Copertina

Decomposed Attention Fusion in MLLMs for Training-Free Video Reasoning Segmentation

Fuente: arXiv

Salvato in:

Dettagli Bibliografici
Autori principali:	Han, Su Ho, Hyun, Jeongseok, Lee, Pilhyeon, Shim, Minho, Wee, Dongyoon, Kim, Seon Joo
Natura:	Preprint
Pubblicazione:	2025
Soggetti:	Computer Vision and Pattern Recognition
Accesso online:	Acceder al recurso
Tags:	Aggiungi Tag Nessun Tag, puoi essere il primo ad aggiungerne!!

Documenti analoghi

Multi-Granular Spatio-Temporal Token Merging for Training-Free Acceleration of Video LLMs
di: Hyun, Jeongseok, et al.
Pubblicazione: (2025)

Classification Matters: Improving Video Action Detection with Class-Specific Attention
di: Lee, Jinsung, et al.
Pubblicazione: (2024)

Exploring Scalability of Self-Training for Open-Vocabulary Temporal Action Localization
di: Hyun, Jeongseok, et al.
Pubblicazione: (2024)

Video-Oasis: Rethinking Evaluation of Video Understanding
di: Lim, Geuntaek, et al.
Pubblicazione: (2026)

ActionSwitch: Class-agnostic Detection of Simultaneous Actions in Streaming Videos
di: Kang, Hyolim, et al.
Pubblicazione: (2024)

Why Can't I Open My Drawer? Mitigating Object-Driven Shortcuts in Zero-Shot Compositional Action Recognition
di: Ahn, Geo, et al.
Pubblicazione: (2026)

Prototypes are Balanced Units for Efficient and Effective Partially Relevant Video Retrieval
di: Moon, WonJun, et al.
Pubblicazione: (2025)

BAM-DETR: Boundary-Aligned Moment Detection Transformer for Temporal Sentence Grounding in Videos
di: Lee, Pilhyeon, et al.
Pubblicazione: (2023)

Learning to Enhance Aperture Phasor Field for Non-Line-of-Sight Imaging
di: Cho, In, et al.
Pubblicazione: (2024)

Which Concepts to Forget and How to Refuse? Decomposing Concepts for Continual Unlearning in Large Vision-Language Models
di: Jin, Hyundong, et al.
Pubblicazione: (2026)

MFP: Making Full Use of Probability Maps for Interactive Image Segmentation
di: Lee, Chaewon, et al.
Pubblicazione: (2024)

SeiT++: Masked Token Modeling Improves Storage-efficient Training
di: Lee, Minhyun, et al.
Pubblicazione: (2023)

Training-Free Reasoning and Reflection in MLLMs
di: Wei, Hongchen, et al.
Pubblicazione: (2025)

MaskRIS: Semantic Distortion-aware Data Augmentation for Referring Image Segmentation
di: Lee, Minhyun, et al.
Pubblicazione: (2024)

Internal-External Boundary Attention Fusion for Glass Surface Segmentation
di: Han, Dongshen, et al.
Pubblicazione: (2023)

A Simple Baseline with Single-encoder for Referring Image Segmentation
di: Yu, Seonghoon, et al.
Pubblicazione: (2024)

Coherent Human-Scene Reconstruction from Multi-Person Multi-View Video in a Single Pass
di: Kim, Sangmin, et al.
Pubblicazione: (2026)

Leveraging Temporal Contextualization for Video Action Recognition
di: Kim, Minji, et al.
Pubblicazione: (2024)

VISAGE: Video Instance Segmentation with Appearance-Guided Enhancement
di: Kim, Hanjung, et al.
Pubblicazione: (2023)

Domain Reduction Strategy for Non Line of Sight Imaging
di: Shim, Hyunbo, et al.
Pubblicazione: (2023)

Regularizing Dynamic Radiance Fields with Kinematic Fields
di: Im, Woobin, et al.
Pubblicazione: (2024)

Humans as a Calibration Pattern: Dynamic 3D Scene Reconstruction from Unsynchronized and Uncalibrated Videos
di: Choi, Changwoon, et al.
Pubblicazione: (2024)

Motion-Oriented Compositional Neural Radiance Fields for Monocular Dynamic Human Modeling
di: Kim, Jaehyeok, et al.
Pubblicazione: (2024)

RL makes MLLMs see better than SFT
di: Song, Junha, et al.
Pubblicazione: (2025)

FreeRet: MLLMs as Training-Free Retrievers
di: Zhu, Yuhan, et al.
Pubblicazione: (2025)

Autoregressive Universal Video Segmentation Model
di: Heo, Miran, et al.
Pubblicazione: (2025)

mEOL: Training-Free Instruction-Guided Multimodal Embedder for Vector Graphics and Image Retrieval
di: Kim, Kyeong Seon, et al.
Pubblicazione: (2026)

DiffuseSlide: Training-Free High Frame Rate Video Generation Diffusion
di: Hwang, Geunmin, et al.
Pubblicazione: (2025)

OmniSparse: Training-Aware Fine-Grained Sparse Attention for Long-Video MLLMs
di: Chen, Feng, et al.
Pubblicazione: (2025)

Dual Prototype Attention for Unsupervised Video Object Segmentation
di: Cho, Suhwan, et al.
Pubblicazione: (2022)

CoCoGaussian: Leveraging Circle of Confusion for Gaussian Splatting from Defocused Images
di: Lee, Jungho, et al.
Pubblicazione: (2024)

Video-R1: Reinforcing Video Reasoning in MLLMs
di: Feng, Kaituo, et al.
Pubblicazione: (2025)

Revisiting Reliability in the Reasoning-based Pose Estimation Benchmark
di: Kim, Junsu, et al.
Pubblicazione: (2025)

Latent Space Super-Resolution for Higher-Resolution Image Generation with Diffusion Models
di: Jeong, Jinho, et al.
Pubblicazione: (2025)

UniSkill: Imitating Human Videos via Cross-Embodiment Skill Representations
di: Kim, Hanjung, et al.
Pubblicazione: (2025)

Hierarchically Structured Neural Bones for Reconstructing Animatable Objects from Casual Videos
di: Jeon, Subin, et al.
Pubblicazione: (2024)

FusionEdit: Semantic Fusion and Attention Modulation for Training-Free Image Editing
di: Lai, Yongwen, et al.
Pubblicazione: (2026)

Training-Free Spatio-temporal Decoupled Reasoning Video Segmentation with Adaptive Object Memory
di: Zhu, Zhengtong, et al.
Pubblicazione: (2026)

Graph-to-Frame RAG: Visual-Space Knowledge Fusion for Training-Free and Auditable Video Reasoning
di: Yang, Songyuan, et al.
Pubblicazione: (2026)

Unleashing the Temporal-Spatial Reasoning Capacity of GPT for Training-Free Audio and Language Referenced Video Object Segmentation
di: Huang, Shaofei, et al.
Pubblicazione: (2024)