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/yunlong10/awesome-llms-for-video-understanding
공식 코드https://github.com/yuzhms/streaming-video-model
공식 코드https://github.com/yytzsy/SCDM
공식 코드Semantic Conditioned Dynamic Modulation for Temporal Sentence Grounding in Videos
https://github.com/yzy-bupt/SVBench
공식 코드SVBench: A Benchmark with Temporal Multi-Turn Dialogues for Streaming Video Understanding
https://github.com/zackhxn/seriesbench-cvpr2025
공식 코드SeriesBench: A Benchmark for Narrative-Driven Drama Series Understanding
https://github.com/zakopz/LVQ_Database
공식 코드A Neural Network based Framework for Effective Laparoscopic Video Quality Assessment
https://github.com/zcfinal/loveu-cvpr23-aqtc
공식 코드A Solution to CVPR'2023 AQTC Challenge: Video Alignment for Multi-Step Inference
https://github.com/zehuichen123/DDOD
공식 코드https://github.com/zfr00/fact-r1
공식 코드Fact-R1: Towards Explainable Video Misinformation Detection with Deep Reasoning
https://github.com/zhang-can/PAN-PyTorch
공식 코드PAN: Towards Fast Action Recognition via Learning Persistence of Appearance
https://github.com/zhangxj199/tinyllava-video
공식 코드TinyLLaVA-Video: A Simple Framework of Small-scale Large Multimodal Models for Video Understanding
https://github.com/zhangxj199/tinyllava-video-r1
공식 코드TinyLLaVA-Video-R1: Towards Smaller LMMs for Video Reasoning
https://github.com/zhoujiahuan1991/cvpr2025-stop
공식 코드STOP: Integrated Spatial-Temporal Dynamic Prompting for Video Understanding
https://github.com/zhoukanglei/asal_cvqa
공식 코드https://github.com/zhuo-cao/flashvtg
공식 코드FlashVTG: Feature Layering and Adaptive Score Handling Network for Video Temporal Grounding
https://github.com/zhuqianglu/b-vllm
공식 코드B-VLLM: A Vision Large Language Model with Balanced Spatio-Temporal Tokens
https://github.com/zibojia/COCOCO
공식 코드https://github.com/zijialewislu/cvpr2025-decafnet
공식 코드DeCafNet: Delegate and Conquer for Efficient Temporal Grounding in Long Videos
https://github.com/ziplab/longvlm
공식 코드LongVLM: Efficient Long Video Understanding via Large Language Models
https://github.com/zli12321/videohallu
공식 코드VideoHallu: Evaluating and Mitigating Multi-modal Hallucinations on Synthetic Video Understanding
https://github.com/zwx8981/BVQA-2021
공식 코드Blindly Assess Quality of In-the-Wild Videos via Quality-aware Pre-training and Motion Perception
https://github.com/zwx8981/DBCNN-PyTorch
공식 코드Blind Image Quality Assessment Using A Deep Bilinear Convolutional Neural Network
https://github.com/zyj-2000/thqa
공식 코드THQA: A Perceptual Quality Assessment Database for Talking Heads
https://github.com/zzc-1998/ddh-qa
공식 코드DDH-QA: A Dynamic Digital Humans Quality Assessment Database
https://github.com/zzc-1998/md-vqa
공식 코드MD-VQA: Multi-Dimensional Quality Assessment for UGC Live Videos
https://github.com/zzc-1998/vqa_pc
공식 코드Evaluating Point Cloud from Moving Camera Videos: A No-Reference Metric
https://github.com/zzy-zhou/dsec-mos
공식 코드Event-Free Moving Object Segmentation from Moving Ego Vehicle
https://gitlab.com/nct_tso_public/pitfalls_bn
공식 코드https://github.com/2023-MindSpore-1/ms-code-17/tree/main/AVA_cifar
AVA: A Video Dataset of Spatio-temporally Localized Atomic Visual Actions
https://github.com/2023-MindSpore-1/ms-code-217/tree/main/tsm
TSM: Temporal Shift Module for Efficient and Scalable Video Understanding on Edge Device
https://github.com/2023-MindSpore-1/ms-code-7/tree/main/TCN
Time-Contrastive Networks: Self-Supervised Learning from Video
https://github.com/2023-MindSpore-1/ms-code-7/tree/main/tsm
TSM: Temporal Shift Module for Efficient and Scalable Video Understanding on Edge Device
https://github.com/2023-MindSpore-4/Code12/tree/main/d2l/chapter_12_computational-performance
https://github.com/2023-MindSpore-4/Code8/tree/main/AVA_cifar
AVA: A Video Dataset of Spatio-temporally Localized Atomic Visual Actions
https://github.com/2024-MindSpore-1/Code6/tree/main/ADNet
출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.