Image de couverture de livre

ReFoCUS: Reinforcement-guided Frame Optimization for Contextual Understanding

Fuente: arXiv

Enregistré dans:

Détails bibliographiques
Auteurs principaux:	Lee, Hosu, Kim, Junho, Kim, Hyunjun, Ro, Yong Man
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

Look Every Frame All at Once: Video-Ma$^2$mba for Efficient Long-form Video Understanding with Multi-Axis Gradient Checkpointing
par: Lee, Hosu, et autres
Publié: (2024)

SALOVA: Segment-Augmented Long Video Assistant for Targeted Retrieval and Routing in Long-Form Video Analysis
par: Kim, Junho, et autres
Publié: (2024)

STRIDE: When to Speak Meets Sequence Denoising for Streaming Video Understanding
par: Kim, Junho, et autres
Publié: (2026)

CODE: Contrasting Self-generated Description to Combat Hallucination in Large Multi-modal Models
par: Kim, Junho, et autres
Publié: (2024)

What if...?: Thinking Counterfactual Keywords Helps to Mitigate Hallucination in Large Multi-modal Models
par: Kim, Junho, et autres
Publié: (2024)

Causal Unsupervised Semantic Segmentation
par: Kim, Junho, et autres
Publié: (2023)

DIP-R1: Deep Inspection and Perception with RL Looking Through and Understanding Complex Scenes
par: Park, Sungjune, et autres
Publié: (2025)

Empathetic Response in Audio-Visual Conversations Using Emotion Preference Optimization and MambaCompressor
par: Kim, Yeonju, et autres
Publié: (2024)

Language-guided Learning for Object Detection Tackling Multiple Variations in Aerial Images
par: Park, Sungjune, et autres
Publié: (2025)

Robust Pedestrian Detection via Constructing Versatile Pedestrian Knowledge Bank
par: Park, Sungjune, et autres
Publié: (2024)

Integrating Language-Derived Appearance Elements with Visual Cues in Pedestrian Detection
par: Park, Sungjune, et autres
Publié: (2023)

GCAgent: Long-Video Understanding via Schematic and Narrative Episodic Memory
par: Yeo, Jeong Hun, et autres
Publié: (2025)

VG3T: Visual Geometry Grounded Gaussian Transformer
par: Kim, Junho, et autres
Publié: (2025)

Pygmalion Effect in Vision: Image-to-Clay Translation for Reflective Geometry Reconstruction
par: Lee, Gayoung, et autres
Publié: (2025)

DETACH : Decomposed Spatio-Temporal Alignment for Exocentric Video and Ambient Sensors with Staged Learning
par: Yoon, Junho, et autres
Publié: (2025)

Visual Speech Recognition for Languages with Limited Labeled Data using Automatic Labels from Whisper
par: Yeo, Jeong Hun, et autres
Publié: (2023)

AV-EmoDialog: Chat with Audio-Visual Users Leveraging Emotional Cues
par: Park, Se Jin, et autres
Publié: (2024)

Prompt Tuning of Deep Neural Networks for Speaker-adaptive Visual Speech Recognition
par: Kim, Minsu, et autres
Publié: (2023)

AV2AV: Direct Audio-Visual Speech to Audio-Visual Speech Translation with Unified Audio-Visual Speech Representation
par: Choi, Jeongsoo, et autres
Publié: (2023)

Robust Grounding with MLLMs Against Occlusion and Small Objects via Language-Guided Semantic Cues
par: Park, Beomchan, et autres
Publié: (2026)

Zero-shot Text-guided Infinite Image Synthesis with LLM guidance
par: Kwon, Soyeong, et autres
Publié: (2024)

Diversify, Contextualize, and Adapt: Efficient Entropy Modeling for Neural Image Codec
par: Kim, Jun-Hyuk, et autres
Publié: (2024)

FPANet: Frequency-based Video Demoireing using Frame-level Post Alignment
par: Oh, Gyeongrok, et autres
Publié: (2023)

Let's Go Real Talk: Spoken Dialogue Model for Face-to-Face Conversation
par: Park, Se Jin, et autres
Publié: (2024)

ReXSonoVQA: A Video QA Benchmark for Procedure-Centric Ultrasound Understanding
par: Wang, Xucheng, et autres
Publié: (2026)

FrameMind: Frame-Interleaved Video Reasoning via Reinforcement Learning
par: Ge, Haonan, et autres
Publié: (2025)

ReSpinQuant: Efficient Layer-Wise LLM Quantization via Subspace Residual Rotation Approximation
par: Kim, Suyoung, et autres
Publié: (2026)

Multimodal Alignment with Cross-Attentive GRUs for Fine-Grained Video Understanding
par: Kim, Namho, et autres
Publié: (2025)

Classifier-guided CLIP Distillation for Unsupervised Multi-label Classification
par: Kim, Dongseob, et autres
Publié: (2025)

Holi-DETR: Holistic Fashion Item Detection Leveraging Contextual Information
par: Kwon, Youngchae, et autres
Publié: (2025)

Enhanced Vision-Language Models for Diverse Sensor Understanding: Cost-Efficient Optimization and Benchmarking
par: Chung, Sangyun, et autres
Publié: (2024)

Is 'Right' Right? Enhancing Object Orientation Understanding in Multimodal Large Language Models through Egocentric Instruction Tuning
par: Jung, Ji Hyeok, et autres
Publié: (2024)

Re-Identifying Kākā with AI-Automated Video Key Frame Extraction
par: Maddigan, Paula, et autres
Publié: (2025)

Frame Guidance: Training-Free Guidance for Frame-Level Control in Video Diffusion Models
par: Jang, Sangwon, et autres
Publié: (2025)

Safety Alignment Backfires: Preventing the Re-emergence of Suppressed Concepts in Fine-tuned Text-to-Image Diffusion Models
par: Kim, Sanghyun, et autres
Publié: (2024)

Fine-Grained Pillar Feature Encoding Via Spatio-Temporal Virtual Grid for 3D Object Detection
par: Park, Konyul, et autres
Publié: (2024)

Domain-Invariant Per-Frame Feature Extraction for Cross-Domain Imitation Learning with Visual Observations
par: Kim, Minung, et autres
Publié: (2025)

CLIP Can Understand Depth
par: Kim, Sohee, et autres
Publié: (2024)

FoPru: Focal Pruning for Efficient Large Vision-Language Models
par: Jiang, Lei, et autres
Publié: (2024)

CUPID: Contextual Understanding of Prompt-conditioned Image Distributions
par: Zhao, Yayan, et autres
Publié: (2024)