https://github.com/facebookresearch/EgoVLPv2
공식 코드EgoVLPv2: Egocentric Video-Language Pre-training with Fusion in the Backbone
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
코드
관련 논문과 평가 결과에 연결된 구현입니다. 출처에서 확인된 저자 구현에는 공식 코드 표시가 있습니다.
https://github.com/facebookresearch/GDT
공식 코드On Compositions of Transformations in Contrastive Self-Supervised Learning
https://github.com/facebookresearch/GloRe
공식 코드https://github.com/facebookresearch/Motionformer
공식 코드Keeping Your Eye on the Ball: Trajectory Attention in Video Transformers
https://github.com/facebookresearch/R2Plus1D
공식 코드A Closer Look at Spatiotemporal Convolutions for Action Recognition
https://github.com/facebookresearch/SlowFast
공식 코드https://github.com/facebookresearch/TimeSformer
공식 코드Is Space-Time Attention All You Need for Video Understanding?
https://github.com/facebookresearch/VMZ
공식 코드Video Classification with Channel-Separated Convolutional Networks
https://github.com/facebookresearch/assemblyhands-toolkit
공식 코드Benchmarks and Challenges in Pose Estimation for Egocentric Hand Interactions with Objects
https://github.com/facebookresearch/detectron2/tree/main/projects/MViTv2
공식 코드MViTv2: Improved Multiscale Vision Transformers for Classification and Detection
https://github.com/facebookresearch/egocentricuseradaptation
공식 코드EgoAdapt: A multi-stream evaluation study of adaptation to real-world egocentric user video
https://github.com/facebookresearch/glitr
공식 코드GliTr: Glimpse Transformers with Spatiotemporal Consistency for Online Action Prediction
https://github.com/facebookresearch/hiera
공식 코드Hiera: A Hierarchical Vision Transformer without the Bells-and-Whistles
https://github.com/facebookresearch/imu2clip
공식 코드IMU2CLIP: Multimodal Contrastive Learning for IMU Motion Sensors from Egocentric Videos and Text
https://github.com/facebookresearch/lavila
공식 코드https://github.com/facebookresearch/maws
공식 코드The effectiveness of MAE pre-pretraining for billion-scale pretraining
https://github.com/facebookresearch/memvit
공식 코드MeMViT: Memory-Augmented Multiscale Vision Transformer for Efficient Long-Term Video Recognition
https://github.com/facebookresearch/mvit
공식 코드MViTv2: Improved Multiscale Vision Transformers for Classification and Detection
https://github.com/facebookresearch/omnivore
공식 코드https://github.com/facebookresearch/video-long-term-feature-banks
공식 코드https://github.com/facebookresearch/video-nonlocal-net
공식 코드https://github.com/facebookresearch/vissl
공식 코드Vision Models Are More Robust And Fair When Pretrained On Uncurated Images Without Supervision
https://github.com/facebookresearch/vjepa2
공식 코드V-JEPA 2: Self-Supervised Video Models Enable Understanding, Prediction and Planning
https://github.com/fandulu/DD-Net
공식 코드Make Skeleton-based Action Recognition Model Smaller, Faster and Better
https://github.com/fandulu/asad
공식 코드Actor-identified Spatiotemporal Action Detection --- Detecting Who Is Doing What in Videos
https://github.com/fbarez/neuroplasticity
공식 코드https://github.com/fcakyon/content-moderation-deep-learning
공식 코드Deep Architectures for Content Moderation and Movie Content Rating
https://github.com/feichtenhofer/st-resnet
공식 코드Spatiotemporal Residual Networks for Video Action Recognition
https://github.com/feichtenhofer/twostreamfusion
공식 코드Two-Stream Convolutional Networks for Action Recognition in Videos
https://github.com/fepegar/gestures-miccai-2021
공식 코드Transfer Learning of Deep Spatiotemporal Networks to Model Arbitrarily Long Videos of Seizures
https://github.com/feyzaakyurek/dune
공식 코드https://github.com/ffyyytt/tsm-mmvpr
공식 코드Action Recognition Using Temporal Shift Module and Ensemble Learning
https://github.com/firework8/brl
공식 코드Balanced Representation Learning for Long-tailed Skeleton-based Action Recognition
https://github.com/flamewei123/DEPN
공식 코드DEPN: Detecting and Editing Privacy Neurons in Pretrained Language Models
https://github.com/floft/calda
공식 코드CALDA: Improving Multi-Source Time Series Domain Adaptation with Contrastive Adversarial Learning
https://github.com/fmi-basel/neural-decoding-RSNN
공식 코드Decoding finger velocity from cortical spike trains with recurrent spiking neural networks
출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.