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/prouast/deep-intake-detection
공식 코드Learning deep representations for video-based intake gesture detection
https://github.com/ptoupas/harflow3d
공식 코드HARFLOW3D: A Latency-Oriented 3D-CNN Accelerator Toolflow for HAR on FPGA Devices
https://github.com/purduedigitaltwin/m2dar
공식 코드M$^2$DAR: Multi-View Multi-Scale Driver Action Recognition with Vision Transformer
https://github.com/pvtokmakov/video_cluster
공식 코드Unsupervised Learning of Video Representations via Dense Trajectory Clustering
https://github.com/q1xiangchen/vmps
공식 코드https://github.com/qilimk/biggan-am
공식 코드https://github.com/qinghua-zhou/stealth-edits
공식 코드https://github.com/qiuzh20/tuning-keys-v.s.-values
공식 코드Empirical Study on Updating Key-Value Memories in Transformer Feed-forward Layers
https://github.com/qiwang233/dailydvs-200
공식 코드DailyDVS-200: A Comprehensive Benchmark Dataset for Event-Based Action Recognition
https://github.com/qizhongtan/d2st-adapter
공식 코드D$^2$ST-Adapter: Disentangled-and-Deformable Spatio-Temporal Adapter for Few-shot Action Recognition
https://github.com/qizhou000/DAFNet
공식 코드DAFNet: Dynamic Auxiliary Fusion for Sequential Model Editing in Large Language Models
https://github.com/qizhou000/RECIPE
공식 코드Lifelong Knowledge Editing for LLMs with Retrieval-Augmented Continuous Prompt Learning
https://github.com/qizhou000/visedit
공식 코드https://github.com/quiil/quiil_thompson_solution
공식 코드https://github.com/quqxui/medlasa
공식 코드Editing Factual Knowledge and Explanatory Ability of Medical Large Language Models
https://github.com/radu1999/walkandtext
공식 코드Aligning Actions and Walking to LLM-Generated Textual Descriptions
https://github.com/rahmyyy/gavd
공식 코드Computer Vision for Clinical Gait Analysis: A Gait Abnormality Video Dataset
https://github.com/rana2149/actnetformer
공식 코드ActNetFormer: Transformer-ResNet Hybrid Method for Semi-Supervised Action Recognition in Videos
https://github.com/raphaelmemmesheimer/skeleton-dml
공식 코드Skeleton-DML: Deep Metric Learning for Skeleton-Based One-Shot Action Recognition
https://github.com/raphaelmemmesheimer/sl-dml
공식 코드SL-DML: Signal Level Deep Metric Learning for Multimodal One-Shot Action Recognition
https://github.com/rate-accuracy-mvcnn/main
공식 코드Rate-Accuracy Trade-Off In Video Classification With Deep Convolutional Neural Networks
https://github.com/realcrane/BASAR-Black-box-Attack-on-Skeletal-Action-Recognition
공식 코드https://github.com/realcrane/SMART
공식 코드Understanding the Robustness of Skeleton-based Action Recognition under Adversarial Attack
https://github.com/reddyav1/rocog-v2
공식 코드Synthetic-to-Real Domain Adaptation for Action Recognition: A Dataset and Baseline Performances
https://github.com/reddyav1/unite
공식 코드Unsupervised Video Domain Adaptation with Masked Pre-Training and Collaborative Self-Training
https://github.com/redwang/DTGRM
공식 코드Temporal Relational Modeling with Self-Supervision for Action Segmentation
https://github.com/rhwxmx/eventmamba
공식 코드https://github.com/richardtml/divita
공식 코드https://github.com/ricky-xian/mitfas
공식 코드https://github.com/ricky-xian/pmi-sampler
공식 코드PMI Sampler: Patch Similarity Guided Frame Selection for Aerial Action Recognition
https://github.com/rllab/rllab
공식 코드Benchmarking Deep Reinforcement Learning for Continuous Control
https://github.com/rmokady/JOKR
공식 코드JOKR: Joint Keypoint Representation for Unsupervised Cross-Domain Motion Retargeting
https://github.com/roberto1648/adversarial-perturbations-on-images-and-videos
공식 코드Targeted Nonlinear Adversarial Perturbations in Images and Videos
https://github.com/rongchangli/zscar_c2c
공식 코드C2C: Component-to-Composition Learning for Zero-Shot Compositional Action Recognition
https://github.com/ruitian12/resformer
공식 코드출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.