Papers with Code 아카이브
Video Understanding
태스크의 하위 분류와 논문·코드·평가·기법·데이터셋을 탐색하세요.
- 하위 태스크
- 7
- 평가표
- 0
- 보존된 평가 기록
- 0
A crucial task of Video Understanding is to recognise and localise (in space and time) different actions or events appearing in the video.
코드
관련 논문과 평가 결과에 연결된 구현입니다. 출처에서 확인된 저자 구현에는 공식 코드 표시가 있습니다.
https://github.com/deepaknlp/medvidqacl
공식 코드A Dataset for Medical Instructional Video Classification and Question Answering
https://github.com/deepcs233/TIN
공식 코드https://github.com/deepsportradar/camera-calibration-challenge
공식 코드DeepSportradar-v1: Computer Vision Dataset for Sports Understanding with High Quality Annotations
https://github.com/deepsportradar/instance-segmentation-challenge
공식 코드DeepSportradar-v1: Computer Vision Dataset for Sports Understanding with High Quality Annotations
https://github.com/deepsportradar/player-reidentification-challenge
공식 코드DeepSportradar-v1: Computer Vision Dataset for Sports Understanding with High Quality Annotations
https://github.com/dhg-wei/topa
공식 코드TOPA: Extending Large Language Models for Video Understanding via Text-Only Pre-Alignment
https://github.com/dibschat/tempAgg
공식 코드Temporal Aggregate Representations for Long-Range Video Understanding
https://github.com/dingkeyan93/DISTS
공식 코드Image Quality Assessment: Unifying Structure and Texture Similarity
https://github.com/doc-doc/NExT-QA
공식 코드NExT-QA:Next Phase of Question-Answering to Explaining Temporal Actions
https://github.com/doc-doc/videoqa-llms
공식 코드https://github.com/dominickrei/egoexo4adl
공식 코드https://github.com/dominickrei/poseawarevt
공식 코드Seeing the Pose in the Pixels: Learning Pose-Aware Representations in Vision Transformers
https://github.com/dot27/temporal-tessellation
공식 코드Temporal Tessellation: A Unified Approach for Video Analysis
https://github.com/dragonlzm/pave
공식 코드https://github.com/dvlab-research/LSDBench
공식 코드Does Your Vision-Language Model Get Lost in the Long Video Sampling Dilemma?
https://github.com/dvlab-research/visionzip
공식 코드VisionZip: Longer is Better but Not Necessary in Vision Language Models
https://github.com/eavnjeong/ief-vad
공식 코드Uncertainty-Weighted Image-Event Multimodal Fusion for Video Anomaly Detection
https://github.com/eceo-epfl/mammalps
공식 코드MammAlps: A multi-view video behavior monitoring dataset of wild mammals in the Swiss Alps
https://github.com/edengabriel/taskweave
공식 코드https://github.com/egoschema/egoschema
공식 코드EgoSchema: A Diagnostic Benchmark for Very Long-form Video Language Understanding
https://github.com/elenabbbuenob/tsa-actionseg
공식 코드Leveraging triplet loss for unsupervised action segmentation
https://github.com/elicassion/3dtrl
공식 코드Learning Viewpoint-Agnostic Visual Representations by Recovering Tokens in 3D Space
https://github.com/epic-kitchens/epic-fields-code
공식 코드https://github.com/eric-ai-lab/mmworld
공식 코드MMWorld: Towards Multi-discipline Multi-faceted World Model Evaluation in Videos
https://github.com/erktkdg/MTFL
공식 코드https://github.com/evgeneybogatyrev/super-resolution-metric
공식 코드SR+Codec: a Benchmark of Super-Resolution for Video Compression Bitrate Reduction
https://github.com/evolvinglmms-lab/egolife
공식 코드https://github.com/evolvinglmms-lab/lmms-eval
공식 코드https://github.com/explainableml/egocvr
공식 코드EgoCVR: An Egocentric Benchmark for Fine-Grained Composed Video Retrieval
https://github.com/f-ilic/AppearanceFreeActionRecognition
공식 코드https://github.com/f3set/f3set
공식 코드F$^3$Set: Towards Analyzing Fast, Frequent, and Fine-grained Events from Videos
https://github.com/facebookresearch/Ego4d
공식 코드Ego-Exo4D: Understanding Skilled Human Activity from First- and Third-Person Perspectives
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/perception_models
공식 코드PerceptionLM: Open-Access Data and Models for Detailed Visual Understanding
출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.