https://github.com/mzolfaghari/ECO-efficient-video-understanding
공식 코드ECO: Efficient Convolutional Network for Online Video Understanding
Papers with Code 아카이브
Action Recognition
태스크의 하위 분류와 논문·코드·평가·기법·데이터셋을 탐색하세요.
- 하위 태스크
- 15
- 평가표
- 56
- 보존된 평가 기록
- 650
Action Recognition is a computer vision task that involves recognizing human actions in videos or images. The goal is to classify and categorize the actions being performed in the video or image into a predefined set of action classes.
In the video domain, it is an open question whether training an action classification network on a sufficiently large dataset, will give a similar boost in performance when applied to a different temporal task or dataset. The challenges of building video datasets has meant that most popular benchmarks for action recognition are small, having on the order of 10k videos.
Please note some benchmarks may be located in the Action Classification or Video Classification tasks, e.g. Kinetics-400.
코드
관련 논문과 평가 결과에 연결된 구현입니다. 출처에서 확인된 저자 구현에는 공식 코드 표시가 있습니다.
https://github.com/naraysa/gzsl-od
공식 코드Out-of-Distribution Detection for Generalized Zero-Shot Action Recognition
https://github.com/naver-ai/tc-clip
공식 코드Leveraging Temporal Contextualization for Video Action Recognition
https://github.com/nawidsayed/Cross-and-Learn
공식 코드https://github.com/nazmul-karim170/FIP-Fisher-Backdoor-Removal
공식 코드Fisher Information guided Purification against Backdoor Attacks
https://github.com/nazmul-karim170/NFT-Augmented-Backdoor-Purification
공식 코드Augmented Neural Fine-Tuning for Efficient Backdoor Purification
https://github.com/nbahador/-fine_tuned_gpt2_model_on_epilepsy_related_pubmed_abstracts
공식 코드https://github.com/ncgarcia/DMCL
공식 코드DMCL: Distillation Multiple Choice Learning for Multimodal Action Recognition
https://github.com/ncgarcia/modality-distillation
공식 코드Modality Distillation with Multiple Stream Networks for Action Recognition
https://github.com/necla-ml/cpr
공식 코드Self-supervised Video Representation Learning with Cascade Positive Retrieval
https://github.com/nervjack2/propertyneurons
공식 코드https://github.com/neuroailab/VIE
공식 코드Unsupervised Learning from Video with Deep Neural Embeddings
https://github.com/newsdata/SoccerDB
공식 코드SoccerDB: A Large-Scale Database for Comprehensive Video Understanding
https://github.com/nifangbaage/explicit-visual-prompt
공식 코드Explicit Visual Prompting for Low-Level Structure Segmentations
https://github.com/nihaomiao/wacv23_tsnet
공식 코드Cross-identity Video Motion Retargeting with Joint Transformation and Synthesis
https://github.com/ningwang2049/laiar
공식 코드https://github.com/nishantrai18/CoCon
공식 코드https://github.com/nishantrai18/homage
공식 코드Home Action Genome: Cooperative Compositional Action Understanding
https://github.com/nkliuyifang/me-gcn
공식 코드Learning Mutual Excitation for Hand-to-Hand and Human-to-Human Interaction Recognition
https://github.com/nlpkeg/D4S
공식 코드Reasons and Solutions for the Decline in Model Performance after Editing
https://github.com/nmegha2601/anticipatr
공식 코드Rethinking Learning Approaches for Long-Term Action Anticipation
https://github.com/nntanaka/Fourier-Analysis-for-Skeleton-based-Action-Recognition
공식 코드https://github.com/noboevbo/ehpi_action_recognition
공식 코드Simple yet efficient real-time pose-based action recognition
https://github.com/noureldien/timeception
공식 코드https://github.com/okankop/Efficient-3DCNNs
공식 코드https://github.com/olga-zats/goal_consistency
공식 코드https://github.com/olga-zats/gtda
공식 코드Gated Temporal Diffusion for Stochastic Long-Term Dense Anticipation
https://github.com/oliverhxh/skeletongcl
공식 코드Graph Contrastive Learning for Skeleton-based Action Recognition
https://github.com/olivesgatech/DARai
공식 코드Hierarchical and Multimodal Data for Daily Activity Understanding
https://github.com/olivesgatech/gradtrust
공식 코드Counterfactual Gradients-based Quantification of Prediction Trust in Neural Networks
https://github.com/ombretta/longterm_datasets
공식 코드Are current long-term video understanding datasets long-term?
https://github.com/ombretta/videobagnet
공식 코드Video BagNet: short temporal receptive fields increase robustness in long-term action recognition
https://github.com/opanhw/FiNE
공식 코드Precise Localization of Memories: A Fine-grained Neuron-level Knowledge Editing Technique for LLMs
https://github.com/opanhw/MM_Neurons
공식 코드Finding and Editing Multi-Modal Neurons in Pre-Trained Transformers
https://github.com/open-mmlab/mmaction
공식 코드https://github.com/openai/CLIP
공식 코드Learning Transferable Visual Models From Natural Language Supervision
출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.