https://github.com/vt-vl-lab/video-data-aug
공식 코드Learning Representational Invariances for Data-Efficient Action Recognition
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/vturrisi/udavt
공식 코드Unsupervised Domain Adaptation for Video Transformers in Action Recognition
https://github.com/vut-hfut/micro-action
공식 코드Benchmarking Micro-action Recognition: Dataset, Methods, and Applications
https://github.com/vvhj/tsgcnext
공식 코드https://github.com/wang-chen/KCC
공식 코드https://github.com/wang-chen/LGL
공식 코드https://github.com/wang-chen/lgl-action-recognition
공식 코드https://github.com/wangbing1416/hami-m3d
공식 코드Harmfully Manipulated Images Matter in Multimodal Misinformation Detection
https://github.com/wangjk666/omnivid
공식 코드OmniVid: A Generative Framework for Universal Video Understanding
https://github.com/wangjs96/graph-in-graph-neural-network
공식 코드https://github.com/wanglimin/ARTNet
공식 코드https://github.com/wanglimin/UntrimmedNet
공식 코드UntrimmedNets for Weakly Supervised Action Recognition and Detection
https://github.com/wangyijunlyy/selafd
공식 코드SelaFD:Seamless Adaptation of Vision Transformer Fine-tuning for Radar-based Human Activity
https://github.com/wangyu-ustc/largescalewashing
공식 코드https://github.com/wangyu-ustc/memoryllm
공식 코드https://github.com/wangywust/deepedit
공식 코드https://github.com/wanliyoung/collapse-in-model-editing
공식 코드The Butterfly Effect of Model Editing: Few Edits Can Trigger Large Language Models Collapse
https://github.com/wanliyoung/revisit-editing-evaluation
공식 코드The Mirage of Model Editing: Revisiting Evaluation in the Wild
https://github.com/watonomous/action-classification
공식 코드RALACs: Action Recognition in Autonomous Vehicles using Interaction Encoding and Optical Flow
https://github.com/wayveai/driving-with-llms
공식 코드Driving with LLMs: Fusing Object-Level Vector Modality for Explainable Autonomous Driving
https://github.com/wdkhuans/SALIENCE
공식 코드https://github.com/wei-tim/YOWO
공식 코드You Only Watch Once: A Unified CNN Architecture for Real-Time Spatiotemporal Action Localization
https://github.com/weichuanw/llm-based-mt-via-model-editing
공식 코드https://github.com/weiqian1/IGA
공식 코드An Interactive Greedy Approach to Group Sparsity in High Dimensions
https://github.com/weiyifan1023/RaKE
공식 코드Assessing Knowledge Editing in Language Models via Relation Perspective
https://github.com/weiyifan1023/knowledge-edit-based-on-relation-perspective
공식 코드Assessing Knowledge Editing in Language Models via Relation Perspective
https://github.com/wenbohuang1002/soap
공식 코드https://github.com/wengwanjiang/usdrl
공식 코드USDRL: Unified Skeleton-Based Dense Representation Learning with Multi-Grained Feature Decorrelation
https://github.com/wengzejia1/open-vclip
공식 코드Open-VCLIP: Transforming CLIP to an Open-vocabulary Video Model via Interpolated Weight Optimization
https://github.com/wenhanwu95/freqmixformer
공식 코드Frequency Guidance Matters: Skeletal Action Recognition by Frequency-Aware Mixed Transformer
https://github.com/wgcban/apt
공식 코드https://github.com/whwu95/ATM
공식 코드What Can Simple Arithmetic Operations Do for Temporal Modeling?
https://github.com/whwu95/BIKE
공식 코드https://github.com/whwu95/DSANet
공식 코드DSANet: Dynamic Segment Aggregation Network for Video-Level Representation Learning
https://github.com/whwu95/MVFNet
공식 코드MVFNet: Multi-View Fusion Network for Efficient Video Recognition
https://github.com/whwu95/text4vis
공식 코드Revisiting Classifier: Transferring Vision-Language Models for Video Recognition
출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.