Image de couverture de livre

PO-GUISE+: Pose and object guided transformer token selection for efficient driver action recognition

Fuente: arXiv

Enregistré dans:

Détails bibliographiques
Auteurs principaux:	Pizarro, Ricardo, Valle, Roberto, Barea, Rafael, Buenaposada, Jose M., Baumela, Luis, Bergasa, Luis Miguel
Format:	Preprint
Publié:	2024
Sujets:	Computer Vision and Pattern Recognition
Accès en ligne:	Acceder al recurso
Tags:	Ajouter un tag Pas de tags, Soyez le premier à ajouter un tag!

Documents similaires

Beyond Flicker: Detecting Kinematic Inconsistencies for Generalizable Deepfake Video Detection
par: Cobo, Alejandro, et autres
Publié: (2025)

Auditing Demographic Bias in Facial Landmark Detection for Fair Human-Robot Interaction
par: Parte, Pablo, et autres
Publié: (2026)

On the representation and methodology for wide and short range head pose estimation
par: Cobo, Alejandro, et autres
Publié: (2024)

BEBLID: Boosted efficient binary local image descriptor
par: Suárez, Iago, et autres
Publié: (2024)

BAdaCost: Multi-class Boosting with Costs
par: Fernández-Baldera, Antonio, et autres
Publié: (2024)

Fast and Efficient Transformer-based Method for Bird's Eye View Instance Prediction
par: Antunes-García, Miguel, et autres
Publié: (2024)

BEVPredFormer: Spatio-temporal Attention for BEV Instance Prediction in Autonomous Driving
par: Antunes-García, Miguel, et autres
Publié: (2026)

Identifying actionable driver mutations in lung cancer using an efficient Asymmetric Transformer Decoder
par: Brattoli, Biagio, et autres
Publié: (2025)

CFE-PPAR: Compression-friendly encryption for privacy-preserving action recognition leveraging video transformers
par: Lin, Haiwei, et autres
Publié: (2026)

Can masking background and object reduce static bias for zero-shot action recognition?
par: Fukuzawa, Takumi, et autres
Publié: (2025)

Egocentric zone-aware action recognition across environments
par: Peirone, Simone Alberto, et autres
Publié: (2024)

Semantic-guided modeling of spatial relation and object co-occurrence for indoor scene recognition
par: Song, Chuanxin, et autres
Publié: (2023)

Hybrid guided variational autoencoder for visual place recognition
par: Wang, Ni, et autres
Publié: (2026)

Zero-shot sketch-based remote sensing image retrieval based on multi-level and attention-guided tokenization
par: Yang, Bo, et autres
Publié: (2024)

EmMixformer: Mix transformer for eye movement recognition
par: Qin, Huafeng, et autres
Publié: (2024)

PoseAnything: Universal Pose-guided Video Generation with Part-aware Temporal Coherence
par: Wang, Ruiyan, et autres
Publié: (2025)

Multi-model learning by sequential reading of untrimmed videos for action recognition
par: Kamiya, Kodai, et autres
Publié: (2024)

Pose-invariant face recognition via feature-space pose frontalization
par: Stanishev, Nikolay, et autres
Publié: (2025)

Pose is all you need: The pose only group activity recognition system (POGARS)
par: Thilakarathne, Haritha, et autres
Publié: (2021)

Real-time 3D human action recognition based on Hyperpoint sequence
par: Li, Xing, et autres
Publié: (2021)

Can VLMs be used on videos for action recognition? LLMs are Visual Reasoning Coordinators
par: Lunia, Harsh
Publié: (2024)

Smooth regularization for efficient video recognition
par: Goldman, Gil, et autres
Publié: (2025)

Rethink Sparse Signals for Pose-guided Text-to-image Generation
par: Xuan, Wenjie, et autres
Publié: (2025)

Less yet robust: crucial region selection for scene recognition
par: Zhang, Jianqi, et autres
Publié: (2024)

Location-guided Head Pose Estimation for Fisheye Image
par: Li, Bing, et autres
Publié: (2024)

Inability of spatial transformations of CNN feature maps to support invariant recognition
par: Jansson, Ylva, et autres
Publié: (2020)

TruePose: Human-Parsing-guided Attention Diffusion for Full-ID Preserving Pose Transfer
par: Xu, Zhihong, et autres
Publié: (2025)

SMART: Scene-motion-aware human action recognition framework for mental disorder group
par: Lai, Zengyuan, et autres
Publié: (2024)

Multi-modality action recognition based on dual feature shift in vehicle cabin monitoring
par: Lin, Dan, et autres
Publié: (2024)

AniGaussian: Animatable Gaussian Avatar with Pose-guided Deformation
par: Li, Mengtian, et autres
Publié: (2025)

Not all tokens contribute equally to diffusion learning
par: Zhang, Guoqing, et autres
Publié: (2026)

Comparison of Autoencoders for tokenization of ASL datasets
par: Praun-Petrovic, Vouk, et autres
Publié: (2025)

The impact of Compositionality in Zero-shot Multi-label action recognition for Object-based tasks
par: Calabrese, Carmela, et autres
Publié: (2024)

Extended multi-stream temporal-attention module for skeleton-based human action recognition (HAR)
par: Mehmood, Faisal, et autres
Publié: (2024)

Using joint angles based on the international biomechanical standards for human action recognition and related tasks
par: Schlegel, Kevin, et autres
Publié: (2024)

Two-stream joint matching method based on contrastive learning for few-shot action recognition
par: Deng, Long, et autres
Publié: (2024)

Gabor-guided transformer for single image deraining
par: He, Sijin, et autres
Publié: (2024)

AvatarPose: Avatar-guided 3D Pose Estimation of Close Human Interaction from Sparse Multi-view Videos
par: Lu, Feichi, et autres
Publié: (2024)

Meta-DAN: towards an efficient prediction strategy for page-level handwritten text recognition
par: Coquenet, Denis
Publié: (2025)

Contrastive learning-based video quality assessment-jointed video vision transformer for video recognition
par: Sun, Jian, et autres
Publié: (2026)