xiongjun, et autres
Publié: (2025)

Direct Regression of Distortion Field from a Single Fingerprint Image
par: Guan, Xiongjun, et autres
Publié: (2024)

Identity-Consistent Multi-Pose Generation of Contactless Fingerprints
par: Pan, Zhiyu, et autres
Publié: (2026)

Joint Identity Verification and Pose Alignment for Partial Fingerprints
par: Guan, Xiongjun, et autres
Publié: (2024)

Regression of Dense Distortion Field from a Single Fingerprint Image
par: Guan, Xiongjun, et autres
Publié: (2024)

Video SimpleQA: Towards Factuality Evaluation in Large Video Language Models
par: Cao, Meng, et autres
Publié: (2025)

ProactiveVideoQA: A Comprehensive Benchmark Evaluating Proactive Interactions in Video Large Language Models
par: Wang, Yueqian, et autres
Publié: (2025)

Hierarchical Memory for Long Video QA
par: Wang, Yiqin, et autres
Publié: (2024)

PCIE_Pose Solution for EgoExo4D Pose and Proficiency Estimation Challenge
par: Chen, Feng, et autres
Publié: (2025)

PCIE_Interaction Solution for Ego4D Social Interaction Challenge
par: Lertniphonphan, Kanokphan, et autres
Publié: (2025)

Fixed-Length Dense Fingerprint Representation with Alignment and Robust Enhancement
par: Pan, Zhiyu, et autres
Publié: (2025)

Latent Fingerprint Matching via Dense Minutia Descriptor
par: Pan, Zhiyu, et autres
Publié: (2024)

Minutiae-Anchored Local Dense Representation for Fingerprint Matching
par: Pan, Zhiyu, et autres
Publié: (2025)

Understanding Complexity in VideoQA via Visual Program Generation
par: Eyzaguirre, Cristobal, et autres
Publié: (2025)

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

CrackSegDiff: Diffusion Probability Model-based Multi-modal Crack Segmentation
par: Jiang, Xiaoyan, et autres
Publié: (2024)

Sports-QA: A Large-Scale Video Question Answering Benchmark for Complex and Professional Sports
par: Li, Haopeng, et autres
Publié: (2024)

Neuromorphic Synergy for Video Binarization
par: Lin, Shijie, et autres
Publié: (2024)

Self-DACE++: Robust Low-Light Enhancement via Efficient Adaptive Curve Estimation
par: Wen, Jianyu, et autres
Publié: (2026)

A DICOM Image De-identification Algorithm in the MIDI-B Challenge
par: Jiang, Hongzhu, et autres
Publié: (2025)

Omni IIE Bench: Benchmarking the Practical Capabilities of Image Editing Models
par: Yang, Yujia, et autres
Publié: (2026)

VoxelNextFusion: A Simple, Unified and Effective Voxel Fusion Framework for Multi-Modal 3D Object Detection
par: Song, Ziying, et autres
Publié: (2024)

Video-in-the-Loop: Span-Grounded Long Video QA with Interleaved Reasoning
par: Wang, Chendong, et autres
Publié: (2025)

Adaptive Dense Evidence Refinement for Video Relational Reasoning for VRR-QA Challenge
par: Sun, Yuyang, et autres
Publié: (2026)

DocVideoQA: Towards Comprehensive Understanding of Document-Centric Videos through Question Answering
par: Wang, Haochen, et autres
Publié: (2025)

Beyond Isolated Facts: Synthesizing Narrative and Grounded Supervision for VideoQA
par: Liang, Jianxin, et autres
Publié: (2025)

DriveDreamer-2: LLM-Enhanced World Models for Diverse Driving Video Generation
par: Zhao, Guosheng, et autres
Publié: (2024)

ReasVQA: Advancing VideoQA with Imperfect Reasoning Process
par: Liang, Jianxin, et autres
Publié: (2025)

StereoDiff: Stereo-Diffusion Synergy for Video Depth Estimation
par: Li, Haodong, et autres
Publié: (2025)