Papers Action Classification
“Action Classification” 태그가 달린 논문 485편 · 필터 해제
Semi Supervised Meta Learning for Spatiotemporal Learning
We approached the goal of applying meta-learning to self-supervised masked autoencoders for spatiotemporal learning in three steps. Broadly, we seek to understand the impact of applying meta-learning to existing state-of…
Action ClassificationClassificationMeta-LearningRepresentation Learning+1Spiking Two-Stream Methods with Unsupervised STDP-based Learning for Action Recognition
Video analysis is a computer vision task that is useful for many applications like surveillance, human-machine interaction, and autonomous vehicles. Deep Convolutional Neural Networks (CNNs) are currently the state-of-th…
Action ClassificationAction RecognitionAutonomous VehiclesSeeing the Pose in the Pixels: Learning Pose-Aware Representations in Vision Transformers
Human perception of surroundings is often guided by the various poses present within the environment. Many computer vision tasks, such as human action recognition and robot imitation learning, rely on pose-based entities…
Action ClassificationAction RecognitionImitation LearningPose Prediction+2How Object Information Improves Skeleton-based Human Action Recognition in Assembly Tasks
As the use of collaborative robots (cobots) in industrial manufacturing continues to grow, human action recognition for effective human-robot collaboration becomes increasingly important. This ability is crucial for cobo…
Action ClassificationAction RecognitionInstance SegmentationObject+3Human Action Recognition in Egocentric Perspective Using 2D Object and Hands Pose
Egocentric action recognition is essential for healthcare and assistive technology that relies on egocentric cameras because it allows for the automatic and continuous monitoring of activities of daily living (ADLs) with…
Action ClassificationAction RecognitionTemporal Action LocalizationHomE: Homography-Equivariant Video Representation Learning
Recent advances in self-supervised representation learning have enabled more efficient and robust model performance without relying on extensive labeled data. However, most works are still focused on images, with few wor…
Action ClassificationAction RecognitionRepresentation LearningSelf-Supervised LearningHiera: A Hierarchical Vision Transformer without the Bells-and-Whistles
Modern hierarchical vision transformers have added several vision-specific components in the pursuit of supervised classification performance. While these components lead to effective accuracies and attractive FLOP count…
Action ClassificationAction RecognitionAction Recognition In VideosImage Classification+3ONE-PEACE: Exploring One General Representation Model Toward Unlimited Modalities
In this work, we explore a scalable way for building a general representation model toward unlimited modalities. We release ONE-PEACE, a highly extensible model with 4B parameters that can seamlessly align and integrate …
1 Image, 2*2 StitchiAction ClassificationAudioCapsAudio Classification+18Self-Supervised Video Representation Learning via Latent Time Navigation
Self-supervised video representation learning aimed at maximizing similarity between different temporal segments of one video, in order to enforce feature persistence over time. This leads to loss of pertinent informatio…
Action ClassificationAction RecognitionContrastive LearningRepresentation LearningAssemblyHands: Towards Egocentric Activity Understanding via 3D Hand Pose Estimation
We present AssemblyHands, a large-scale benchmark dataset with accurate 3D hand pose annotations, to facilitate the study of egocentric activities with challenging hand-object interactions. The dataset includes synchroni…
3D Hand Pose EstimationAction ClassificationHand Pose EstimationPose EstimationImplicit Temporal Modeling with Learnable Alignment for Video Recognition
Contrastive language-image pretraining (CLIP) has demonstrated remarkable success in various image tasks. However, how to extend CLIP with effective temporal modeling is still an open and crucial problem. Existing factor…
Action ClassificationAction RecognitionVideo RecognitionVicTR: Video-conditioned Text Representations for Activity Recognition
Vision-Language models (VLMs) have excelled in the image-domain -- especially in zero-shot settings -- thanks to the availability of vast pretraining data (i.e., paired image-text samples). However for videos, such paire…
Action ClassificationActivity RecognitionFormZero-Shot Action RecognitionVideoMAE V2: Scaling Video Masked Autoencoders with Dual Masking
Scale is the primary factor for building a powerful foundation model that could well generalize to a variety of downstream tasks. However, it is still challenging to train video foundation models with billions of paramet…
Action ClassificationAction RecognitionAction Recognition In VideosDecoder+3Unmasked Teacher: Towards Training-Efficient Video Foundation Models
Video Foundation Models (VFMs) have received limited exploration due to high computational costs and data scarcity. Previous VFMs rely on Image Foundation Models (IFMs), which face challenges in transferring to the video…
Action ClassificationAction Recognitioncross-modal alignmentSpatio-Temporal Action Localization+4The effectiveness of MAE pre-pretraining for billion-scale pretraining
This paper revisits the standard pretrain-then-finetune paradigm used in computer vision for visual recognition tasks. Typically, state-of-the-art foundation models are pretrained using large scale (weakly) supervised da…
Action ClassificationAction RecognitionFew-Shot Image Classificationimage-classification+6ViC-MAE: Self-Supervised Representation Learning from Images and Video with Contrastive Masked Autoencoders
We propose ViC-MAE, a model that combines both Masked AutoEncoders (MAE) and contrastive learning. ViC-MAE is trained using a global featured obtained by pooling the local representations learned under an MAE reconstruct…
Action ClassificationAction RecognitionContrastive Learningimage-classification+4Multi-modal Prompting for Low-Shot Temporal Action Localization
In this paper, we consider the problem of temporal action localization under low-shot (zero-shot & few-shot) scenario, with the goal of detecting and classifying the action instances from arbitrary categories within some…
Action ClassificationAction LocalizationTemporal Action LocalizationDual-path Adaptation from Image to Video Transformers
In this paper, we efficiently transfer the surpassing representation power of the vision foundation models, such as ViT and Swin, for video understanding with only a few trainable parameters. Previous adaptation methods …
Action ClassificationAction RecognitionAction Recognition In VideosActivity Recognition+2Classification of Primitive Manufacturing Tasks from Filtered Event Data
Collaborative robots are increasingly present in industry to support human activities. However, to make the human-robot collaborative process more effective, there are several challenges to be addressed. Collaborative ro…
Action ClassificationClassificationScaling Vision Transformers to 22 Billion Parameters
The scaling of Transformers has driven breakthrough capabilities for language models. At present, the largest large language models (LLMs) contain upwards of 100B parameters. Vision Transformers (ViT) have introduced the…
Action ClassificationFairnessImage ClassificationLinear-Probe Classification+2