Cover Image

Which Way Did It Move? Diagnosing and Overcoming Directional Motion Blindness in Video-LLMs

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Lee, Jongseo, Lee, Hyuntak, Kim, Sunghun, Kim, Sooa, Chung, Jihoon, Choi, Jinwoo
Format:	Preprint
Published:	2026
Subjects:	Computer Vision and Pattern Recognition
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

CAST: Cross-Attention in Space and Time for Video Action Recognition
by: Lee, Dongho, et al.
Published: (2023)

CA^2ST: Cross-Attention in Audio, Space, and Time for Holistic Video Recognition
by: Lee, Jongseo, et al.
Published: (2025)

Disentangled Concepts Speak Louder Than Words: Explainable Video Action Recognition
by: Lee, Jongseo, et al.
Published: (2025)

PCEvE: Part Contribution Evaluation Based Model Explanation for Human Figure Drawing Assessment and Beyond
by: Lee, Jongseo, et al.
Published: (2024)

PCBEAR: Pose Concept Bottleneck for Explainable Action Recognition
by: Lee, Jongseo, et al.
Published: (2025)

ESSENTIAL: Episodic and Semantic Memory Integration for Video Class-Incremental Learning
by: Lee, Jongseo, et al.
Published: (2025)

Restoration-Aligned Generative Flow Models for Blind Motion Deblurring
by: Kim, Insoo, et al.
Published: (2026)

MASH-VLM: Mitigating Action-Scene Hallucination in Video-LLMs through Disentangled Spatial-Temporal Representations
by: Bae, Kyungho, et al.
Published: (2025)

TransFlow: Motion Knowledge Transfer from Video Diffusion Models to Video Salient Object Detection
by: Cho, Suhwan, et al.
Published: (2025)

Real-World Efficient Blind Motion Deblurring via Blur Pixel Discretization
by: Kim, Insoo, et al.
Published: (2024)

Improving Motion in Image-to-Video Models via Adaptive Low-Pass Guidance
by: Choi, June Suk, et al.
Published: (2025)

Controllable Long-term Motion Generation with Extended Joint Targets
by: Lee, Eunjong, et al.
Published: (2025)

EVIDENT: Routing MLLM Adaptation through Entity-Grounded Visual Evidence for Cross-Domain Video Temporal Grounding
by: Ahn, Geo, et al.
Published: (2026)

Video Diffusion Models are Strong Video Inpainter
by: Lee, Minhyeok, et al.
Published: (2024)

STATIC : Surface Temporal Affine for TIme Consistency in Video Monocular Depth Estimation
by: Yang, Sunghun, et al.
Published: (2024)

Effective SAM Combination for Open-Vocabulary Semantic Segmentation
by: Lee, Minhyeok, et al.
Published: (2024)

DEVIAS: Learning Disentangled Video Representations of Action and Scene
by: Bae, Kyungho, et al.
Published: (2023)

PoseBridge: Bridging the Skeletonization Gap for Zero-Shot Skeleton-Based Action Recognition
by: Lee, Sanghyeon, et al.
Published: (2026)

How to Move Your Dragon: Text-to-Motion Synthesis for Large-Vocabulary Objects
by: Lee, Wonkwang, et al.
Published: (2025)

SlotVTG: Object-Centric Adapter for Generalizable Video Temporal Grounding
by: Han, Jiwook, et al.
Published: (2026)

HiCM$^2$: Hierarchical Compact Memory Modeling for Dense Video Captioning
by: Kim, Minkuk, et al.
Published: (2024)

Do You Remember? Dense Video Captioning with Cross-Modal Memory Retrieval
by: Kim, Minkuk, et al.
Published: (2024)

Leveraging Image Augmentation for Object Manipulation: Towards Interpretable Controllability in Object-Centric Learning
by: Kim, Jinwoo, et al.
Published: (2023)

Text to Blind Motion
by: Kim, Hee Jae, et al.
Published: (2024)

MATRIX: Mask Track Alignment for Interaction-aware Video Generation
by: Jin, Siyoon, et al.
Published: (2025)

Safety Alignment Backfires: Preventing the Re-emergence of Suppressed Concepts in Fine-tuned Text-to-Image Diffusion Models
by: Kim, Sanghyun, et al.
Published: (2024)

NOAH: Benchmarking Narrative Prior driven Hallucination and Omission in Video Large Language Models
by: Lee, Kyuho, et al.
Published: (2025)

A Review of Image Retrieval Techniques: Data Augmentation and Adversarial Learning Approaches
by: Jinwoo, Kim
Published: (2024)

MonoCLUE : Object-Aware Clustering Enhances Monocular 3D Object Detection
by: Yang, Sunghun, et al.
Published: (2025)

Video Parallel Scaling: Aggregating Diverse Frame Subsets for VideoLLMs
by: Chung, Hyungjin, et al.
Published: (2025)

DAFT-GAN: Dual Affine Transformation Generative Adversarial Network for Text-Guided Image Inpainting
by: Lee, Jihoon, et al.
Published: (2024)

CoMoGaussian: Continuous Motion-Aware Gaussian Splatting from Motion-Blurred Images
by: Lee, Jungho, et al.
Published: (2025)

Infusing Environmental Captions for Long-Form Video Language Grounding
by: Lee, Hyogun, et al.
Published: (2024)

Flashback: Memory-Driven Zero-shot, Real-time Video Anomaly Detection
by: Lee, Hyogun, et al.
Published: (2025)

Context-Aware Input Orchestration for Video Inpainting
by: Kim, Hoyoung, et al.
Published: (2024)

Treating Motion as Option with Output Selection for Unsupervised Video Object Segmentation
by: Cho, Suhwan, et al.
Published: (2023)

NVS-Adapter: Plug-and-Play Novel View Synthesis from a Single Image
by: Jeong, Yoonwoo, et al.
Published: (2023)

HypeVPR: Exploring Hyperbolic Space for Perspective to Equirectangular Visual Place Recognition
by: Woo, Suhan, et al.
Published: (2025)

Generating Human Motion Videos using a Cascaded Text-to-Video Framework
by: Nam, Hyelin, et al.
Published: (2025)

SMURF: Continuous Dynamics for Motion-Deblurring Radiance Fields
by: Lee, Jungho, et al.
Published: (2024)