Papers with Code 아카이브
Video Semantic Segmentation
태스크의 하위 분류와 논문·코드·평가·기법·데이터셋을 탐색하세요.
- 하위 태스크
- 1
- 평가표
- 5
- 보존된 평가 기록
- 26
The goal of video semantic segmentation is to assign a predefined class to each pixel in all frames of a video. This requires the model not only to predict accurate segmentation masks but also to ensure that these masks remain temporally consistent across frames. This task has broad applications in areas such as autonomous driving, medical video analysis, and AR/VR.
코드
관련 논문과 평가 결과에 연결된 구현입니다. 출처에서 확인된 저자 구현에는 공식 코드 표시가 있습니다.
https://github.com/nust-machine-intelligence-laboratory/hpan
공식 코드https://github.com/nust-machine-intelligence-laboratory/hvc
공식 코드Dynamic in Static: Hybrid Visual Correspondence for Self-Supervised Video Object Segmentation
https://github.com/nust-machine-intelligence-laboratory/videomac
공식 코드https://github.com/opengvlab/mutr
공식 코드Referred by Multi-Modality: A Unified Temporal Transformer for Video Object Segmentation
https://github.com/opennlplab/avsbench
공식 코드https://github.com/openseg-group/mlseg
공식 코드RankSeg: Adaptive Pixel Classification with Image Category Ranking for Segmentation
https://github.com/openseg-group/rankseg
공식 코드RankSeg: Adaptive Pixel Classification with Image Category Ranking for Segmentation
https://github.com/pansanity666/INO_VOS
공식 코드In-N-Out Generative Learning for Dense Unsupervised Video Segmentation
https://github.com/pcasolab/vdst-net
공식 코드https://github.com/phiphiphi31/DMB
공식 코드Learning Spatio-Appearance Memory Network for High-Performance Visual Tracking
https://github.com/pinxueguo/x-prompt
공식 코드X-Prompt: Multi-modal Visual Prompt for Video Object Segmentation
https://github.com/pipixin321/holmesvau
공식 코드Holmes-VAU: Towards Long-term Video Anomaly Understanding at Any Granularity
https://github.com/pkyong95/PCVOS
공식 코드https://github.com/ponimatkin/ssl-vos
공식 코드A Simple and Powerful Global Optimization for Unsupervised Video Object Segmentation
https://github.com/rascalgdd/vpseg
공식 코드Vanishing-Point-Guided Video Semantic Segmentation of Driving Scenes
https://github.com/raymondwang987/nvds
공식 코드NVDS+: Towards Efficient and Versatile Neural Stabilizer for Video Depth Estimation
https://github.com/rkzheng99/villa
공식 코드ViLLa: Video Reasoning Segmentation with Large Language Model
https://github.com/robert80203/GSVNet
공식 코드GSVNet: Guided Spatially-Varying Convolution for Fast Semantic Segmentation on Video
https://github.com/robertluo1/iccv2023_rvos_challenge
공식 코드1st Place Solution for 5th LSVOS Challenge: Referring Video Object Segmentation
https://github.com/rongfu-dsb/MPG-SAM2
공식 코드https://github.com/rtous/lester
공식 코드Lester: rotoscope animation through video object segmentation and tracking
https://github.com/sabarim/3DC-Seg
공식 코드Making a Case for 3D Convolutions for Object Segmentation in Videos
https://github.com/sallymmx/TransVOS
공식 코드https://github.com/sam1224/fssam
공식 코드https://github.com/schmiddo/d2conv3d
공식 코드D^2Conv3D: Dynamic Dilated Convolutions for Object Segmentation in Videos
https://github.com/scott-yjyang/vivim
공식 코드https://github.com/segmentationblwx/sssegmentation
공식 코드MCIBI++: Soft Mining Contextual Information Beyond Image for Semantic Segmentation
https://github.com/shaohuadong2021/dplnet
공식 코드Efficient Multimodal Semantic Segmentation via Dual-Prompt Learning
https://github.com/shaoyuanlo/stpl
공식 코드https://github.com/shelhamer/revolver
공식 코드https://github.com/shilinyan99/panovos
공식 코드PanoVOS: Bridging Non-panoramic and Panoramic Views with Transformer for Video Segmentation
https://github.com/showlab/sam-i2v
공식 코드SAM-I2V: Upgrading SAM to Support Promptable Video Segmentation with Less than 0.2% Training Cost
https://github.com/showlab/videolisa
공식 코드One Token to Seg Them All: Language Instructed Reasoning Segmentation in Videos
https://github.com/shuangjiexu/MHP-VOS
공식 코드MHP-VOS: Multiple Hypotheses Propagation for Video Object Segmentation
https://github.com/shvdiwnkozbw/ssl-uvos
공식 코드Betrayed by Attention: A Simple yet Effective Approach for Self-supervised Video Object Segmentation
출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.