https://github.com/sunilhoho/everest
공식 코드EVEREST: Efficient Masked Video Autoencoder by Removing Redundant Spatiotemporal Tokens
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/sunoh-kim/pps
공식 코드https://github.com/sunwei925/CompressedVQA
공식 코드https://github.com/sunwei925/SimpleVQA
공식 코드A Deep Learning based No-reference Quality Assessment Model for UGC Videos
https://github.com/sunwei925/dn-piqa
공식 코드https://github.com/sunwei925/minimalisticvqa
공식 코드Analysis of Video Quality Datasets via Design of Minimalistic Video Quality Models
https://github.com/sunwei925/rq-vqa
공식 코드Enhancing Blind Video Quality Assessment with Rich Quality-aware Features
https://github.com/superz678/mg-had
공식 코드https://github.com/svip-lab/weaksvr
공식 코드Weakly Supervised Video Representation Learning with Unaligned Text for Sequential Videos
https://github.com/t-montes/viqagent
공식 코드ViQAgent: Zero-Shot Video Question Answering via Agent with Open-Vocabulary Grounding Validation
https://github.com/taco-group/video-quality-assessment-a-comprehensive-survey
공식 코드https://github.com/tanyjiang/video_cil
공식 코드https://github.com/taufikxu/youtube
공식 코드https://github.com/tavihalperin/AV-sync
공식 코드https://github.com/technomad-ds/lovr-benchmark
공식 코드LoVR: A Benchmark for Long Video Retrieval in Multimodal Contexts
https://github.com/tencent/censeoqoe
공식 코드https://github.com/tencent/hunyuanvideo
공식 코드HunyuanVideo: A Systematic Framework For Large Video Generative Models
https://github.com/tencentarc/seed-bench-r1
공식 코드Exploring the Effect of Reinforcement Learning on Video Understanding: Insights from SEED-Bench-R1
https://github.com/tencentarc/tvts
공식 코드Learning Transferable Spatiotemporal Representations from Natural Script Knowledge
https://github.com/tensorflow/models
공식 코드VideoGLUE: Video General Understanding Evaluation of Foundation Models
https://github.com/tensorflow/models/tree/master/official/vision/beta/projects/assemblenet
공식 코드AssembleNet: Searching for Multi-Stream Neural Connectivity in Video Architectures
https://github.com/tensorssun/rgtr
공식 코드Diversifying Query: Region-Guided Transformer for Temporal Sentence Grounding
https://github.com/thu-nics/framefusion
공식 코드https://github.com/thudm/cogvideo
공식 코드CogVideoX: Text-to-Video Diffusion Models with An Expert Transformer
https://github.com/thudm/cogvlm2
공식 코드CogVLM2: Visual Language Models for Image and Video Understanding
https://github.com/thudm/glm-4
공식 코드CogVLM2: Visual Language Models for Image and Video Understanding
https://github.com/thudm/glm-4.1v-thinking
공식 코드GLM-4.1V-Thinking: Towards Versatile Multimodal Reasoning with Scalable Reinforcement Learning
https://github.com/thudm/visionreward
공식 코드https://github.com/thuml/videodg
공식 코드VideoDG: Generalizing Temporal Relations in Videos to Novel Domains
https://github.com/thunlp-mt/museg
공식 코드MUSEG: Reinforcing Video Temporal Understanding via Timestamp-Aware Multi-Segment Grounding
https://github.com/thunlp-mt/streamingbench
공식 코드StreamingBench: Assessing the Gap for MLLMs to Achieve Streaming Video Understanding
https://github.com/tianyu0207/RTFM
공식 코드Weakly-supervised Video Anomaly Detection with Robust Temporal Feature Magnitude Learning
https://github.com/tianyuan168326/vcs-pytorch
공식 코드A Coding Framework and Benchmark towards Low-Bitrate Video Understanding
https://github.com/tiger-ai-lab/quickvideo
공식 코드QuickVideo: Real-Time Long Video Understanding with System Algorithm Co-Design
https://github.com/timemarker-llm/timemarker
공식 코드https://github.com/timmeinhardt/trackformer
공식 코드출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.