paper-with-me

Papers

Pose-guided multi-task video transformer for driver action recognition

2024-07-18 · Ricardo Pizarro, Roberto Valle, Luis Miguel Bergasa, José M. Buenaposada, Luis Baumela

We investigate the task of identifying situations of distracted driving through analysis of in-car videos. To tackle this challenge we introduce a multi-task video transformer that predicts both distracted actions and driver pose. Leveraging VideoMAEv2, a large pre-trained architecture, our approach incorporates semantic information from human keypoint locations to enhance action recognition and decrease computational overhead by minimizing the number of spatio-temporal tokens. By guiding token selection with pose and class information, we notably reduce the model's computational requirements while preserving the baseline accuracy. Our model surpasses existing state-of-the art results in driver action recognition while exhibiting superior efficiency compared to current video transformer-based approaches.

📄 PDF Abstract BibTeX arXiv:2407.13750

Code (0)

등록된 구현이 없습니다.

Tasks

Action Recognition

Similar Papers 제목 키워드 기반

DiT as Real-Time Rerenderer: Streaming Video Stylization with Autoregressive Diffusion Transformer

2026-04-15 · Hengye Lyu, Zisu Li, Yue Hong, Yueting Weng 외 arxiv

Recent advances in video generation models has significantly accelerated video generation and related downstream tasks. Among these, video stylization holds important research value in areas such as immersive application…

Video Generation

IVT: An End-to-End Instance-guided Video Transformer for 3D Pose Estimation

2022-08-06 · Zhongwei Qiu, Qiansheng Yang, Jian Wang, Dongmei Fu

Video 3D human pose estimation aims to localize the 3D coordinates of human joints from videos. Recent transformer-based approaches focus on capturing the spatiotemporal information from sequential 2D poses, which cannot…

2D Pose Estimation3D Human Pose Estimation3D Multi-Person Pose Estimation3D Pose Estimation+1

Transferable-guided Attention Is All You Need for Video Domain Adaptation

2024-07-01 · André Sacilotti, Samuel Felipe dos Santos, Nicu Sebe, Jurandy Almeida

Unsupervised domain adaptation (UDA) in videos is a challenging task that remains not well explored compared to image-based UDA techniques. Although vision transformers (ViT) achieve state-of-the-art performance in many …

AllDomain AdaptationUnsupervised Domain Adaptation

Scene Graph-guided SegCaptioning Transformer with Fine-grained Alignment for Controllable Video Segmentation and Captioning

2026-03-21 · Xu Zhang, Jin Yuan, BinHong Yang, Xuan Liu 외 arxiv

Recent advancements in multimodal large models have significantly bridged the representation gap between diverse modalities, catalyzing the evolution of video multimodal interpretation, which enhances users' understandin…

Video Segmentation

TokenMotion: Motion-Guided Vision Transformer for Video Camouflaged Object Detection Via Learnable Token Selection

2023-11-05 · Zifan Yu, Erfan Bank Tavakoli, Meida Chen, Suya You 외

The area of Video Camouflaged Object Detection (VCOD) presents unique challenges in the field of computer vision due to texture similarities between target objects and their surroundings, as well as irregular motion patt…

object-detectionObject Detection