Papers with Code 아카이브
Activity Recognition
태스크의 하위 분류와 논문·코드·평가·기법·데이터셋을 탐색하세요.
- 하위 태스크
- 11
- 평가표
- 4
- 보존된 평가 기록
- 10
Human Activity Recognition is the problem of identifying events performed by humans given a video input. It is formulated as a binary (or multiclass) classification problem of outputting activity class labels. Activity Recognition is an important problem with many societal applications including smart surveillance, video search/retrieval, intelligent robots, and other monitoring systems.
Source: Learning Latent Sub-events in Activity Videos Using Temporal Attention Filters
논문
이 태스크와 하위 분야의 관련 논문입니다. 실제 성능 비교는 평가 결과에서 확인하세요.
A Video-based End-to-end Pipeline for Non-nutritive Sucking Action Recognition and Segmentation in Young Infants
Channel Phase Processing in Wireless Networks for Human Activity Recognition
Colo-SCRL: Self-Supervised Contrastive Representation Learning for Colonoscopic Video Retrieval
Unmasked Teacher: Towards Training-Efficient Video Foundation Models
Rethinking matching-based few-shot action recognition
CycleACR: Cycle Modeling of Actor-Context Relations for Video Action Detection
TimeBalance: Temporally-Invariant and Temporally-Distinctive Video Representations for Semi-Supervised Action Recognition
Provable Robustness for Streaming Models with a Sliding Window
Structured Video-Language Modeling with Temporal Grouping and Spatial Grounding
Prompt-Guided Zero-Shot Anomaly Action Recognition using Pretrained Deep Skeleton Features
Unified Keypoint-based Action Recognition Framework via Structured Keypoint Pooling
Multimodal video and IMU kinematic dataset on daily life activities using affordable devices (VIDIMU)
Multi-view knowledge distillation transformer for human action recognition
3Mformer: Multi-order Multi-mode Transformer for Skeletal Action Recognition
Enlarging Instance-specific and Class-specific Information for Open-set Action Recognition
Towards Scalable Neural Representation for Diverse Videos
The effectiveness of MAE pre-pretraining for billion-scale pretraining
A Large-scale Study of Spatiotemporal Representation Learning with a New Benchmark on Action Recognition
Learning and Verification of Task Structure in Instructional Videos
Self-distillation for surgical action recognition
ViC-MAE: Self-Supervised Representation Learning from Images and Video with Contrastive Masked Autoencoders
Automatic evaluation of herding behavior in towed fishing gear using end-to-end training of CNN and attention-based networks
Explicit Visual Prompting for Low-Level Structure Segmentations
Actionlet-Dependent Contrastive Learning for Unsupervised Skeleton-Based Action Recognition
HMC: Hierarchical Mesh Coarsening for Skeleton-free Motion Retargeting
A Multi-Task Deep Learning Approach for Sensor-based Human Activity Recognition and Segmentation
Modeling the Trade-off of Privacy Preservation and Activity Recognition on Low-Resolution Images
Augmenting and Aligning Snippets for Few-Shot Video Domain Adaptation
Video Action Recognition with Attentive Semantic Units
Dual-path Adaptation from Image to Video Transformers
Synthetic-to-Real Domain Adaptation for Action Recognition: A Dataset and Baseline Performances
Mobiprox: Supporting Dynamic Approximate Computing on Mobiles
Skinned Motion Retargeting with Residual Perception of Motion Semantics & Geometry
MAtch, eXpand and Improve: Unsupervised Finetuning for Zero-Shot Action Recognition with Language Knowledge
EgoViT: Pyramid Video Transformer for Egocentric Action Recognition
출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.