Copertina

$\text{PKS}^4$:Parallel Kinematic Selective State Space Scanners for Efficient Video Understanding

Fuente: arXiv

Salvato in:

Dettagli Bibliografici
Autori principali:	Zeng, Lingjie, Zhang, Hailun, Wang, Xiwen, Zhao, Qijun
Natura:	Preprint
Pubblicazione:	2026
Soggetti:	Computer Vision and Pattern Recognition
Accesso online:	Acceder al recurso
Tags:	Aggiungi Tag Nessun Tag, puoi essere il primo ad aggiungerne!!

Documenti analoghi

Dehallu3D: Hallucination-Mitigated 3D Generation from Single Image via Cyclic View Consistency Refinement
di: Wang, Xiwen, et al.
Pubblicazione: (2026)

VideoMamba: State Space Model for Efficient Video Understanding
di: Li, Kunchang, et al.
Pubblicazione: (2024)

FOCUS: Efficient Keyframe Selection for Long Video Understanding
di: Zhu, Zirui, et al.
Pubblicazione: (2025)

LiquidTAD: Efficient Temporal Action Detection via Parallel Liquid-Inspired Temporal Relaxation
di: Sun, Zepeng, et al.
Pubblicazione: (2026)

FlexSelect: Flexible Token Selection for Efficient Long Video Understanding
di: Zhang, Yunzhu, et al.
Pubblicazione: (2025)

Efficient Self-Supervised Video Hashing with Selective State Spaces
di: Wang, Jinpeng, et al.
Pubblicazione: (2024)

Unleashing the Power of Motion and Depth: A Selective Fusion Strategy for RGB-D Video Salient Object Detection
di: He, Jiahao, et al.
Pubblicazione: (2025)

MAMBA4D: Efficient Long-Sequence Point Cloud Video Understanding with Disentangled Spatial-Temporal State Space Models
di: Liu, Jiuming, et al.
Pubblicazione: (2024)

CamoSAM2: Motion-Appearance Induced Auto-Refining Prompts for Video Camouflaged Object Detection
di: Zhang, Xin, et al.
Pubblicazione: (2025)

Video Mamba Suite: State Space Model as a Versatile Alternative for Video Understanding
di: Chen, Guo, et al.
Pubblicazione: (2024)

MambaVF: State Space Model for Efficient Video Fusion
di: Zhao, Zixiang, et al.
Pubblicazione: (2026)

On the Perception Bottleneck of VLMs for Chart Understanding
di: Liu, Junteng, et al.
Pubblicazione: (2025)

StreamForest: Efficient Online Video Understanding with Persistent Event Memory
di: Zeng, Xiangyu, et al.
Pubblicazione: (2025)

Mamba-based Spatio-Frequency Motion Perception for Video Camouflaged Object Detection
di: Li, Xin, et al.
Pubblicazione: (2025)

OmniMamba: Efficient and Unified Multimodal Understanding and Generation via State Space Models
di: Zou, Jialv, et al.
Pubblicazione: (2025)

Event-Anchored Frame Selection for Effective Long-Video Understanding
di: Chen, Wang, et al.
Pubblicazione: (2026)

VideoMamba: Spatio-Temporal Selective State Space Model
di: Park, Jinyoung, et al.
Pubblicazione: (2024)

Wavelet-based Frame Selection by Detecting Semantic Boundary for Long Video Understanding
di: Chen, Wang, et al.
Pubblicazione: (2026)

S3T-Former: A Purely Spike-Driven State-Space Topology Transformer for Skeleton Action Recognition
di: Zheng, Naichuan, et al.
Pubblicazione: (2026)

An Efficient Streaming Video Understanding Framework with Agentic Control
di: Liu, Jinming, et al.
Pubblicazione: (2026)

Selective Structured State Space for Multispectral-fused Small Target Detection
di: Zhang, Qianqian, et al.
Pubblicazione: (2025)

Adaptively Bypassing Vision Transformer Blocks for Efficient Visual Tracking
di: Yang, Xiangyang, et al.
Pubblicazione: (2024)

GIFT: Global Irreplaceability Frame Targeting for Efficient Video Understanding
di: Ma, Junpeng, et al.
Pubblicazione: (2026)

Trajectory-aware Shifted State Space Models for Online Video Super-Resolution
di: Zhu, Qiang, et al.
Pubblicazione: (2025)

M-LLM Based Video Frame Selection for Efficient Video Understanding
di: Hu, Kai, et al.
Pubblicazione: (2025)

TRAM: Global Trajectory and Motion of 3D Humans from in-the-wild Videos
di: Wang, Yufu, et al.
Pubblicazione: (2024)

KPM-Bench: A Kinematic Parsing Motion Benchmark for Fine-grained Motion-centric Video Understanding
di: Lin, Boda, et al.
Pubblicazione: (2026)

On Structured State-Space Duality
di: Hu, Jerry Yao-Chieh, et al.
Pubblicazione: (2025)

State Space Prompting via Gathering and Spreading Spatio-Temporal Information for Video Understanding
di: Zhou, Jiahuan, et al.
Pubblicazione: (2025)

From Articulated Kinematics to Routed Visual Control for Action-Conditioned Surgical Video Generation
di: Li, Bohan, et al.
Pubblicazione: (2026)

Ego4o: Egocentric Human Motion Capture and Understanding from Multi-Modal Input
di: Wang, Jian, et al.
Pubblicazione: (2025)

ECMamba: Consolidating Selective State Space Model with Retinex Guidance for Efficient Multiple Exposure Correction
di: Dong, Wei, et al.
Pubblicazione: (2024)

Explicit Motion Handling and Interactive Prompting for Video Camouflaged Object Detection
di: Zhang, Xin, et al.
Pubblicazione: (2024)

$\text{S}^{3}$Mamba: Arbitrary-Scale Super-Resolution via Scaleable State Space Model
di: Xia, Peizhe, et al.
Pubblicazione: (2024)

Towards Long Video Understanding via Fine-detailed Video Story Generation
di: You, Zeng, et al.
Pubblicazione: (2024)

Towards Training-Free Scene Text Editing
di: Li, Yubo, et al.
Pubblicazione: (2026)

Feeling the Space: Egomotion-Aware Video Representation for Efficient and Accurate 3D Scene Understanding
di: Shi, Shuyao, et al.
Pubblicazione: (2026)

Dynamic Patch-aware Enrichment Transformer for Occluded Person Re-Identification
di: Zhang, Xin, et al.
Pubblicazione: (2024)

Stable Part Diffusion 4D: Multi-View RGB and Kinematic Parts Video Generation
di: Zhang, Hao, et al.
Pubblicazione: (2025)

StereoDiff: Stereo-Diffusion Synergy for Video Depth Estimation
di: Li, Haodong, et al.
Pubblicazione: (2025)